modrexio/modrex / .agents/skills/changelog
changelog
VerifiedAdd user-facing entries to CHANGELOG.md's Unreleased section for recent changes
changelog
Add entries to CHANGELOG.md's ## Unreleased section for
changes that haven't been recorded yet. Never touch a released (## X.Y.Z) section.
Version headings have no brackets and no date — just the bare number (e.g. ## 0.10.0).
Scope
Determine which changes to record based on the argument passed:
- No argument — find the last tag (
git describe --tags --abbrev=0) and readgit log <tag>..HEAD(full messages, not just subjects). Compare against what's already underUnreleasedand add only what's missing — safe to re-run after every change. - A ref or range (e.g.
HEAD~3..HEAD, a single SHA) — read exactly that range (git log <range>,git show <sha>). - Uncommitted changes — if there's nothing new in the commit log but
git statusshows a dirty tree, readgit diff HEADinstead.
Read full commit messages and diffs, not just subject lines — a one-line fix: subject
often hides the user-facing detail worth recording (or reveals it's purely internal).
Categorization
Use Keep a Changelog sections, in this order: Added, Changed, Fixed, Security (add Deprecated / Removed only if genuinely applicable).
Commit type is a starting hint, not the final answer:
feat→ Addedfix→ Fixed, unless the change addresses a security issue (path traversal, injection, URL/scheme handling, CSP, auth, secrets) — those go in Security regardless of commit type. Read the diff to tell an ordinary bug from a security-relevant one.perf→ Changedrefactor,test,docs,chore,ci,build,style→ skip — never enters the changelog. Same for dependency bumps, license regen, and version-bump commits.- Anything with no observable effect for someone using the app → skip, regardless of conventional-commit type.
Writing entries
- One bullet per user-facing change, in product voice, past tense: "Added X.", "Fixed Y appearing when Z.", not commit subjects, hashes, scopes, or issue numbers.
- If several commits implement one feature or fix, merge them into a single bullet — the changelog reflects shipped behavior, not commit-by-commit history.
- If a commit fixes something introduced earlier in the same
Unreleasedblock (the buggy behavior was never released), fold the fix into the existing Added bullet instead of adding a separate Fixed line for code users never saw broken. - If a commit adds a sub-detail to an unreleased feature (e.g. a progress counter added to a modal that itself hasn't shipped), fold it into the existing bullet for that feature — never add a separate entry for behavior users haven't seen without it.
- Keep entries short. Don't describe a feature's internal contents unless the detail is itself the user-facing point — "Added a per-mod options menu." is enough; listing what's inside the menu is not.
- No Unicode arrows/symbols — plain words ("becomes", "to", "via").
- Match the tone already in
CHANGELOG.md's released sections — read a couple before writing new ones.
Procedure
- Resolve scope (see above) and read the actual diffs, not just messages.
- If nothing in scope is user-facing, say so and stop — do not invent an entry.
- Check existing
Unreleasedbullets first; merge/refine rather than duplicate. - Insert into the right subsection under
## Unreleased, creating a subsection heading only if needed, keeping section order (Added, Changed, Fixed, Security). - Report a 1–3 sentence summary of what was added.
Rules
- Only ever edit the
## Unreleasedsection. Released sections (## X.Y.Z) are historical — never rewrite them. - Never write a version number —
bun releasestampsUnreleasedinto a versioned section at release time. - Edit the file and stop. Do not run
git commit— suggest/commitafterward if the user wants the changelog update committed.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 467k | Updated | Claude CodeCodex | Verified | Install |
| 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: 196k | Updated | Claude CodeCodex | Verified | Install |
| 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: 196k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 196k | Updated | Claude CodeCodex | Verified | Install |