CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

review-renovate

Review Renovate bot PRs that update GitHub Actions dependencies. Verifies supply chain integrity by checking pinned commit SHAs against upstream tagged releases, reviews changelogs for breaking changes, and confirms compatibility with existing workflow configurations. Use when a Renovate PR updates GitHub Actions in .github/workflows/.

77

Quality

97%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

92%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.

A tight, well-sequenced review procedure with executable gh commands, an explicit supply-chain validation gate, and a concrete report template. The only notable weakness is a technical subtlety in the SHA-verification command that mishandles annotated tags, which slightly dents actionability.

Suggestions

Handle annotated tags in step 3: for tags where the ref points at a tag object, dereference it (e.g., follow `.object.url` to the commit, or use `git rev-parse {version}^{commit}`) so the comparison yields the commit SHA; otherwise verified pins of annotated-tag releases will be reported as integrity failures.

Add one concrete diff snippet in step 2 showing an action-version change (e.g., a `-uses: oven-sh/setup-bun@v1... / +uses: ...@v2...` hunk) so the extraction of old/new tag and SHA is unambiguous.

In step 4, note the fallback when Renovate's PR body lacks release notes (e.g., fetch `https://github.com/{owner}/{repo}/releases/tag/{version}`) so the breaking-change check remains executable.

DimensionReasoningScore

Conciseness

The body is lean: every section is a step with concrete commands, checks, or a report template; there is no explanation of concepts Claude already knows. The brief opening sentence and the "major version bumps (these almost always have breaking changes)" heuristic both earn their tokens, matching the 5 anchor rather than 4 ('minor instances of over-explanation' — there are none of substance).

5 / 5

Actionability

Steps 1 and 3 give copy-paste `gh` commands with placeholders, and steps 4–6 give specific checklists and an output table — mostly fully executable. It falls short of the 5 anchor because the SHA-verification command (`gh api .../git/ref/tags/{version} --jq '.object.sha'`) returns the tag-object SHA for annotated tags, a common case among action releases, where the pinned SHA comparison would then fail incorrectly; no dereference guidance is given, so a common case isn't correctly covered.

4 / 5

Workflow Clarity

A clear 6-step sequence with an explicit validation checkpoint and failure instruction ("If any SHA does not match, stop and report a supply chain integrity failure. Do not approve the PR.") plus checklists in steps 4–5 and a structured decision output in step 6. This matches the 5 anchor (explicit validation steps, error-recovery guidance, checklists); not 4, because no meaningful validation gap exists.

5 / 5

Progressive Disclosure

There are no bundle files (no references/, scripts/, or assets/) and nothing in the ~60-line body that warrants being split out — all content legitimately belongs inline, and the sections are well organized with clear headers and a table. Under the rubric's small-skill guidance this matches the top anchor; not 4, since there is no inline content that should live in a separate file.

5 / 5

Total

19

/

20

Passed

Description

100%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.

The description is excellent: third-person, concise, lists concrete capabilities, and ends with an explicit 'Use when' trigger naming the exact PR type and workflow path. It follows the strongest reference examples closely with no fluff or over-claims.

DimensionReasoningScore

Specificity

"checking pinned commit SHAs against upstream tagged releases", "reviews changelogs for breaking changes", and "confirms compatibility with existing workflow configurations" are multiple concrete actions that comprehensively cover the skill's scope. It clearly matches the 5 anchor ('multiple specific concrete actions; comprehensive coverage') and not 4, since no meaningful capability gaps remain.

5 / 5

Completeness

The 'what' is explicit (verify SHA pins against upstream tags, review changelogs, check workflow compatibility) and the 'when' is an explicit trigger clause: "Use when a Renovate PR updates GitHub Actions in .github/workflows/". This directly matches the 5 anchor with concrete trigger phrases; not 4, since the 'when' is already fully explicit and specific.

5 / 5

Trigger Term Quality

Natural user phrasing is well covered: "Renovate bot PRs", "GitHub Actions dependencies", "pinned commit SHAs", and the file-path trigger ".github/workflows/" — exactly the terms a user would say, including the path-based variation. It fits the 5 anchor (comprehensive natural terms including extensions/paths) rather than 4, which requires 'a few natural terms missing'.

5 / 5

Distinctiveness Conflict Risk

"Renovate bot" + "GitHub Actions" pins a clear niche with distinct, unlikely-to-collide triggers; only trivial overlap with a generic PR-review skill. Matches the 5 anchor (clear niche, distinct triggers, minimal conflict risk) rather than 4, because the trigger combination is essentially unique to this task.

5 / 5

Total

20

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

backnotprop/plannotator

Path

.agents/skills/review-renovate/SKILL.md

Reviewed

Table of Contents

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.