CtrlK
BlogDocsLog inGet started
Tessl Logo

api-changes

Use when customer-facing API changes were made — i.e., API report .md files differ from the branch's resolved comparison base. Guides through release tag assignment, API Council review requirements, breaking change classification, deprecation process, and changeset guidance. Triggered automatically by ci-readiness-check when api-report diffs are detected.

72

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

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.

A well-constructed process skill: a clearly ordered review workflow with executable commands, decision tables, checklists, and user-confirmation checkpoints, written almost entirely from repo-specific knowledge Claude lacks. The main improvement opportunities are trimming occasional over-explanation and moving long policy tables into reference files.

DimensionReasoningScore

Conciseness

The body is dense with repo-specific policy Claude cannot know (tag semantics, break windows, council rules) and uses compact tables, but occasionally explains known concepts, e.g. 'A breaking change removes or modifies an existing API in a way that causes compile errors for consumers upgrading.' Efficient with minor trimmable passages — anchor 4, not 5.

4 / 5

Actionability

Guidance is copy-paste ready throughout: 'git diff "$BASE_COMMIT" -- ':(glob)**/api-report/*.md'', 'pnpm flub changeset add --releaseGroup <releaseGroup> --empty', the exact 'test/breaks/client/#.#0/' branch pattern, and a complete @deprecated TSDoc template.

5 / 5

Workflow Clarity

Seven clearly sequenced steps with explicit checkpoints: flagging missing release tags and documentation, verifying export reachability, 'show the content to the user and confirm it looks right before moving on', a deprecation checklist, and a final go/no-go summary. This is a review (non-destructive) workflow, so the validation cap does not apply.

5 / 5

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ are absent), and the ~150-line body is well-sectioned with clearly signaled links to deeper repo docs (API-Deprecation.md, Beta-Break-Process.md, .changeset/README.md). Some inline policy tables could live in reference files — good structure with minor organization gaps, an anchor-4 fit.

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, concise, with an explicit 'Use when' trigger tied to a concrete detectable condition and a comprehensive list of the skill's capabilities. The only gap is modest synonym coverage of trigger terms.

DimensionReasoningScore

Specificity

The description enumerates five concrete actions — 'release tag assignment, API Council review requirements, breaking change classification, deprecation process, and changeset guidance' — comprehensively covering the skill's workflow end-to-end.

5 / 5

Completeness

It explicitly answers both questions: 'Guides through …' states the what, and 'Use when customer-facing API changes were made — i.e., API report .md files differ from the branch's resolved comparison base' states the when with a concrete trigger condition.

5 / 5

Trigger Term Quality

It includes the natural domain phrases users would say ('customer-facing API changes', 'API report .md files', 'breaking change', 'deprecation', 'changeset'), but offers no synonyms or extension variants beyond '.md'. Good coverage, a few natural terms missing — an anchor-4 fit, not 5.

4 / 5

Distinctiveness Conflict Risk

It is scoped to a clear niche — api-report .md diffs, the resolved comparison base, and the ci-readiness-check trigger — making confusion with other skills very unlikely.

5 / 5

Total

19

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 3 suspicious

Warning

Total

15

/

16

Passed

Repository
microsoft/FluidFramework
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.