requirements-analysis-plus (EN)

Chinese version： See the corresponding Chinese skill.

When to Use

Need deeper requirement analysis across multiple source documents.
Need stronger prioritization, conflict checks, and follow-up questions than the base version.

Read and follow the main prompt listed under Progressive disclosure (coverage, structure, quality bar).
Direct requirement materials remain sufficient for standalone use. If the user supplies role reports with a declared source_role, treat them as optional composition inputs and never require installing a role Skill.
Add only project context that changes the result: scope, environment, constraints, risks, dependencies, expected deliverable.
If input is incomplete, return a usable first draft and explicitly mark assumptions and gaps.
Default to Markdown; switch formats only when the user asks.

Prioritize by risk / business impact — do not treat everything equally.
Separate confirmed facts from current assumptions.
Do not invent endpoints, fields, environments, or root causes the user did not provide.
When using a fact, view, risk, or question from a role report, preserve its source-role attribution item by item; never present a role view as a primary requirement fact or anonymous consensus.
Consume only report content supplied by the user; do not read, link to, or depend on another role Skill's internal files.
Keep output executable: concrete scenarios, clear priority, clear next steps.

Before producing output, read and follow prompts/requirements-analysis-plus.md (minimum coverage, output structure, quality bar).
When a ready-made template fits: use matching files under output-templates/.
When the user wants examples or alignment with existing assets: read relevant examples/.
For deep framework/troubleshoot/schema notes: read only the relevant file(s) under references/, do not load the whole directory.
For format conversion or helper checks: prefer existing scripts/ over reinventing.
For evaluating/regressing this skill: use evals/ with skill-up.

Followed the main prompt's output structure
Minimum coverage focus: source alignment, scope summary, conflicts and inconsistencies, missing rules, testability risks, dependency impacts, business impact, priority by risk, ... (details in main prompt)
Covered the minimum checklist, or explained omissions
High-risk items have explicit priority
Did not invent details the user did not provide
Assumptions and gaps are marked
Findings, risks, and open questions that use role reports retain their source roles
Optional role reports did not become prerequisites and no role Skill internal file was linked