Skip to content

snapsynapse/skill-provenance / skills/close

Update version tracking when finishing work on a skill bundle. Use when you're done editing a skill project and need to bump version headers, recompute manifest hashes, update the changelog, flag stale files, or prepare a commit message. Triggers on: "close the session", "update versions", "save the bundle", "I'm done editing", "prepare to commit", "wrap up this skill session".

FileKindSize
SKILL.mdskill md3.6 KB
---
name: close
description: >
  Update version tracking when finishing work on a skill bundle. Use when
  you're done editing a skill project and need to bump version headers,
  recompute manifest hashes, update the changelog, flag stale files, or
  prepare a commit message. Triggers on: "close the session", "update
  versions", "save the bundle", "I'm done editing", "prepare to commit",
  "wrap up this skill session".
license: MIT
---

# Skill Provenance: Close

Update all version-tracking artifacts when finishing a skill editing session.
This ensures the bundle leaves the session in a consistent, verifiable state.

## When to use

Run `/skill-provenance:close` after you've finished editing files in a skill
bundle and before committing, packaging, or handing off.

## Protocol

1. **Validate before mutation.** Run verify-only `validate.sh` first when
   available. Resolve structural grammar, unsafe or duplicate paths, symlink
   components, missing files, and unlisted files before updating hashes. Add
   a manifest entry for each new file; `--update` never adds unlisted files. Hash mismatches and
   missing or malformed hashes may then be repaired with an explicit
   `validate.sh --update` workflow; `hash: null` remains an intentional opt-out.

2. **Update internal version headers.** For each changed file that carries
   YAML frontmatter with version metadata:
   - Increment `version` by 1.
   - Set `version_date` to today.
   - Set `previous_version` to the old version number.
   - Write a `change_summary` (1-3 sentences describing what changed, not
     just that something changed).

3. **Update MANIFEST.yaml.** For every changed versioned file:
   - Update `version` to match the new internal version.
   - Recompute and update `hash`.
   - For files that don't carry internal headers (JSON, scripts, binaries),
     the manifest `version` field is authoritative — increment it there.
   - Bump `bundle_version` (semver): PATCH for fixes/docs, MINOR for new
     features, MAJOR for breaking changes.
   - Update `bundle_date` to today.
   - If the user deployed or reinstalled the skill this session, update
     relevant `deployments` metadata.

4. **Update CHANGELOG.md.** Add a new entry at the top:
   - Use the new `bundle_version` and today's date as the heading.
   - Name every file that changed and what changed in it.
   - **Flag staleness explicitly.** If a versioned file was changed but a
     dependent file was not updated (e.g., SKILL.md changed but evals.json
     wasn't updated to match), say so in the entry.

5. **Final validation.** Run verify-only validation after all version,
   changelog, and hash updates. Do not package or commit a failing bundle.

6. **Deliver.** Provide the user with the changed files plus updated
   `MANIFEST.yaml` and `CHANGELOG.md`.

7. **Git commit message.** If the bundle is in a git repo, provide a
   ready-to-use commit message:

   ```
   bundle-name MAJOR.MINOR.PATCH: one-line summary

   - file1.md: what changed
   - file2.json: what changed
   - Stale: file3.js (not updated this session)
   ```

   Return the message inline. Only write a `git_commit.txt` file if the
   user explicitly asks for one.

## Conventions referenced

- **Per-file versions are integers.** Bundle version is semver.
- **change_summary is required** for every version after v1. Describe
  what changed, not just that something changed.
- **previous_version creates a chain** so any session can trace lineage.
- **MANIFEST.yaml is not self-listed.** It tracks other files only.
- **Hashes are SHA-256** of file contents.

For the full spec: https://skillprovenance.dev
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall