SuperAPI AI Directory
Partner with us中文AI newsFavorites
Skillsbusiness-evaluation

business-evaluation

General & other

View repository

Updated 10-15 21:35

About this skill

Codex compatibility note:

  • Invoke repository skills with $skill-name in Codex; this mirrored copy rewrites legacy Claude /skill-name references.
  • Task tracker mandate: BEFORE executing any workflow or skill step, create/update task tracking for all steps and keep it synchronized as progress changes.
  • User-question prompts mean to ask the user directly in Codex.
  • Ignore Claude-specific mode-switch instructions when they appear.
  • Strict execution contract: when a user explicitly invokes a skill, execute that skill protocol as written.
  • Subagent authorization: when a skill is user-invoked or AI-detected and its protocol requires subagents, that skill activation authorizes use of the required spawn_agent subagent(s) for that task.
  • Do not skip, reorder, or merge protocol steps unless the user explicitly approves the deviation first.
  • For workflow skills, execute each listed child-skill step explicitly and report step-by-step evidence.
  • If a required step/tool cannot run in this environment, stop and ask the user before adapting.

Codex Project-Reference Loading (Hook-Independent)

Claude and Codex use static project-reference loading as the authority; hooks may accelerate discovery but never replace the explicit read. When coding, planning, debugging, testing, or reviewing, open project docs explicitly using this routing.

Always read:

  • docs/project-config.json (project-specific paths, commands, modules, and workflow/test settings)
  • docs/project-reference/docs-index-reference.md (routes to the full docs/project-reference/* catalog)
  • docs/project-reference/lessons.md (always-on guardrails and anti-patterns)

Missing/stale context route: If docs/project-config.json, the docs index, lessons.md, CLAUDE.md, AGENTS.md, or any task-required reference doc is missing or stale, auto-run $project-init or the narrow setup route ($project-config, $docs-init, $scan-all, $scan --target=<key>, $ai-context-refresh) before ordinary project-specific work. A full $sync-codex run preflights CLAUDE.md; a completed $ai-context-refresh run may invoke the standalone runner with --skip=claude-md after final source edits. Markerless roots need AI smart-merge unless portability.requireUniversalGuides: false is explicit.

Situation-based docs:

  • Project structure/architecture/tech-stack/deployment/setup (any layer — backend, frontend, or infra): project-structure-reference.md
  • Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md
  • Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
  • Spec authoring, docs/specs/ pathing, or TC format: feature-spec-reference.md, spec-system-reference.md, spec-principles.md
  • Behavior/public-contract changes or spec-test-code sync: workflow-spec-test-code-cycle-reference.md plus the spec docs above
  • Derived spec indexes/ERDs/reimplementation guides: spec-system-reference.md and source Feature Specs under docs/specs/
  • Integration test implementation/review: integration-test-reference.md
  • E2E test implementation/review: e2e-test-reference.md
  • Code review/audit work: code-review-rules.md plus domain docs above based on changed files

Do not read all docs blindly. Start from docs-index-reference.md, then open only relevant files for the task.

[BLOCKING] Execute declared steps in order. NEVER skip, reorder, or merge without explicit user approval. [BLOCKING] Before each step/sub-skill call, update task tracking: set in_progress at start, completed at end. [BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason. [BLOCKING] If Task tools unavailable, maintain equivalent step tracker with same status transitions.

Quick Summary

Goal: Evaluate business idea viability; deliver evidence-backed viability verdict—score, confidence, Pursue/Pivot/Pause/Pass recommendation—grounded in complete 9-block BMC, 3-year financials + assumptions, 5+ risks with mitigation + residual risk, phased execution + GTM plan, so go/no-go rests on traced evidence, never optimism.

Summary:

  • Order: Seven evaluation steps, preceded by a market-evidence precondition: load market evidence first, then run ALL 7 evaluation steps in order — detect idea/scope/evidence completeness; (1) capture idea (problem/solution/target), (2) 9-block BMC, (3) 3-year financials + assumptions, (4) 5+ risks + mitigation/residual risk, (5) phased execution, (6) GTM, (7) verdict. NEVER skip, reorder, or merge — why: partial evaluation invalidates the decision.
  • Market gate: In workflow parent, read exact MARKET_ANALYSIS_PATH ({plan-dir}/research/market-analysis.md only copy fallback); standalone, use supplied path. If absent, state $market-analysis did not run, mark TAM/SAM/SOM, share, and segment size N/A, cap verdict confidence at 60%; NEVER re-derive sizing.
  • Evidence gate: all 9 BMC blocks cite proof; every financial number has assumption + source; each 5+ risk has mitigation + residual risk; unbacked artifact fails.
  • Decision/output: verdict = 1-10 score + confidence tier (95/80/60/<60%) + basis + Pursue/Pivot/Pause/Pass + key success condition; write to docs/knowledge/strategy/business/{descriptive-slug}.md via enforced .claude/templates/business-evaluation-template.md, then ask the user directly for next route (domain-analysis recommended); NEVER auto-decide, favor skepticism.

Workflow:

Before evaluation — detect + reason: classify supplied idea, scope, and market evidence as present, missing, or ambiguous; for each step run focused Think: evidence / economics / execution / decision passes. Derive concerns from idea + evidence; required blocks/categories guide coverage, not checklist recitation.

Precondition — load market analysis: In workflow-research business-eval mode, read exact parent-provided MARKET_ANALYSIS_PATH ({plan-dir}/research/market-analysis.md only copy fallback); standalone, use explicitly supplied path. Absent → do NOT re-derive: state $market-analysis did not run; mark every market-sizing figure (TAM/SAM/SOM, share, segment size) N/A with that reason; cap verdict confidence at 60%.

  1. Capture idea — Problem, solution, target customer
  2. Business Model Canvas — All 9 blocks with evidence
  3. Financial projections — 3-year revenue, costs, break-even
  4. Risk assessment — 5+ risks with mitigation
  5. Execution plan — 3 phases with milestones
  6. Go-to-market — Launch, channels, pricing rationale
  7. Verdict — Viability score, confidence, recommendation

Key Rules:

  • Require all 9 BMC blocks; each cites evidence
  • Financial projections require explicit assumptions table
  • Require ≥5 risks, each with mitigation AND residual risk
  • Verdict requires evidence + confidence declaration
  • Risk profile: analysis. Fresh-eyes review, specialist routing, inline sub-agent protocols, and recursive quality loops: N/A — not required by this target contract; this skill does not delegate or own fix convergence.

Be skeptical; apply critical/sequential thinking. Every claim needs traced proof + confidence percentage (Idea should be more than 80%).

Business Evaluation

Step 1: Capture the Idea

Extract from user input:

  • One-liner — Elevator pitch in 1 sentence
  • Problem — What pain point does it solve?
  • Solution — How does it solve it?
  • Target customer — Who specifically benefits?

Step 2: Business Model Canvas

Require all 9 blocks:

Block Key Question Evidence Required
Customer Segments Who are we serving? Market research
Value Propositions What value do we deliver? Customer pain points
Channels How do we reach customers? Channel analysis
Customer Relationships How do we maintain relationships? Retention strategy
Revenue Streams How do we make money? Pricing research
Key Resources What do we need? Resource assessment
Key Activities What must we do? Operational analysis
Key Partnerships Who helps us? Partner landscape
Cost Structure What does it cost? Cost analysis

Step 3: Financial Projections (3 Years)

Revenue Model

Year Users/Customers ARPU Revenue Growth

Cost Structure

Category Y1 Y2 Y3

Break-Even

  • Monthly burn: ${X}
  • Break-even point: Month/Year
  • Funding needed: ${X}

Assumptions Table

Every number lists its assumption + source.

Step 4: Risk Assessment

Require ≥5 risks:

Risk Likelihood Impact Mitigation Residual Risk

Consider market, execution, financial, competitive, regulatory, technical.

Step 5: Execution Plan

Phase Timeline Focus Key Milestones
Validation 0-3 months Customer discovery, MVP N interviews, prototype
Build 3-6 months Core product, early users Beta launch, first revenue
Growth 6-12 months Scale, optimize Revenue target, team size

Step 6: Go-to-Market

  • Launch strategy — How to enter market
  • Initial channels — Top 3 acquisition channels
  • Pricing strategy — Model + rationale + competitive comparison

Step 7: Verdict

  • Viability score: 1-10 with rationale
  • Confidence: 95%/80%/60%/<60% with evidence basis
  • Recommendation: Pursue | Pivot | Pause | Pass
  • Key condition: What must be true for this to succeed?

Output

Write to docs/knowledge/strategy/business/{descriptive-slug}.md using enforced template from .claude/templates/business-evaluation-template.md.

Next Steps

MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS After completion, use ask the user directly to present these options. Do NOT skip because the task seems "simple" or "obvious"—the user decides:

  • "$domain-analysis (Recommended)" — Analyze domain model from business evaluation
  • "$plan" — If ready to plan implementation
  • "Skip, continue manually" — user decides

[IMPORTANT] Use task tracking to split ALL work into small tasks BEFORE starting.

External Memory: For complex/lengthy research, analysis, scans, or reviews, write intermediate findings + final results to tmp/reports/—preserves context and serves as deliverable.

Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION—every claim, finding, and recommendation requires file:line proof or traced evidence + confidence percentage (>80% act; <80% verify first).

AI Mistake Prevention — Failure modes to avoid on every task:

ROOT-CAUSE GATE — INVESTIGATE FIRST. Before applying any project-related correction, always use the project's root-cause investigation protocol and establish the cause; the failure site may be only a symptom. FAILED-TEST GATE. For any failed or unstable test, use the project's test-investigation protocol before editing source or tests; never change either side merely to force green. Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting. Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect. Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk. Assert the outcome your system owns, not the intermediate state your infrastructure owns. When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. Store disposable generated output in the project workspace. If an output can be regenerated and is not source code, a canonical source-of-truth, or an intentionally versioned projection, write it under the project-root tmp/ or temp/ directory (prefer tmp/), scoped to the run. This includes temporary state, integration/E2E results, reports, logs, screenshots, traces, videos, coverage, dumps, and candidate evidence. Never put these outputs in source, docs, plans/, team-artifacts/, or mirror directories; the project-root .gitignore must ignore /tmp/ and /temp/ by default. Committed fixtures, accepted baselines, canonical specs/docs, and explicitly versioned generated mirrors remain at their declared owner paths. Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.

MUST ATTENTION ROOT-CAUSE GATE: before any project-related correction, use the appropriate root-cause investigation protocol; failed/unstable tests require the test-investigation protocol before editing source/tests — never force green.

Prompt-Enhance Closing Anchors

IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval IMPORTANT MUST ATTENTION for every step/sub-skill call: set in_progress before execution, set completed after execution IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses

Project Protocol Overlay — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the Target column of the project's skill-protocol index (docs/project-reference/skill-protocols-reference.md by default; a referenceDocs entry in docs/project-config.json overrides the path), taking the most specific matching tier ONLY — exact name > glob > *. That precedence orders overlays against EACH OTHER, never against this skill. Read ONLY the matched bodies, resolved as <protocols-dir>/<Name>.md; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: .claude/skills/project-skill-protocol/references/registry.md.

Overlays are ADDITIVE ONLY: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently.

MUST ATTENTION resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > *, which ranks overlays against each other, NEVER against this skill), read only matched bodies at <protocols-dir>/<Name>.md; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user.

Closing Reminders

IMPORTANT MUST ATTENTION Goal: Evaluate business idea viability; deliver evidence-backed viability verdict—score, confidence, Pursue/Pivot/Pause/Pass recommendation—grounded in complete 9-block BMC, 3-year financials + assumptions, 5+ risks with mitigation + residual risk, phased execution + GTM plan, so go/no-go rests on traced evidence, never optimism.

MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries):

  • AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
  • Critical Thinking: traced file:line proof, confidence >80% to act, NEVER guess as fact.

IMPORTANT MUST ATTENTION every claim, financial number, BMC block, and verdict carries evidence + confidence % (95/80/60/<60) — NEVER present a guess as fact — why: an unbacked number turns the go/no-go into optimism dressed as analysis. IMPORTANT MUST ATTENTION bias toward skepticism on the verdict — NEVER round optimism up; surface the single key condition that must hold and the residual risk if it fails — why: a falsely-rosy Pursue burns capital that an honest Pause would save. IMPORTANT MUST ATTENTION validate the next route with user by asking the user directly — NEVER auto-decide domain-analysis/plan — why: this skill judges viability, the human owns the go/no-go.

MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting; keep one in_progress, mark completed with evidence; add a final review todo — why: untracked multi-step work loses state on compaction. MANDATORY IMPORTANT MUST ATTENTION consume market data FROM market-analysis as evidence — NEVER re-derive market sizing here; if that producer did not run, mark the market figures N/A with the reason and cap verdict confidence at 60% rather than inventing them — why: this skill judges viability, it does not research the market; duplicated sizing diverges from the source. MANDATORY IMPORTANT MUST ATTENTION all 9 BMC blocks present, each citing proof; every financial number lists its assumption + source in the assumptions table — why: a missing block or bare number is a silent gap the verdict then rests on. MANDATORY IMPORTANT MUST ATTENTION minimum 5 risks, each with mitigation AND a residual-risk entry across market/execution/financial/competitive/regulatory/technical — why: a risk without residual pretends mitigation is total. MANDATORY IMPORTANT MUST ATTENTION detect idea/scope/evidence completeness; load exact market-analysis evidence first (parent MARKET_ANALYSIS_PATH; {plan-dir}/research/market-analysis.md copy fallback; supplied standalone path; absent → market figures N/A + confidence cap 60%); then run ALL 7 steps in order: idea → 9-block BMC → 3-year financials → 5+ risks → 3-phase execution → GTM → verdict; output via template; ask the user directly for next route. NEVER re-derive sizing, skip/reorder/merge steps, drop financials/execution/GTM, or auto-decide — why: verdict quality follows the weakest step/evidence. MANDATORY IMPORTANT MUST ATTENTION before writing any figure or claim, search market-analysis output + prior evaluations for 3+ comparable patterns and cite them — why: a number with no comparable anchor is a fabrication. MANDATORY IMPORTANT MUST ATTENTION write the result to docs/knowledge/strategy/business/{descriptive-slug}.md via the enforced .claude/templates/business-evaluation-template.md — NEVER hand-roll the structure — why: the template is the contract downstream skills (domain-analysis/plan) read. MANDATORY IMPORTANT MUST ATTENTION persist intermediate findings to tmp/reports/ for lengthy evaluations — why: external memory survives context loss and serves as the deliverable.

Anti-Rationalization:

Evasion Rebuttal
"Idea is obviously viable, skip rigor" Optimism is not evidence. Run all 9 blocks + financials + risks anyway.
"Skip a BMC block — not relevant" Every block cites proof or states why N/A explicitly; silent omission fails the gate.
"Estimate the number, source it later" No assumption + source = no number. Fill the assumptions table before the verdict.
"5 risks is a lot, 2 covers it" Minimum 5, each with residual risk. Thin risk lists hide the real downside.
"Recommendation is clear, skip the ask" Still ask the user directly for the next route — the human owns go/no-go.

IMPORTANT MUST ATTENTION evidence + confidence % on every number — NEVER present a guess as fact. IMPORTANT MUST ATTENTION bias toward skepticism — NEVER round optimism up. IMPORTANT MUST ATTENTION ask the user directly for the next route — NEVER auto-decide.

Static Prompt Protocol Mirror (Auto-Synced)

Source: .claude/.ck.json + .claude/skills/shared/sync-inline-versions.md (:full blocks) + .claude/scripts/lib/hookless-prompt-protocol.cjs (legacy filename; static protocol composer)

[WORKFLOW-EXECUTION-PROTOCOL] [BLOCKING] Workflow Execution Protocol — MANDATORY IMPORTANT MUST CRITICAL. Do not skip for any reason.

Generic portability boundary: Reusable skills and protocol text stay project-neutral; project-specific conventions are discovered from docs/project-config.json and docs/project-reference/. Apply shared AI-SDD from shared/sdd-artifact-contract.md. Read docs/project-config.json and docs/project-reference/docs-index-reference.md, then open the project reference docs named there immediately before the first target read, grep, edit, test, or analysis. For spec, test-case, behavior-change, public-contract, or docs/specs/ work, route through the local spec docs named by the docs index: feature-spec-reference.md, spec-system-reference.md, spec-principles.md, and workflow-spec-test-code-cycle-reference.md when specs/tests/code must stay synchronized. If either file or a required reference doc is missing or stale, auto-run $project-init (or the narrow lower-level route such as $project-config, $docs-init, $scan-all, or $scan --target=<key>) before ordinary project-specific work. After compaction, resume, delegation, or a material context change, re-read the required docs and state Reference docs read: ... | Not applicable: ...; a hook reminder or prior conversation is not proof that the files are loaded. Any supported AI tool may execute when this shared context and local docs are available.

  1. DETECT: If the prompt starts with an explicit slash skill/workflow command, execute it directly. Otherwise match the prompt against the workflow catalog and skill list.
  2. ANALYZE: Choose the best option: execute directly, invoke a skill, activate a standard workflow, or compose a custom step combination.
  3. AUTO-SELECT: Pick the best option yourself. Do not ask the user to choose between direct execution, skill, standard workflow, or custom workflow.
  4. ACTIVATE: For a selected workflow, call $start-workflow <workflowId>; for a selected skill, invoke that skill; for a custom workflow, sequence custom steps directly; for direct execution, proceed with the task.
  5. CREATE TASKS: task tracking for ALL workflow/skill/custom steps before execution when the selected path has multiple steps.
  6. PARALLELIZE: Before executing the task list, tag each task PAR (independent inputs + write set disjoint from every other PAR task) or SEQ (name the blocking dependency), group PAR tasks into waves, declare the wave plan, and spawn each wave's sub-agents in ONE message — all-return barrier per wave, fan-out one level deep unless a sub-agent's own definition authorizes further fan-out. Sequential-by-default is a defect when tasks are independent; do not parallelize shared write targets, output-consuming tasks, trivial single-file work, ordering a skill or workflow explicitly fixes, or user-approval gates.
  7. EXECUTE: Advance per the Workflow Step Advancement & Parallel Phases rule in your context instructions — model-driven; a sub-agent completion advances a step identically to an inline call; a parallel-phase group is an all-return barrier (advance only after ALL members return, never serialize it)

Shared AI-SDD Protocol Markers

Source: .claude/skills/shared/sync-inline-versions.md

SYNC:ai-sdd-artifact-contract

AI-SDD Artifact Contract — Shared spec-driven development rules stay portable and source-owned.

  1. Keep reusable AI-SDD principles in .claude; put repository-specific paths, commands, owners, products, and formats in project config/reference docs.
  2. Preserve cycle: spec -> plan -> tasks -> implement -> verify -> update spec/docs.
  3. Trace every requirement or invariant through decision, task, TC/test, source evidence, and docs/spec update.
  4. Treat code-to-spec extraction as reference-only until accepted by the canonical spec owner.
  5. Any supported AI tool may plan, implement, review, or verify with synced context; using multiple tools is optional.
  6. Update .claude source first, then sync generated mirrors; do not manually edit .agents, .codex, or AGENTS.md. — why: mirrors are generated artifacts; hand-edits are overwritten on the next sync
  7. If docs/project-config.json, root instruction files, or a required project-reference doc is missing or stale, auto-run $project-init or the narrow lower-level route before ordinary project-specific work.

Active reference: shared/sdd-artifact-contract.md in the active skills root.

SYNC:ai-sdd-artifact-contract:reminder

  • MANDATORY Apply shared/sdd-artifact-contract.md; keep reusable AI-SDD in .claude and local rules in project docs.
  • MANDATORY Code-to-spec extraction is reference-only until canonical acceptance; any supported AI tool may execute with synced context.
  • MANDATORY Update .claude source before syncing generated mirrors; do not manually edit .agents, .codex, or AGENTS.md.
  • MANDATORY Missing or stale project config, root instruction files, or required reference docs route project-specific work through $project-init or the narrow setup route automatically. [TASK-PLANNING] [MANDATORY] BEFORE executing any workflow or skill step, create/update task tracking for all planned steps, then keep it synchronized as each step starts/completes.

[LESSON-LEARNED-REMINDER] [BLOCKING] Task Planning & Continuous Improvement — MANDATORY. Do not skip.

Break work into small tasks (task tracking) before starting. Add final task: "Analyze AI mistakes & lessons learned".

Extract lessons — ROOT CAUSE ONLY, not symptom fixes:

  1. Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
  2. Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
  3. Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
  4. Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
  5. Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
  6. Auto-fix gate: "Could $code-review/$code-simplifier/$security-review/$lint catch this?" — Yes → improve review skill instead.
  7. BOTH gates pass → ask user to run $learn. [CRITICAL-THINKING-MINDSET] Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination principle: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. AI Attention principle (Primacy-Recency): Put the 3 most critical rules at both top and bottom of long prompts/protocols so instruction adherence survives long context windows. Goal-driven execution: Define success criteria first, loop until verified, and stop only when observable checks pass. Tests verify intent: Tests must protect business rules/invariants and fail when the protected intent breaks, not only mirror current behavior.

Common AI Mistake Prevention (System Lessons)

  • ROOT-CAUSE GATE — INVESTIGATE FIRST. Before applying any project-related correction, always use the project's root-cause investigation protocol and establish the cause; the failure site may be only a symptom.
  • FAILED-TEST GATE. For any failed or unstable test, use the project's test-investigation protocol before editing source or tests; never change either side merely to force green.
  • Re-read files after context compaction. Edit requires prior Read in same context; compaction wipes read state. Re-read before editing.
  • Grep for old terms after bulk replacements. AI over-trusts find/replace completeness. Grep full repo after bulk edits for missed refs in docs/configs/catalogs.
  • Check downstream references before deleting. Deletions cascade doc/code staleness. Map referencing files before removal.
  • After memory loss, check existing state before creating new. Compaction wipes prior-work memory. Query current state to resume — never blindly duplicate.
  • Verify AI-generated content against actual code. AI hallucinates APIs, class names, method signatures. Grep to confirm existence before documenting/referencing.
  • Trace full dependency chain after edits. Changing a definition misses downstream consumers. Trace the full chain.
  • When renaming, grep ALL consumer file types. Some file types silently ignore missing refs (no compile error). Search code, templates, configs, generated files.
  • Trace ALL code paths when verifying correctness. Code existing ≠ code executing. Trace early exits, error branches, conditional skips — not just happy path.
  • Update docs that embed canonical data when source changes. Docs inlining derived data (workflows, schemas, configs) go stale silently. Update all embedding docs alongside source.
  • Verify sub-agent results after context recovery. Background agents may finish while parent compacted — grep-verify output, don't trust assumed completion.
  • Cross-check full target list against sub-agent assignments. Parallel sub-agents by category miss boundary items. Reconcile union of assignments against target list before proceeding.
  • Sub-agents inherit knowledge only from their agent .md definition — use custom agent types, not built-in Explore. Tool adoption = permission + knowledge + enforcement (numbered workflow step).
  • Persist sub-agent findings incrementally, not as a final batch. Long sub-agents hit cutoffs before final write — findings lost. Instruct append-per-section to report file.
  • Ownership before action. When investigating a failure, ask which part owns the behavior before changing anything. Trace the wrong state to the component responsible for its invariant, then make one authoritative correction there.
  • Test failure → record a provisional verdict before trace/edit, then investigate. Use the full five-way taxonomy: SOURCE-WRONG (production violates intent), TEST-WRONG (assertion/setup is stale), TEST-NOT-OPTIMAL (valid but fragile or low-signal test), ENVIRONMENT-BLOCKED (external state prevents a verdict), or AMBIGUOUS (intent/evidence cannot choose safely). Then trace root cause and triangulate against the governing spec (docs/specs/** if one exists) AND source. NEVER weaken an assertion, add a skip, relax a timeout, or change source merely to force green.
  • Grep ALL removed names after extraction/refactoring. Primary file "done" ≠ secondary files clean. Grep entire scope for every removed symbol before declaring complete.
  • Assume existing values are intentional — ask WHY before changing OR flagging one as a defect. Pattern-matching as "wrong" skips context. Before changing or reporting any constant/limit/flag/cutoff: read comments, git blame, the CALLER's ordering (the guarantee that makes the value correct usually lives in code running immediately BEFORE the cited line), and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard — and in a validation pass, an accurate file:line citation proves the transcription, never the defect.
  • Verify ALL affected outputs, not just the first. One build green ≠ all green. Multi-stack changes (backend/frontend/tests/docs) require verifying EVERY output.
  • Evaluate fit before copying a nearby pattern. Closest example ≠ matching preconditions — verify the new context shares the same constraints, base classes, scope, lifetime.
  • Holistic analysis — resist the nearest-attention trap. Do not dive into the first plausible cause. List every precondition (configuration, environment, inputs, dependencies, versions, permissions, and state). Verify each against evidence, not intuition. Ask "what would falsify this?" — if nothing, it is not a hypothesis. The most expensive failure is going deeper into an assumed area while the real issue sits in an unexamined condition.
  • Minimal changes — apply the relevance test. Every change must trace to the reported problem; avoid unrelated cleanup. For review or enhancement work, announce improvements beyond the main request rather than silently expanding scope. Ask: "Would this change exist if I were not addressing this request?" — if not, remove it or disclose it.
  • Surface ambiguity before coding — don't pick silently. Multiple valid interpretations → present each with effort: "[Request] could mean (1) [N h], (2) [N h]. Which matters?" List scope/format/volume/constraints assumptions first. If simpler path exists, say so. Never silently pick.
  • [MANDATORY FIRST ACTION] ALWAYS activate a suitable skill or workflow BEFORE responding. Match task against workflow catalog + skill list; invoke via skill invocation or $start-workflow <workflowId>. NEVER answer or write code before checking. Skip = protocol violation.
  • Why-Review adversarial mindset — apply when reviewing any plan, decision, or design. Default SKEPTIC not VALIDATOR: steel-man a rejected alternative, invert each stated reason ("what does it sacrifice?"), stress-test top 2-3 assumptions, run pre-mortem ("ships, fails in 3 months — what breaks?"), surface 1-2 alternatives author missed. Section presence ≠ quality; quality = causal reasoning + concrete mitigations + evidence, not "it's better" or "monitor closely".
  • Front-load report-write in sub-agent prompts for large reviews. Many-file sub-agents hit budget before final write — findings lost. Design prompts so: (1) report-write is first explicit deliverable, (2) append per-file/section (not batched), (3) scope bounded so reads don't exhaust budget. Truncated mid-sentence with no report file → spawn narrower scope, don't retry same prompt.
  • After context compaction, re-verify all prior phase outcomes before continuing. Summaries describe intent, not environment state (git index, filesystem, processes). On resume, FIRST audit: git status, re-read modified files, verify filesystem. Every "completed" claim is an untested hypothesis until evidence confirms.
  • OOM/memory: check row count before row size. Triage: (1) Unbounded query — no DB filter for trigger? Push filter to DB; eliminates OOM. (2) Large rows? Projection reduces proportionally. Row reduction > projection in ROI.
  • Assert the outcome your system OWNS, never the intermediate state your INFRASTRUCTURE owns. When testing anything asynchronous (queue/broker delivery, retries, background jobs, caches, replication), assert the final business/entity state. NEVER assert the delivery bookkeeping — consume/send status, attempt counts, last-error, row existence or counts in a broker, scheduler, or outbox/inbox table. That bookkeeping lives in shared infrastructure that ANY co-running process (a peer worker, a second replica, a leftover local container) can write, usually under a deterministic shared key, so the assertion silently tests the developer's environment instead of the system: green when run alone, flaky the instant anything else shares that broker + database. Gate question for every assertion: "would this hold no matter WHICH process did the work?" — if no, assert the converged data state instead. Corollary: process-local fault injection and in-process telemetry cannot gate work any process may perform — use them as stress amplifiers (arm → bounded window → disarm → assert convergence), never as preconditions.
  • Store disposable generated output in the project workspace. If an output can be regenerated and is not source code, a canonical source-of-truth, or an intentionally versioned projection, write it under the project-root tmp/ or temp/ directory (prefer tmp/), scoped to the run. This includes temporary state, integration/E2E results, reports, logs, screenshots, traces, videos, coverage, dumps, and candidate evidence. Never put these outputs in source, docs, plans/, team-artifacts/, or mirror directories; the project-root .gitignore must ignore /tmp/ and /temp/ by default. Committed fixtures, accepted baselines, canonical specs/docs, and explicitly versioned generated mirrors remain at their declared owner paths.
  • Keep domain concepts out of generic/shared/infrastructure layers. Reusable layer (shared library, framework, infra module) must reference NO consumer-specific domain concept — tenant/customer/product IDs, business entities, feature rules. Leak compiles + runs → passes review silently while coupling the "reusable" layer to one consumer. Keep shared type domain-free; push domain fields/logic down into the consumer via subclass/composition. — why: a layer coupled to one consumer's domain is no longer reusable.