English version: See the corresponding English skill.
When to Use
- When you need to perform deeper requirements analysis based on multiple materials.
- When you need stronger conflict checking, prioritization, and follow-up questions than the basic version.
Script Capability Boundaries
Optional scripts/run_*.py Only prepare parsed input materials or source candidates, output NOT_ASSESSED, do not call models, do not execute the main Prompt, do not generate semantic conclusions, risk priorities, complete use cases, or approvals. Formal analysis is executed by the Agent according to the main Prompt; when you need to run scripts, first read references/script-contract.md。
Execution Flow
- Read and follow the main prompt in "Load on Demand" (coverage checklist, output structure, quality requirements).
- Direct requirements materials can always be used independently; when the user provides a role report with
source_role(source role), treat it as an optional combined input, and do not require additional installation of role Skills. - Only supplement project context that truly affects the result: scope, environment, constraints, risks, dependencies, expected deliverables.
- When information is incomplete, first provide a usable initial version, and explicitly mark assumptions and information gaps.
- Default to Markdown; switch only when the user specifies another format.
Core Constraints
- Prioritize by risk/business impact; do not spread effort evenly.
- Write "confirmed facts" and "current assumptions" separately.
- Do not fabricate interfaces, fields, environments, or root cause details that the user did not provide.
- When using facts, opinions, risks, or issues from role reports, retain the source role for each item; do not pass off role opinions as original requirements facts or unsourced consensus.
- Only consume the report content provided by the user; do not read, link to, or depend on the internal files of other role Skills.
- Results must be actionable: scenarios specific, prioritized, and able to guide the next step.
Load on Demand
- Before producing output, you must read and follow
prompts/requirements-analysis-plus.md(minimum coverage checklist, output structure, quality requirements). - When you need to apply an existing template: read the matching template in
output-templates/, and do not invent a conflicting structure. - When the user wants examples or to benchmark against existing assets: read the relevant samples in
examples/. - When you need in-depth materials such as framework specifications, troubleshooting, or report schema: read only the files in
references/that are relevant to the current issue; do not read through the entire directory. - When you need format conversion or auxiliary validation: prefer using the existing scripts in
scripts/, rather than rewriting them. - When you need to evaluate/regress this skill: use
evals/, and validate and run with skill-up.
Pre-Delivery Self-Check
- Has followed the output structure of the main prompt
- Minimum coverage concerns: source consistency, scope summary, conflicts and inconsistencies, missing rules, testability risks, dependency impact, business impact, risk priority… (details are subject to the main prompt)
- Has covered the minimum checklist, or indicated why it was omitted
- High-risk items have clear priorities
- Has not fabricated details that the user did not provide
- Assumptions and information gaps have been marked
- When using role reports, relevant facts, risks, and open questions all retain their source role
- Optional role reports are not made into required inputs for independent analysis, nor are internal files of the role Skill linked
Common Misconceptions
- When both the scope and context are unclear, do not pretend it is already fully usable.
- Do not write all items as equally important.
- Do not skip assumptions and information gaps.
- Do not output large sections of vague theory unrelated to the current toolchain.