Good skill
Local-first toolkit for creating, validating, and publishing high-quality AI-agent skills.
npx -y skills add Sparvovic/agent-skill-foundry --skill good-skillAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Use when the user asks an AI coding agent to turn a git diff into concise release notes with risks, validation evidence, and reviewer-ready wording.
SKILL.md
1.5 KB, 277 tokens by cl100k_base, as published. Nobody here has run it
Release Note Review
Purpose
Create clear release-note drafts from a local diff without hiding risk or inventing user impact.
Use When
Use this skill when the user asks for release notes, changelog text, launch notes, or a reviewer handoff based on local code changes.
Inputs
- The current git diff.
- Existing changelog or release-note style, if present.
- Package manifests or docs that identify the product area.
Workflow
- Inspect the diff and nearby docs before writing.
- Separate user-visible changes from internal refactors.
- Flag migrations, behavior changes, removed APIs, and validation gaps.
- Draft concise release notes in the existing project voice.
- Keep uncertainty explicit when impact cannot be proven from the diff.
Outputs
- A Markdown release-note draft.
- A short risk section.
- Validation evidence and commands that were run.
Validation
Run the repo's relevant test, build, or lint command before finalizing. If no validation command is available, state that clearly.
Safety Boundaries
- Do not claim tests passed unless the command was run.
- Do not invent customer impact that is not visible in the diff.
- Do not publish or submit release notes externally without user approval.
Additional Resources
- Read references/release-note-checklist.md before preparing a public release note.
What ships with it: 1 file
257 B alongside SKILL.md
references/
Gives 0 of the 12 instructions most review quality skills give in 277 tokens
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07
- Ask questions one at a timein 81 of 1048, across 64 files
- Provide a recommended answer for each questionin 73 of 1048, across 50 files
- Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
- Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
- Interview the user relentlessly about the planin 38 of 1048, across 13 files
- Order findings by severityin 31 of 1048
- Resolve each branch of the decision treein 27 of 1048, across 5 files
- Run a grilling sessionin 26 of 1048, across 5 files
- Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
- Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
- Create documentation files lazilyin 24 of 1048, across 5 files
- Assign severity to every findingin 24 of 1048
Said here and by no other author read
- Separate user-visible changes from internal refactors
- Flag migrations, behavior changes, and removed APIs
- Draft release notes in the existing project voice
- Keep uncertainty explicit when impact is unproven
- State clearly if no validation command is available
- Read the release-note checklist before drafting
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.