scan-codebase

Perform a fresh-context scan of code and docs that turns verification observations and missing-test gaps into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/scan-codebase/SKILL.md

Quality

Content

75%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 body is a lean, well-structured instruction-only skill with clear workflow sequencing and concrete file/handoff targets. Its main weaknesses are missing validation checkpoints in the workflow and dangling shared-reference paths.

Suggestions

Add an explicit validation checkpoint in the workflow (e.g. 'Confirm each finding is backed by evidence before writing it to path/findings.md').

Resolve or remove the dangling shared references (`../shared/references/findings.schema.md`, `findings.lifecycle.md`) that do not exist in the bundle.

De-duplicate the path/depth defaults between the Depth/Path Input sections and Workflow step 1 to tighten conciseness.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no concept over-explanation, but the depth/path defaults are restated across the Depth, Path Input, and Workflow step 1 sections, leaving minor trimmable redundancy that keeps it just below the lean 5.	4 / 5
Actionability	Concrete, actionable targets are given (write `path/findings.md`, hand off to named skills triage-findings/test-codebase/resolve-findings, read specific artifact types), but the long finding-category list ('correctness, consistency, completeness...') stays somewhat abstract, leaving minor gaps versus fully executable guidance.	4 / 5
Workflow Clarity	A clear 5-step sequence with an explicit handoff step is present; because updating a findings record is not a destructive or batch operation the cap-at-3 does not bind, but no explicit validation checkpoint (e.g. confirm each finding is evidence-backed before recording) leaves a minor validation gap versus the 5.	4 / 5
Progressive Disclosure	Sections are well-organized and the two shared references are clearly signaled one level deep at the top, but those referenced files (`../shared/references/findings.schema.md`, `findings.lifecycle.md`) do not exist in the bundle, a minor navigation gap that holds it below the clean 5.	4 / 5
	Total	16 / 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 reasonably distinctive, but it lacks any explicit 'Use when...' trigger guidance, which caps its completeness. Adding concrete trigger phrases would lift the strongest remaining weakness.

Suggestions

Add an explicit 'Use when...' clause naming natural triggers, e.g. 'Use when reviewing code/docs for findings or surfacing missing-test gaps'.

Include common synonyms or variations users might say (e.g. 'code review', 'coverage gaps', 'audit') to broaden trigger-term coverage.

Briefly contrast against adjacent skills (test-codebase, triage-findings) in the description to sharpen distinctiveness.

Dimension	Reasoning	Score
Specificity	Names the domain (code/docs scan) and several concrete actions — turning verification observations and missing-test gaps into findings, accepting parameters, confirming variables — with only minor coverage gaps, fitting the 'lists several specific actions' anchor rather than the comprehensive 5.	4 / 5
Completeness	It clearly states what the skill does ('Perform a fresh-context scan...turns...observations and missing-test gaps into findings') but provides no 'Use when...' clause or equivalent explicit trigger guidance, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural terms like 'scan', 'code', 'docs', 'missing-test gaps', and 'findings' give good keyword coverage a user would plausibly say, but synonyms and file extensions are absent so it stops short of the comprehensive 5.	4 / 5
Distinctiveness Conflict Risk	The fresh-context-scan-into-findings framing carves a mostly distinct niche with only minor overlap risk against closely related skills like test-codebase and review, matching the 'mostly distinct' anchor rather than the fully-distinct 5.	4 / 5
	Total	15 / 20 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: Agenta-AI/agenta
Path: .agents/skills/scan-codebase/SKILL.md
Commit: 7a975fb

Reviewed: 3 days 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.