mjmorales/spec-writer
skills/spec-writer/SKILL.md
Create, revise, and audit technical specifications following RFC/IETF conventions. Use when the user wants to write a new spec, edit an existing spec, review a spec for completeness, or formalize a design decision into a specification document. Triggers on "write a spec", "spec for", "formalize this", "draft a specification", "audit this spec", "revise the spec", "protocol spec", "format spec", or any request to create structured technical documentation with normative requirements. Also triggers when the user has a brainstorm decision record they want to turn into a formal spec.
$ install --global
skillsauthnpx skillsauth add mjmorales/claude-prove spec-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 24, 2026, 8:51 PM1.8s1 file scanned
SKILL.md
- name:
- spec-writer
- description:
- Create, revise, and audit technical specifications following RFC/IETF conventions. Use when the user wants to write a new spec, edit an existing spec, review a spec for completeness, or formalize a design decision into a specification document. Triggers on "write a spec", "spec for", "formalize this", "draft a specification", "audit this spec", "revise the spec", "protocol spec", "format spec", or any request to create structured technical documentation with normative requirements. Also triggers when the user has a brainstorm decision record they want to turn into a formal spec.
Spec Writer
Orchestrate spec lifecycle (create, revise, audit). Delegate all writing to the spec-writer agent.
Workflow
Step 1: Determine Mode
If not obvious from context, use AskUserQuestion (header "Mode") with "Research & proceed" per references/interaction-patterns.md:
- New Draft — from user description, decision records, or conversation context
- Revise — edit existing spec (user provides path or search
specs/) - Audit — review for completeness, ambiguity, consistency without modifying
Default to Revise if $ARGUMENTS points to a .spec.md file. Default to New Draft if it references a .prove/decisions/ record.
Step 2: Gather Context
New Draft:
- Read referenced decision records; extract chosen option and design details
- Check
specs/for related specs to cross-reference - Confirm scope with user (what it covers, what it excludes)
Revise:
- Read the spec in full
- Clarify desired changes (additions, removals, clarifications, restructuring)
- Determine version bump: major (breaking) or minor (additive/clarification)
Audit:
- Read the spec in full
- Optionally read related specs for cross-reference consistency
Step 3: Delegate to spec-writer Agent
Launch with a structured prompt. The agent handles RFC conventions, section structure, terminology, and self-auditing.
New Draft:
Mode: New Draft
Subject: [title]
Version: 0.1 (Draft)
Input context: [decision records, brainstorm notes, or requirements]
Scope:
- In scope: [what the spec defines]
- Out of scope: [what it excludes]
Related specs: [existing specs in specs/ to cross-reference]
Write to: specs/[slug].spec.md
Revise:
Mode: Revise
Spec path: specs/[name].spec.md
Current version: [X.Y]
Changes requested: [what to add, remove, or modify]
Version bump: [major | minor]
Update in place.
Audit:
Mode: Audit
Spec path: specs/[name].spec.md
Run the full Completeness Checklist. Report findings as:
- Location (section number or line)
- Issue description
- Severity (Critical / Important / Improvement)
- Suggested fix
Do not modify the spec.
Step 4: Review Output
New Draft: Verify file at specs/[slug].spec.md follows expected structure (Purpose, Scope, Terminology, Conformance, normative body, Change Log). Report location and version.
Revise: Verify version bump, Change Log update, and cross-reference resolution. Report changes.
Audit: Present findings by severity. Use AskUserQuestion (header "Next step"): "Fix issues" (switch to Revise) / "Done".
Committing
Delegate to the commit skill. Examples:
docs(spec-writer): draft validation config v2 specificationdocs(spec-writer): revise handoff protocol — add context fields
Rules
- Delegate writing to the
spec-writeragent; this skill orchestrates only. - Confirm scope before drafting; prefer promoting existing decision records over starting from scratch.
Related Skills
mjmorales/janitor
tools
VerifiedTrustedCommunity
Clean and compact prove's durable memory layers — team Lore, the Codex (scrum decisions), annotations, and contributor artifacts — keeping the tribal knowledge that grows team accuracy and folding away the rot. Triggers on "janitor", "clean the lore", "compact the lore", "compact the codex", "memory cleanup", "clean up team memory", "prune stale decisions", "tidy tribal knowledge", "lore cleanup". You are the driver: the CLI emits inventories and executes writes; the `memory-janitor` agent judges each entry; a per-team batch gate approves; nothing is ever deleted — consolidation, promotion, and supersession only.
2SKILL.mdUpdated Jun 9, 2026
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