mjmorales/skills/docs-writer
skills/docs-writer/SKILL.md
--- name: docs-writer description: Generate human-readable documentation (READMEs, guides, API references, contributor docs). Triggers: "document this", "write docs", "create a README", "write a guide for". --- # Docs Writer Delegate writing to the `technical-writer` subagent. Follow `references/interaction-patterns.md` for all `AskUserQuestion` usage. ## Workflow 1. Identify subject type and audience 2. Gather context -- targeted reads, single pass 3. Delegate to `technical-writer` with str
$ install --global
skillsauthnpx skillsauth add mjmorales/claude-prove skills/docs-writerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 5:59 AM3.9s1 file scanned
SKILL.md
- name:
- docs-writer
- description:
- Generate human-readable documentation (READMEs, guides, API references, contributor docs). Triggers: "document this", "write docs", "create a README", "write a guide for".
Docs Writer
Delegate writing to the technical-writer subagent. Follow references/interaction-patterns.md for all AskUserQuestion usage.
Workflow
- Identify subject type and audience
- Gather context -- targeted reads, single pass
- Delegate to
technical-writerwith structured prompt - Validate output against checklist below
Subject Identification
AskUserQuestion header "Subject" if ambiguous. For <=3 choices, include "Research & proceed".
| Subject | Indicators | Key Sections | |---------|------------|--------------| | Project | Root directory, package.json, multiple components | Quick start, usage, architecture, config | | API | HTTP handlers, REST/GraphQL endpoints | Endpoints, request/response, errors, examples | | Module | Package exports, public interfaces | Installation, API surface, examples | | Script | Executable file, CLI flags | Usage, flags table, examples | | Workflow | Multi-step process, multiple tools | Prerequisites, steps, troubleshooting |
Audience Identification
AskUserQuestion header "Audience" if ambiguous. For <=3 choices, include "Research & proceed".
| Audience | Tone | Depth | Assumes | |----------|------|-------|---------| | Contributor | Casual, direct | Deep on internals | Tech stack familiarity | | Consumer | Precise, professional | Interface-level only | No internal knowledge | | Operator | Practical, task-oriented | Config and operations | Infra/deployment experience | | End user | Friendly, no jargon | Surface-level | Minimal technical background |
Context Gathering
- Grep to locate targets, then read specific lines
- Document public interface only -- never follow imports recursively
- Complete all reads before delegating
Delegation to technical-writer
Invoke with:
Document [SUBJECT_TYPE]: [SUBJECT_NAME]
Audience: [AUDIENCE_TYPE]
Source: [FILE_PATH]:[LINE_RANGE]
Context:
[MINIMAL RELEVANT CODE/CONFIG]
Requirements:
- Output: [project-readme | api-reference | module-docs | script-docs | workflow-guide]
- Audience: [contributor | consumer | operator | end-user]
- Include: [sections beyond the standard template only]
- Format: Markdown, no YAML frontmatter unless docs system requires it
Include: lists only subject-specific sections the template does not cover by default.
Prove Plugin Documentation
| Component | Document | |-----------|----------| | Skills | Purpose, when to use, workflow phases, interaction points | | Agents | Role, invocation triggers, output format | | Commands | What it does, arguments, delegated skill | | Scripts | Usage, flags, output format, examples |
Reference .claude/.prove.json scopes for canonical component list.
Output Validation Checklist
Verify before accepting technical-writer output:
- [ ] Title states what the subject is
- [ ] First paragraph answers "what is this and why use it?"
- [ ] Examples are concrete and runnable (no
foo/bar/...) - [ ] Headings create a scannable outline
- [ ] Structured data uses tables, not prose
- [ ] No unexplained jargon on first use
- [ ] No redundant content across sections
- [ ] Tone matches target audience
AskUserQuestion header "Quality": "Approve" / "Revise".
Anti-Patterns
| Anti-Pattern | Instead |
|--------------|---------|
| Reading entire files | Grep target, read specific lines |
| Re-listing template sections in Include: | Only add non-default sections |
| Interleaving gathering and writing | Complete all reads before delegating |
| Omitting audience from prompt | Always include Audience: |
Committing
Delegate to commit skill. Example: docs(docs-writer): add README for cafi tool
Related Skills
mjmorales/smart-compaction
testing
VerifiedTrustedCommunity
Anchor session context into prove primitives before compaction and rehydrate from them after. Built-in compaction summarizes by recency and drops the claude-prove state an agent needs to reorient; this skill externalizes volatile context into durable anchors (scrum tasks, decisions, run-state, a compact-anchors pointer file) pre-compact, then runs a deterministic reorientation sequence post-compact. Use before a manual /compact, when context is about to auto-compact, or immediately after a compaction. Triggers on "smart compact", "prepare for compaction", "anchor before compact", "context is getting long", "rehydrate", "reorient after compact".
2SKILL.mdUpdated Jun 5, 2026
mjmorales/run-migrate
tools
VerifiedTrustedCommunity
Apply model-driven CONTENT reshaping to stored run artifacts that sit behind the current schema, on explicit operator invocation only. Triggers on "migrate runs", "migrate run artifacts", "run content migration", "reshape run artifacts", "bring runs to current schema". You are the driver: the `run-state migrate-runs` CLI mechanically detects which artifacts are behind and emits a plan naming each one plus its migration-instruction file; you read the instructions and reshape the prose/findings, gated by the operator. The deterministic `schema migrate` handles structural column moves; this skill covers only the content reshaping beyond them. Never run as a background or resident loop — only when the operator asks.
2SKILL.mdUpdated Jun 5, 2026
mjmorales/reasoning-brief
tools
VerifiedTrustedCommunity
Synthesize the 7-section risk-forward Review Brief from a run's reasoning log. Triggers on "reasoning brief", "review brief", "synthesize the brief", "generate the brief", "brief the run", "brief for review", "story brief". You are the driver: the `acb brief` CLI renders a mechanical preservation-safe backbone and proves preservation; you synthesize the narrative prose (summary + changes), single-pass or multipass over episode chunks, then gate it through Stage-1 (mechanical, blocking) and Stage-2 (prose judge, advisory).
2SKILL.mdUpdated Jun 5, 2026
mjmorales/plugin-cache-cleanup
tools
VerifiedTrustedCommunity
Prune stale cached versions of the prove plugin from Claude Code's plugin cache. Use when superseded versions pile up under plugins/cache and agents read stale skills/references from them, or when reclaiming plugin-cache disk space. Triggers on "clean up cached plugin versions", "prune the plugin cache", "remove old prove versions", "stale plugin cache".
2SKILL.mdUpdated Jun 5, 2026