CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

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

85%

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 end-to-end workflow with explicit sequencing, validation checkpoints, and a clean one-level reference structure. The only weakness is mild redundancy between the inline phase instructions and the consolidated Commit conventions / Routing sections.

Suggestions

Remove the standalone 'Commit conventions' section — it duplicates the format already shown in Phase 4 step e; fold only the scope-examples list into that step and drop the rest.

Trim the Routing table to only references not already obvious from the phase flow, or drop it entirely, since every listed file is already cited in its corresponding phase.

Reduce 'Minimum self-check' to the few items that are real failure modes a model might skip (e.g., reviewing ALL files vs. a sample), rather than restating each workflow step as a question.

DimensionReasoningScore

Conciseness

Mostly lean and action-oriented with no concept re-explanation, but the standalone 'Commit conventions' section repeats the commit format already shown in Phase 4 step e, and the Routing table re-lists every references/*.md file already cited inline in its phase — both could be tightened.

2 / 3

Actionability

Fully executable commands throughout: 'gh issue create ...', 'git worktree add ../<repo>-audit-fix-<issue-number> -b fix/... origin/main', 'git commit -m ...', 'gh pr create ...', 'gh pr checks <number>', and 'npm run build && npm run test'. Template placeholders are appropriate copy-paste-ready scaffolding.

3 / 3

Workflow Clarity

Five phases are explicitly sequenced with validation checkpoints and a feedback loop: 'wait for confirmation before proceeding' (Phase 2), 'Verify locally: npm run build && npm run test' (Phase 4), and 'If CI fails, re-enter the worktree, fix, and push again' (Phase 5).

3 / 3

Progressive Disclosure

SKILL.md is an overview pointing to well-signaled, one-level-deep references (review-strategy.md, dependency-audit.md, classification.md, issue-workflow.md, worktree-fix.md, verification.md, security-severity-checklist.md) — all of which exist as real files in references/, with a routing table for navigation.

3 / 3

Total

11

/

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.

A strong description: third-person voice, multiple concrete actions, explicit 'Use when' triggers covering natural phrasings, and a clearly distinct niche. It scores at the top of every dimension with no vague fluff or over-claims.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Perform a full codebase review, categorize findings by severity, file GitHub issues, then fix each issue in an isolated git worktree and submit PRs' — matching the anchor for listing several specific actions.

3 / 3

Completeness

Clearly answers both what (review → classify → issue → worktree fix → PR) and when via an explicit 'Use this skill when the user asks to...' trigger clause.

3 / 3

Trigger Term Quality

Natural user phrasing is well covered: 'audit the codebase', 'comprehensive code review', 'find and fix security/quality/reliability issues', 'proactive health check'. These are terms a user would actually say.

3 / 3

Distinctiveness Conflict Risk

The full audit→issue→worktree→PR pipeline is a distinct niche with specific triggers, unlikely to fire for unrelated skills; the body further disambiguates from systematic-debugging, pr-review-fix, and mcp-attribution-worktree.

3 / 3

Total

12

/

12

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.

Validation15 / 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
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.