Analyze scope and delegate to docs-writer and/or agentic-doc-writer. Triggers on "auto docs", "document everything", "generate docs".
From provenpx claudepluginhub mjmorales/claude-prove --plugin proveThis skill uses the workspace's default tool permissions.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Analyzes BMad project state from catalog CSV, configs, artifacts, and query to recommend next skills or answer questions. Useful for help requests, 'what next', or starting BMad.
Orchestrate documentation generation by resolving scope, classifying subjects, and delegating to docs-writer and/or agentic-doc-writer. Follow references/interaction-patterns.md for all AskUserQuestion usage.
| Input | Resolution |
|---|---|
| No argument | Session context: files read, written, edited, or discussed |
| Topic name (e.g., "auth", "cafi") | Grep/Glob for matching files/packages/modules |
| Directory path | All exported/public code in that directory |
| File path(s) | Those specific files |
If ambiguous, AskUserQuestion header "Scope": "This session" / "Directory" / "Specific files".
Skip: test files, lock files, build artifacts, self-documenting configs.
| Subject Type | Indicators | Human Docs | Agent Docs |
|---|---|---|---|
| Agent (agents/*.md) | tools:/model: frontmatter | No | Yes |
| Skill (skills/*/SKILL.md) | name: frontmatter, workflow | Yes | Yes |
| Command (commands/*.md) | description: frontmatter | Yes | No |
| Script (scripts/*.sh) | Executable, CLI flags | Yes | Only if agents invoke it |
| Package/Module (src/, lib/) | Exports, public API | Yes | Yes |
| Config (.json, .yaml) | Schema, options | Yes | Only if agents read it |
AskUserQuestion header "Doc Types":
If "Let me pick per subject": follow up with per-subject AskUserQuestion.
Audience (human docs): If not obvious, AskUserQuestion header "Audience": "Contributor" / "Consumer" / "Operator".
Output location: AskUserQuestion header "Output":
Order: agent docs first (define contracts), then human docs (can reference contracts). Within each type, core modules before consumers.
Document [SUBJECT_TYPE]: [SUBJECT_NAME]
Audience: [AUDIENCE]
Source: [FILE_PATH]
Output: [OUTPUT_PATH]
Context:
[MINIMAL RELEVANT CODE/CONFIG]
Document [SUBJECT_TYPE]: [SUBJECT_NAME]
Source: [FILE_PATH]
Output: [OUTPUT_PATH]
Context:
[MINIMAL RELEVANT CODE/CONFIG]
Present summary table of generated docs (subject, human/agent, path, file count).
AskUserQuestion header "Review": "Approve all" / "Revise" / "Discard".
Delegate to commit skill. Example: docs(auto-docs): generate human and agent docs for cafi