release-notes

Generate a starting-point GitHub release notes draft for an upcoming Warp release (feature or bugfix, auto-detected from the version). Run from a release branch, or pass a branch / git ref as the argument.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

85%Weight 40%Scale 1-3

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-architected, highly actionable multi-phase workflow with strong sequencing, explicit validation gates, and clean one-level-deep references to real bundle files; its main weakness is length, with some rationale prose that could be trimmed for token efficiency.

Suggestions

Tighten the rationale asides (e.g., the cherry-pick-filter and gh gist edit --filename explanations) to bare operational instruction to push conciseness toward 3, moving the full 'why' into a reference file if needed.

Consider condensing the four Phase 2 gh-state proposal blocks into a shared template with per-state deltas to reduce repeated boilerplate.

Dimension	Reasoning	Score
Conciseness	The body is dense and procedural with mostly repo-specific operational detail rather than general concepts Claude already knows, but it is long and includes rationale asides (e.g., why --cherry-pick filtering matters, why --filename is needed for gh gist edit) that could be tightened to earn a 3.	2 / 3
Actionability	Highly actionable with concrete, copy-paste-ready commands throughout — 'git show <head-ref>:VERSION.md', 'git tag --list ... --sort=-v:refname', 'uv run "<skill-dir>/scripts/list_contributors.py" --base ... --head ...', 'gh gist edit <id> --filename <gist-filename> ...' — plus explicit template files carrying inline per-section instructions.	3 / 3
Workflow Clarity	Six numbered phases with explicit validation checkpoints and feedback loops: Phase 2 mandates a 'wait for explicit user confirmation' pause before proceeding, abort conditions are enumerated ('If zero after filtering, abort'), new refs re-run Phase 1, and 5e adds a self-audit re-read step — matching the anchor for clear sequence with explicit validation and error-recovery loops.	3 / 3
Progressive Disclosure	The SKILL.md body is an overview that points to real, one-level-deep bundle files with clear signaling — 'Read references/style-rules.md, references/feature-investigation.md, and references/feature-release-template.md', 'See references/contributor-attribution.md', 'Fill in references/bugfix-release-template.md' — all of which exist in the bundle, with content appropriately split out rather than inlined.	3 / 3
	Total	11 / 12 Passed

Description

82%Weight 40%Scale 1-3

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A specific, distinct, third-person description that names concrete actions and natural trigger terms, but it lacks an explicit 'Use when...' clause so the 'when to use it' is only implied.

Suggestions

Append an explicit 'Use when ...' clause (e.g., 'Use when preparing GitHub release notes for an upcoming Warp release, when the user mentions release notes or a release branch, or asks to draft the next release.') to lift completeness from 2 to 3.

Consider adding the tag/ref keyword variants users might say ('release branch', 'git tag', 'version bump') to reinforce trigger_term_quality.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Generate a starting-point GitHub release notes draft', 'auto-detected from the version', 'Run from a release branch, or pass a branch / git ref as the argument' — matching the anchor for listing several specific concrete actions rather than vague language.	3 / 3
Completeness	The 'what' is explicit ('Generate a ... release notes draft ... auto-detected from the version'), but there is no 'Use when...' clause or equivalent explicit trigger guidance — the 'when' is only implied via 'for an upcoming Warp release' and 'Run from a release branch', which caps completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	Natural user-facing terms are well covered: 'release notes', 'GitHub release notes draft', 'release branch', 'Warp release', 'version', 'bugfix', 'feature' — terms a user would actually say when requesting this, with good variation rather than jargon-only phrasing.	3 / 3
Distinctiveness Conflict Risk	The Warp-specific framing ('upcoming Warp release', feature/bugfix auto-detection from version, prior-tag diffing) carves a clear niche with distinct triggers unlikely to fire for an unrelated skill; it is not a generic 'helps with documents' style description.	3 / 3
	Total	11 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: NVIDIA/warp
Path: .claude/skills/release-notes/SKILL.md
Commit: ee184d6

Reviewed: 10 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.