greptimedb-release-note

Generate a GreptimeDB release changelog with git cliff (correct range, subtract already-released patch PRs, rebuild contributors, add human-curated highlights), output to a file, and prepare the docs-repo blog PR. Use when asked to write/generate a GreptimeDB release note or changelog.

Quality

91%

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

88%Weight 40%Scale 1-5

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

An unusually dense, high-signal skill: concrete commands, real git-topology gotchas, fallback paths, and an explicit verify step. The two real gaps are that the pivotal subtract-PRs/rebuild-contributors Python script is described but never provided, and there is no progressive disclosure structure at all — the whole procedure, including the somewhat separable docs blog workflow, lives inline in one file.

Suggestions

Bundle the subtract-PRs / rebuild-contributors logic as an executable script in scripts/ (e.g. subtract_prs.py) and reference it with a one-line invocation, instead of only describing that 'a small Python script is the reliable way' — this turns the most fragile step into copy-paste-ready guidance and raises actionability.

Move the docs-repo blog variant (§8) into references/docs-blog-pr.md and keep a 2-3 line pointer in SKILL.md; it is a secondary workflow that roughly doubles the file's length for users who only need the changelog itself.

Add a brief 'Verify' checklist line in §4 mirroring §5 (e.g. confirm no removed contributor appears and the sorted contributor set matches the remaining bullets), so the rebuild step is validated the same way the subtraction step is.

Dimension	Reasoning	Score
Conciseness	Every section carries non-obvious, repo-specific knowledge ('patch tags ... are NOT ancestors of main', the squashed-pick-commit gotcha, the gh org-scope workaround) with zero padding and no explanation of concepts Claude already knows. It matches the 'lean and efficient; every token earns its place' anchor despite its length, because that length is all task-specific edge cases.	5 / 5
Actionability	Concrete, copy-adaptable commands appear throughout (git cliff ranges, gh release view, the worktree/push/PR-create sequence). It stops short of anchor 5 because the central subtraction/contributor-rebuild step is only described — 'a small Python script is the reliable way' — with neither the script nor its matching logic written out or bundled.	4 / 5
Workflow Clarity	The eight numbered sections form a clear sequence with an explicit verification step ('Cross-check the result against git log <base>..<tip>'), error-recovery loops (re-run cliff until pagination completes, fall back to hand-written bullets), and user-confirmation checkpoints ('Double-check with the user', 'ask the user which they prefer'). This matches the top anchor including feedback loops for the batch subtraction operation.	5 / 5
Progressive Disclosure	The body is well-sectioned with clear headers and each part is directly relevant, but the skill is a single ~185-line monolith with no bundle files at all. It fits anchor 4 ('good structure; most content appropriately placed; minor organization gaps') rather than 5 because content that plausibly belongs in separate files — the docs-repo blog variant (§8) and the subtraction script — is inlined.	4 / 5
	Total	18 / 20 Passed

Description

92%Weight 40%Scale 1-5

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 strong description: third-person, specific, comprehensive action list, and an explicit 'Use when...' trigger clause tied to natural phrasing. The only weakness is modest keyword breadth (no synonyms like 'release notes' or 'blog post'), which slightly limits trigger recall.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions — 'subtract already-released patch PRs, rebuild contributors, add human-curated highlights', 'output to a file', 'prepare the docs-repo blog PR' — with no vague filler. It matches the anchor for comprehensive coverage of specific actions, and is not score 4 because there are no minor gaps in the action inventory.	5 / 5
Completeness	It explicitly answers both questions: the 'what' is the full changelog-generation pipeline, and the 'when' is the concrete trigger clause 'Use when asked to write/generate a GreptimeDB release note or changelog.' This matches the anchor for a clear what AND when with concrete trigger phrases; score 4 would require the 'when' to be less explicit than it is.	5 / 5
Trigger Term Quality	Natural user phrasings like 'release note', 'changelog', and 'write/generate' are present and domain-anchored by 'GreptimeDB'. It falls short of anchor 5 because common synonyms/variations (e.g. 'release notes', 'docs blog post for the release') are not covered, but exceeds anchor 3 since the core natural terms users would actually say are all there.	4 / 5
Distinctiveness Conflict Risk	The 'GreptimeDB' scope and release-note/changelog triggers define a clear niche that would not fire for any other skill. Minimal conflict risk matches the top anchor; there is no overlap with generic git or docs skills because the trigger is product-specific.	5 / 5
	Total	19 / 20 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: GreptimeTeam/greptimedb
Path: .agents/skills/greptimedb-release-note/SKILL.md
Commit: 3a4c24a

Reviewed: 3 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.