release-notes
Use when drafting or updating release notes from commits, pull requests, tags, waves, or sprints. USE FOR: create release notes for a version, summarize changes since a tag, generate notes by wave/sprint labels, produce internal or customer-facing changelog drafts, and structure upgrade notes with traceability. DO NOT USE FOR: release readiness audits, deployment execution, rollback operations, or post-release production incident troubleshooting.
Works with
--- name: release-notes description: Use when drafting or updating release notes from commits, pull requests, tags, waves, or sprints. USE FOR: create release notes for a version, summarize changes since a tag, generate notes by wave/sprint labels, produce internal or customer-facing changelog drafts, and structure upgrade notes with traceability. DO NOT USE FOR: release readiness audits, deployment execution, rollback operations, or post-release production incident troubleshooting. license: MIT --- # Release Notes Skill Generate release notes from git/PR history with traceability. Prefer `wave:*` / `sprint:*` labels over Projects/Milestones. ## USE FOR - Drafting release notes for a version, wave, or sprint. - Summarizing merged PRs and commits in a version range. - Generating notes scoped by PR labels such as `wave:*` and `sprint:*`. - Creating internal or customer-facing release notes from templates. - Capturing breaking changes and upgrade notes. ## DO NOT USE FOR - Release readiness audits or compliance checks. - Executing deployment, publish, or rollback actions. - Incident debugging or backlog triage. ## Workflow 1. Resolve scope: tag range, PR list, or labels. 2. For wave/sprint runs, filter PRs by `wave:*` / `sprint:*` first. 3. Collect evidence from commits, PRs, and linked issues. 4. Render notes from template and mark uncertain items `Needs confirmation`. ## Wave and Sprint Binding Use this contract to keep release-note grouping stable: - Primary keys: PR labels `wave:<id>` and `sprint:<id>`. - Recommended policy: require one of these labels on PRs merged to main. - Projects and Milestones are secondary hints. - If labels are missing, group by merge window and mark `Needs confirmation`. ## Output Contract Always output: Highlights, Breaking changes, Fixes and improvements, Known issues, Upgrade notes, Contributors. Include metadata at top: Version/range, Wave (if present), Sprint (if present). Each item should include traceability (PR number, commit SHA, or issue link). ## Guardrails - Never invent PRs, issues, or fixes. - Prefer customer-safe wording for external notes. - When evidence is incomplete, flag for confirmation. ## Reference Files - [`references/templates/internal.md`](references/templates/internal.md) - [`references/templates/external.md`](references/templates/external.md) - `scripts/validate-release-notes.ps1` writes validation reports to `reports/release-notes/`
More Writing & Documentation skills
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
repo-intake-and-plan
lllllllama/rigorpilot-skills
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.
