CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

frb-write-changelog

Update flutter_rust_bridge CHANGELOG.md for a new release by collecting merged PRs since the previous version tag, mapping them to the target release section, and formatting entries to match the existing changelog style. Use when writing or refreshing a release section in CHANGELOG.md.

Quality

92%

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

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 exceptionally actionable, well-sequenced workflow skill: concrete commands, explicit mechanical verification with feedback loops, and careful edge-case rules that assume Claude's competence. The main gaps are minor duplication of the verifier checklist in Step 9 and a monolithic Step 5 whose stable-release grouping rules could move to a one-level-deep reference file.

Suggestions

In Step 9, replace the restated checklist ('Confirm there are no missing, duplicated, or extra PR numbers…') with a single instruction to re-run the verifier and act on its output, since Step 7 already enumerates what it checks.

Move the stable-release grouping rules in Step 5 (beta parent entries, copied groups, ordering precedence) into a one-level-deep reference file such as references/stable-release-format.md, keeping only a short summary and the entry-format rules in SKILL.md.

Ship the referenced verifier script in the skill's scripts/ bundle (or note its dependency explicitly) so the 'uv run --script .claude/skills/frb-write-changelog/verify_changelog.py' invocation is self-contained with the skill.

DimensionReasoningScore

Conciseness

Dense, imperative rules with zero concept explanation — every line carries repo-specific knowledge Claude cannot infer. Not 5: Step 9 restates the verifier's checks already enumerated in Step 7 ('Confirm entries with third-party thanks appear before entries without thanks…') where 're-run the verifier' would suffice.

4 / 5

Actionability

Fully executable throughout: 'git tag --sort=-creatordate | head -n 20', 'gh pr list --state merged --limit 200 --json number,title,author,mergedAt,baseRefName,url', the complete 'uv run --script .claude/skills/frb-write-changelog/verify_changelog.py' invocation with all flags, and './frb_internal generate-internal-readme --set-exit-if-changed'. Not 4: commands are copy-paste ready with only legitimate placeholders.

5 / 5

Workflow Clarity

Ten clearly sequenced steps with explicit validation checkpoints and feedback loops: 'Apply any confirmed fixes, then re-run the verifier' (Steps 7, 9), the human-review checkpoint (Step 8), and the final drift gate run from a clean post-commit tree (Step 10). Not 4: validation and error-recovery loops are explicit, not implicit.

5 / 5

Progressive Disclosure

Clean step-based sections and the single external dependency (the verify script) is referenced by exact path with its full invocation — no nested references. Not 5: the ~75 lines of dense stable-release grouping and ordering rules in Step 5 are inlined in SKILL.md where a one-level-deep reference file could carry them, and no bundle files are provided here.

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 voice, concrete multi-action what-statement, and an explicit 'Use when…' trigger clause. Its only weakness is modest keyword breadth — missing natural synonyms like 'release notes' that users might say instead of 'changelog'.

DimensionReasoningScore

Specificity

Lists three concrete, comprehensive actions — 'collecting merged PRs since the previous version tag', 'mapping them to the target release section', and 'formatting entries to match the existing changelog style' — fully covering the task. Not 4: coverage has no minor gaps.

5 / 5

Completeness

Explicitly answers what (collect PRs, map to the release section, format entries) and when ('Use when writing or refreshing a release section in CHANGELOG.md'). Not 4: the when-clause is explicit and concrete, matching the anchor-5 example structure.

5 / 5

Trigger Term Quality

Natural terms like 'CHANGELOG.md', 'new release', 'release section', 'merged PRs', and 'writing or refreshing' match what a user would say. Not 5: common synonyms such as 'release notes' or 'changelog entry' are absent.

4 / 5

Distinctiveness Conflict Risk

Scoped to 'flutter_rust_bridge CHANGELOG.md' — a clear niche with distinct triggers and minimal conflict risk with any generic changelog or release skill. Not 4: no overlap risk with closely related skills.

5 / 5

Total

19

/

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

fzyzcjy/flutter_rust_bridge

Path

.claude/skills/frb-write-changelog/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.