CtrlK
BlogDocsLog inGet started
Tessl Logo

github-pipeline-audit

Sweeps every surface of the MockServer GitHub repository and the build pipeline to confirm nothing is outstanding and everything is clean and up to date. Covers issues, pull requests, all three GitHub security-alert types, the Dependabot updater's own health, GitHub Actions, Buildkite, branches and worktrees, discussions, releases, and published-artifact parity. Use when the user says "check GitHub", "anything outstanding", "is everything clean", "audit the repo", "check the build pipeline", "housekeeping", or before cutting a release.

76

Quality

94%

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.

A highly actionable, well-sequenced audit runbook with strong validation checkpoints and executable commands throughout. Its main weakness is progressive disclosure: all content lives in one ~345-line file with no bundle files, though the inline structure is well organized.

Suggestions

Move the large lookup tables (Dependabot symptom/cause/fix in §4, release-channel parity in §9) into reference files under ./references/ and link to them, reducing the main SKILL.md footprint while keeping the runbook navigable.

Tighten the narrative asides ('Seen in practice', 'The governing principle') into one-line callouts so the body stays lean and command-focused.

Consider extracting the per-surface bash command blocks into a ./scripts/ helper or reference so the SKILL.md body reads as a concise overview with one-level-deep pointers.

DimensionReasoningScore

Conciseness

The body is dense with executable commands and domain-specific failure tables that earn their tokens, but a few narrative flourishes ('Seen in practice', 'The governing principle') could be trimmed; it is efficient rather than padded.

4 / 5

Actionability

Provides fully executable, copy-paste-ready gh/bk/git/curl commands with concrete jq filters and parameterized placeholders covering the common audit cases across every surface.

5 / 5

Workflow Clarity

Sequenced sections 0–10 with explicit validation checkpoints ('MUST be 0', 'CLEAN requires having run the query', the report checklist), feedback loops for error recovery (PR/Dependabot diagnosis order), and safety notes for destructive actions like worktree removal and alert dismissal.

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections with one-level-deep, clearly signaled references to sibling skills (issue-review, pipeline-investigation, release-management) and no nested references; however it is monolithic with large inline tables that, at ~345 lines, could partially live in bundle files (none are present).

4 / 5

Total

18

/

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.

A strong, specific description that clearly states what the skill does and when to invoke it with natural trigger phrases. Third-person voice is maintained and coverage is comprehensive with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete audit actions — issues, PRs, all three security-alert types, Dependabot updater health, Actions, Buildkite, branches/worktrees, discussions, releases, and artifact parity — giving comprehensive coverage rather than vague language.

5 / 5

Completeness

Explicitly answers both what (sweeps every surface of the repo and pipeline) and when (concrete trigger phrases), in third-person voice with no first/second-person phrasing.

5 / 5

Trigger Term Quality

The 'Use when the user says...' clause enumerates natural phrases users would actually say ('check GitHub', 'anything outstanding', 'is everything clean', 'audit the repo', 'housekeeping') including synonyms and a release-cutting context.

5 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (GitHub + build-pipeline audit for the MockServer monorepo) with distinctive triggers, making conflict with unrelated skills minimal.

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mock-server/mockserver-monorepo
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.