CtrlK
BlogDocsLog inGet started
Tessl Logo

ci-readiness-check

Use when the user explicitly asks for a CI check or to push their branch — e.g. "ci readiness", "check ci", "pre-push check", "ready for CI", "ci check", "ready to push", "push my changes", "push the branch", "let's push". Catches common CI failures before pushing — formatting, stale API reports, missing changesets, policy violations.

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.

An exceptionally actionable, well-sequenced workflow document: every step is executable, mode-dependent paths are explicit, and validation with feedback loops is built in throughout. Its only weaknesses are mild repetition of the mode/task rules and tree-package guidance, plus a referenced companion file (tree-api-checks.md) whose content is partially duplicated inline.

DimensionReasoningScore

Conciseness

Every section is command-driven with no concept-explanation padding, but the <required> block restates mode/task rules that reappear under 'Tasks to create by mode', and the tree-package incremental-bug warning is repeated in both Step 3 and the API-surface section.

4 / 5

Actionability

Copy-paste bash blocks with $PKG placeholders, exact task flags (fluid-build --task checks:fix, -t build:api-reports, typetests:gen), named error codes (ae-missing-release-tag, ae-unresolved-link) with prescribed fixes, and explicit skip lists for slow tests — fully executable guidance covering the common cases.

5 / 5

Workflow Clarity

Steps 1–9 are clearly sequenced with mode-conditional branches explicitly marked ('Check mode stops here — skip steps 4–8 entirely'), feedback loops for error recovery (add release tag and retry, full clean build on spurious API diffs, re-run the readiness check), validation checkpoints (script verifies checks pass, git diff --name-only | grep api-report, final git status), and a 5-item final-report checklist.

5 / 5

Progressive Disclosure

References are one level deep and clearly signaled (.claude/skills/ci-readiness-check/tree-api-checks.md at Step 6, the api-changes skill, the changeset README link), but neither referenced bundle file is present in this skill's bundle directories to verify, and tree-package guidance is duplicated inline in Step 3 rather than deferred to the referenced file — good structure with minor organization gaps.

4 / 5

Total

18

/

20

Passed

Description

91%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 that explicitly answers both what and when, with an unusually rich set of natural trigger phrases and concrete failure classes in third-person voice. The only weakness is that the 'what' undersells the build/lint/regeneration capabilities documented in the body.

DimensionReasoningScore

Specificity

"Catches common CI failures before pushing — formatting, stale API reports, missing changesets, policy violations" names the domain and four concrete failure classes in third-person voice, but doesn't enumerate the build/lint/API-report actions the skill also performs, matching 'several specific actions; minor gaps'.

4 / 5

Completeness

"Use when the user explicitly asks for a CI check or to push their branch — e.g. ..." gives an explicit when with concrete triggers, and the second sentence explicitly states what the skill does, satisfying the top anchor on both halves.

5 / 5

Trigger Term Quality

Nine natural trigger phrasings are quoted ("ci readiness", "check ci", "pre-push check", "ready for CI", "ci check", "ready to push", "push my changes", "push the branch", "let's push"), covering synonyms and phrasings a user would actually say.

5 / 5

Distinctiveness Conflict Risk

The CI-readiness framing is a clear niche, but push-oriented triggers ("push my changes", "let's push") create minor overlap risk with a plain git-push skill, matching 'mostly distinct; minor overlap risk'.

4 / 5

Total

18

/

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: 1 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.