CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-audit-pre-push

Deep audit before GitHub push: removes junk files, dead code, security holes, and optimization issues. Checks every file line-by-line for production readiness.

54

Quality

61%

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

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/codebase-audit-pre-push/SKILL.md

The canonical home for this skill is codebase-audit-pre-push in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

57%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.

The content is highly concrete and well-sequenced with a terminal verification step, but it is an exhaustive monolithic checklist with no progressive disclosure via bundle files and only terminal (not per-step) validation for a destructive batch workflow.

Suggestions

Split the large domain sections (security, scalability, performance) into reference files under references/ and point to them from a concise overview in the body, improving progressive disclosure and conciseness.

Add an explicit validation/checkpoint after each destructive or batch section (e.g., "After deleting junk files, confirm the app still builds before proceeding") to lift workflow clarity above 3.

Trim exhaustive enumerations (e.g., listing every OS/IDE/backup file pattern) into a referenceable .gitignore template or shorter representative examples to tighten conciseness.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows and keeps items concrete, but the ~230-line exhaustive enumeration of every junk-file pattern and check is more than a lean overview needs and could be tightened, fitting the 'mostly efficient but could be tightened' anchor.

3 / 5

Actionability

Provides concrete, executable guidance throughout — exact file patterns to delete, specific rules ("Use `===` instead of `==`", "no `innerHTML`", "run `npm audit`"), and a copy-paste output template — with only minor gaps (few actual runnable commands beyond `npm audit`).

4 / 5

Workflow Clarity

A clear numbered 1–10 sequence exists and section 10 provides a final validation checkpoint ("run the app... tests pass... no regressions"), but this is a destructive/batch skill with only a terminal validation step and no intermediate checkpoints between destructive sections, fitting the 'steps listed but checkpoints missing/implicit' anchor.

3 / 5

Progressive Disclosure

No bundle files exist and the entire large checklist is inlined in one monolithic SKILL.md; section headers give some structure, but content that could be split into references (security, scalability, etc.) is all inline with no one-level-deep references signaled, matching the 'some structure but content that should be separate is inline' anchor.

3 / 5

Total

13

/

20

Passed

Description

66%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.

The description is specific and action-oriented with a clear niche, but it lacks an explicit 'Use when...' trigger clause, which caps its completeness. Trigger-term coverage is good but not comprehensive of natural user phrasings.

Suggestions

Add an explicit "Use when..." trigger clause, e.g. "Use when preparing a first push to GitHub, before making a repo public, or when the user asks to audit/clean up code before shipping."

Broaden trigger terms with natural synonyms users actually say: "review my code", "clean up the repo", "is it safe to push", "pre-push check".

Make actions slightly more granular in the description (e.g., name the audit dimensions explicitly: secrets scan, .gitignore fixes, N+1/performance checks) to push specificity toward 5.

DimensionReasoningScore

Specificity

Lists several concrete action categories ("removes junk files, dead code, security holes, and optimization issues"; "Checks every file line-by-line") but stays at category level rather than granular actions, so not a 5.

4 / 5

Completeness

The 'what' is clear (junk/dead code/security/optimization removal), but there is no explicit "Use when..." trigger clause — the 'when' is only weakly implied by "before GitHub push", which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Includes natural phrases like "audit before GitHub push" and "production readiness", but misses common synonyms a user might actually say ("review my code", "clean up the repo", "is it safe to push"), so not comprehensive enough for a 5.

4 / 5

Distinctiveness Conflict Risk

"Deep audit before GitHub push" carves a fairly clear niche with distinct triggers, with only minor overlap risk against general code-review or security-auditor skills, placing it above the 3 anchor but not fully conflict-free at 5.

4 / 5

Total

15

/

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.

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
administrakt0r/AI-Agents-Safe-Coding-Skills
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.