CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

codebase-audit

Perform a full codebase review, categorize findings by severity, file GitHub issues, then fix each issue in an isolated git worktree and submit PRs. Use this skill when the user asks to audit the codebase, do a comprehensive code review, find and fix security/quality/reliability issues, or run a proactive health check across the entire repository.

86

1.75x
Quality

93%

Does it follow best practices?

Impact

93%

1.75x

2 of 3 eval scenarios. Add 1 more for a full score.

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 well-engineered workflow skill: executable commands, explicit validation checkpoints with a CI retry loop, and a clean routing table over real reference files. Its only deductions are deliberate cross-section repetition and the Phase 4 procedure duplicating the worktree-fix reference.

DimensionReasoningScore

Conciseness

Efficient and free of concept explanations, but several rules are deliberately restated across sections — 'One worktree per issue', the commit format, and 'verify build + test' each appear two or more times (workflow, Git safety rules, Commit conventions, self-check) and could be consolidated.

4 / 5

Actionability

Fully executable commands throughout: 'gh issue create --title "<type>(<scope>): <summary>" …', 'git worktree add ../<repo>-audit-fix-<issue-number> -b fix/<slug>-<issue-number> origin/main', 'cd mcp && npm run build && npm run test', 'gh pr checks <number>'. Placeholders are only where data (issue numbers, scopes) is inherently session-specific.

5 / 5

Workflow Clarity

Five clearly sequenced phases with explicit checkpoints and feedback loops: user confirmation before creating issues, local build+test verification before each push, CI status check with a 're-enter the worktree, fix, and push again' retry loop, and a final minimum self-check checklist.

5 / 5

Progressive Disclosure

A routing table maps every task to a real one-level-deep reference file (all 7 referenced files exist), but Phase 4 inlines a detailed worktree procedure that duplicates references/worktree-fix.md — minor placement/duplication gaps rather than the ideal split.

4 / 5

Total

18

/

20

Passed

Description

96%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: concrete multi-step capabilities, explicit 'Use when' triggers with natural synonyms, and a distinct end-to-end audit niche. The only weakness is minor overlap risk with generic code-review skills since the description omits the exclusions the body provides.

DimensionReasoningScore

Specificity

The description lists five concrete actions covering the full pipeline — 'Perform a full codebase review, categorize findings by severity, file GitHub issues, then fix each issue in an isolated git worktree and submit PRs' — which matches the comprehensive multi-action anchor with no coverage gaps.

5 / 5

Completeness

Explicitly answers both 'what' (the full review → classify → issue → fix → PR pipeline) and 'when' via a concrete 'Use this skill when the user asks to…' clause with multiple trigger scenarios.

5 / 5

Trigger Term Quality

Natural user phrasings are comprehensively covered with synonyms: 'audit the codebase', 'comprehensive code review', 'find and fix security/quality/reliability issues', 'proactive health check', 'entire repository'. No materially missing natural terms for this domain.

5 / 5

Distinctiveness Conflict Risk

The whole-repository audit with issue/PR follow-through is a clear niche, but 'comprehensive code review' overlaps with diff/PR-review skills and the description carries none of the body's exclusion cues, leaving minor conflict risk.

4 / 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

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

TencentCloudBase/CloudBase-AI-Toolkit

Path

skills/codebase-audit/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.