project-manager

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 (No Hooks)

Codex does not receive Claude hook-based doc injection. 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)

Situation-based docs:

Backend/CQRS/API/domain/entity changes: backend-patterns-reference.md, domain-entities-reference.md, project-structure-reference.md
Frontend/UI/styling/design-system: frontend-patterns-reference.md, scss-styling-guide.md, design-system/README.md
Spec/test-case planning or TC mapping: feature-docs-reference.md
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.

Quick Summary

Goal: Generate project status reports, track dependencies, manage risks, and facilitate team sync meetings.

Workflow:

Status Reports — Aggregate sprint progress, blockers, velocity from PBIs/PRs/todos
Dependency Tracking — Map inter-feature dependencies and critical path
Risk Management — Score probability x impact (1-9), define mitigations
Team Sync — Generate meeting agendas, track action items and decisions

Key Rules:

MUST ATTENTION READ references/report-templates.md before executing
All data must be current; blockers need owners and actions
Status colors: Green (on track), Yellow (at risk), Red (blocked)

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Project Manager Assistant

Help Project Managers generate status reports, track dependencies, manage risks, and facilitate team synchronization.

Prerequisites

⚠️ MUST ATTENTION READ references/report-templates.md before executing — contains status report template, dependency tracker, risk register, team sync agenda, and sprint ceremony checklists required by all capabilities below.

Core Capabilities

Capability	Command	Key Activities
Status Reports	`$status`	Aggregate sprint progress, summarize completions/blockers, track velocity
Dependency Tracking	`$dependency`	Map inter-feature dependencies, identify critical path, alert on risks
Risk Management	Update register	Score probability x impact, define mitigations, escalate critical
Team Sync	`$team-sync`	Generate agendas, track action items, document decisions

Status Report Generation

Command: $status

Generate from:

PBIs in team-artifacts/pbis/ with in_progress status
Recent PRs and commits
Open blockers in todo lists
Quality gate reports

⚠️ MUST ATTENTION READ: references/report-templates.md for full status report template.

Dependency Tracking

Command: $dependency

Visualize and track upstream/downstream dependencies, external dependencies, and critical path.

⚠️ MUST ATTENTION READ: references/report-templates.md for dependency matrix and tracker template.

Risk Management

Maintain risk register with probability x impact scoring (1-9 scale).

Threshold	Action
7-9 Critical	Escalate to stakeholders, daily review
4-6 High	Active mitigation, weekly review
1-3 Low	Monitor, bi-weekly review

⚠️ MUST ATTENTION READ: references/report-templates.md for risk register template and scoring matrix.

Team Sync Facilitation

Command: $team-sync

Generate meeting agenda covering: sprint health, role updates, blockers, risks, action items.

⚠️ MUST ATTENTION READ: references/report-templates.md for agenda template and sprint ceremonies checklists.

Output Conventions

File Naming

{YYMMDD}-pm-status-sprint-{n}.md
{YYMMDD}-pm-dependency-{feature}.md
{YYMMDD}-pm-risk-register.md
{YYMMDD}-pm-sync-{date}.md

Status Colors

Green: On Track
Yellow: At Risk
Red: Blocked/Critical

Integration Points

When	Trigger	Action
End of day	`$status`	Generate daily status
Sprint start	`$dependency`	Map sprint dependencies
Risk identified	Update register	Score and assign
Before sync	`$team-sync`	Generate agenda

Quality Checklist

All data is current (as of today)
Blockers have owners and actions
Risks are scored and have mitigations
Dependencies are mapped both directions
Status colors accurately reflect health
Action items have owners and due dates

product-owner
planning

References

File	Contents
`references/report-templates.md`	Status report, dependency tracker, risk register, team sync agenda, sprint ceremony checklists

[IMPORTANT] Use task tracking to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

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

Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

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 thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.

MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

Closing Reminders

IMPORTANT MUST ATTENTION break work into small todo tasks using task tracking BEFORE starting IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act) IMPORTANT MUST ATTENTION add a final review todo task to verify work quality MANDATORY IMPORTANT MUST ATTENTION READ the following files before starting: IMPORTANT MUST ATTENTION READ references/report-templates.md before starting

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using task tracking.

Hookless Prompt Protocol Mirror (Auto-Synced)

Source: .claude/hooks/lib/prompt-injections.cjs + .claude/.ck.json

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

DETECT: Match prompt against workflow catalog
ANALYZE: Find best-match workflow AND evaluate if a custom step combination would fit better
ASK (REQUIRED FORMAT): Use a direct user question with this structure:
- Question: "Which workflow do you want to activate?"
- Option 1: "Activate [BestMatch Workflow] (Recommended)"
- Option 2: "Activate custom workflow: [step1 → step2 → ...]" (include one-line rationale)
ACTIVATE (if confirmed): Call $workflow-start <workflowId> for standard; sequence custom steps manually
CREATE TASKS: task tracking for ALL workflow steps
EXECUTE: Follow each step in sequence [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.

Learned Lessons

Lessons

[2026-03-10] Mirror copies create staleness traps. Editing a canonical source is insufficient when mirror copies exist — must trace and update ALL mirrored files (configs, skill definitions, docs). Grep verification after edits catches missed mirrors.
[2026-03-10] Docs embedding derived data stale on source modification. Documentation that inlines data from a canonical source (e.g., workflow sequences, API schemas) goes stale silently when the source changes. Map all docs that embed canonical data and update them alongside the source.
[2026-04-14] Front-load report-write in sub-agent prompts for large reviews. Sub-agents reviewing many files exhaust token budget before writing the final report — all findings lost. Design prompts so: (1) report-write is the explicit first deliverable, (2) findings appended per-file immediately (not batched), (3) scope is bounded. If sub-agent returns truncated output with no report, spawn a new one with narrower scope.
[2026-04-14] After context compaction, re-verify all prior phase outcomes before continuing. Session summaries describe what the AI intended — not what persisted in the environment. When resuming a multi-phase task, the first action must be a state audit: re-check git status, re-read files, verify filesystem state. Treat every "completed" phase claim as an untested hypothesis.

[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:

Name the FAILURE MODE (reasoning/assumption failure), not symptom — "assumed API existed without reading source" not "used wrong enum value".
Generality test: does this failure mode apply to ≥3 contexts/codebases? If not, abstract one level up.
Write as a universal rule — strip project-specific names/paths/classes. Useful on any codebase.
Consolidate: multiple mistakes sharing one failure mode → ONE lesson.
Recurrence gate: "Would this recur in future session WITHOUT this reminder?" — No → skip $learn.
Auto-fix gate: "Could $code-review/$code-simplifier/$security/$lint catch this?" — Yes → improve review skill instead.
BOTH gates pass → ask user to run $learn. [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.

About this skill