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.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

77%

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

A well-structured, highly actionable CI readiness workflow with strong sequencing and validation, undermined only by some duplicated troubleshooting guidance and limited offloading of conditional detail into the reference file.

Suggestions

De-duplicate the @fluidframework/tree full-clean-build guidance: state it once and cross-reference it from the second occurrence instead of repeating the full `pnpm clean && pnpm build` block.

Move the detailed tree-package/incremental-TypeScript troubleshooting and the API-surface-change determination into `tree-api-checks.md`, keeping SKILL.md as the sequenced overview with a one-line pointer.

Verify the referenced bundle files (`ci-readiness-check.sh`, `tree-api-checks.md`) are actually shipped with the skill so the inline references resolve.

Dimension	Reasoning	Score
Conciseness	Mostly efficient and earned, but the @fluidframework/tree incremental-TypeScript-bug / full-clean-build guidance is repeated in Step 3 and again in the "Determining if the public API surface changed" section, and could be tightened.	2 / 3
Actionability	Fully executable, copy-paste-ready commands throughout — e.g. `bash .claude/skills/ci-readiness-check/ci-readiness-check.sh [base-branch]`, `pnpm clean && pnpm build`, `cd $PKG && pnpm exec fluid-build . --task compile`.	3 / 3
Workflow Clarity	Clear numbered Step 1–9 sequence with explicit validation checkpoints and feedback loops — e.g. API Extractor failure → add release tag → rebuild → retry, and unexpected artifacts → full clean build → re-run the check.	3 / 3
Progressive Disclosure	References to `tree-api-checks.md` and the bundled script are clearly signaled and one level deep, but the referenced bundle files are not present in the review context and substantial conditional troubleshooting detail (tree-package clean, API-surface determination) is kept inline rather than offloaded.	2 / 3
	Total	10 / 12 Passed

Description

100%

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 concise, third-person, and hits all four anchors at the top level: explicit trigger terms, a clear what-and-when statement, and a distinct niche. It is one of the strongest possible descriptions.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions the skill catches — "formatting, stale API reports, missing changesets, policy violations" — rather than vague language.	3 / 3
Completeness	Explicitly answers both: "Use when the user explicitly asks for a CI check or to push their branch" (when) and "Catches common CI failures before pushing — formatting, stale API reports, missing changesets, policy violations" (what).	3 / 3
Trigger Term Quality	Excellent coverage of natural phrases users say — "ci readiness", "check ci", "pre-push check", "ready for CI", "ready to push", "push my changes", "push the branch", "let's push".	3 / 3
Distinctiveness Conflict Risk	A narrow CI-pre-push niche with distinctive triggers unlikely to collide with other skills.	3 / 3
	Total	12 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: microsoft/FluidFramework
Path: .claude/skills/ci-readiness-check/SKILL.md
Commit: f9f2007

Reviewed: about 7 hours 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.