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

73%

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

87%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is concise, actionable, and well-structured with appropriate one-level-deep references, scoring well on token efficiency, actionability, and progressive disclosure. The only gap is workflow clarity: the steps are clearly sequenced but lack explicit validation checkpoints for confirming findings before recording them.

Suggestions

Add an explicit validation checkpoint in the workflow, e.g., 'Verify each finding is evidence-backed before adding it to path/findings.md', to raise workflow clarity to 3.

Optionally include a short acceptance check at the end of the workflow (e.g., re-confirm scope and effective variables were honored) to close the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and well-sectioned (Role, Depth, Path Input, Workflow, Rules) with no explanations of concepts Claude already knows and no padding. It matches the level-3 anchor of lean, efficient content where every token earns its place, and is above level 2 because there is no unnecessary explanation to tighten.	3 / 3
Actionability	For an instruction-only skill it gives concrete, specific guidance: named handoffs ('Use triage-findings... test-codebase... resolve-findings'), a named record file ('Use path/findings.md'), and explicit variable defaults. Per the scoring notes, absence of code is not penalized when guidance is actionable, which this is.	3 / 3
Workflow Clarity	The five numbered workflow steps are clearly sequenced, but there are no explicit validation/checkpoint steps (e.g., verifying a finding is evidence-backed before recording it). The sequence is above level 1 but the missing checkpoints match the level-2 anchor; the destructive-operation cap is not triggered since this is a read-only scan.	2 / 3
Progressive Disclosure	The overview points to two one-level-deep, clearly signaled shared references at the top ('findings.schema.md', 'findings.lifecycle.md') with no nested references, and sections are well organized. This matches the level-3 anchor of a clear overview with well-signaled one-level-deep references.	3 / 3
	Total	11 / 12 Passed

Description

60%

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 concrete and specific about capabilities and parameters but lacks an explicit 'Use when...' trigger clause, leaving the 'when to use' dimension implied. This caps completeness and limits trigger-term naturalness. Adding natural-language use triggers would lift the two weaker dimensions.

Suggestions

Add an explicit 'Use when...' clause naming natural user phrases (e.g., 'Use when running a fresh review of code/docs for findings, or when the user asks to scan for missing tests or coverage gaps').

Soften jargon like 'verification observations' and 'missing-test gaps' with natural synonyms users would actually say, to improve trigger-term quality.

Add a distinguishing phrase that separates this skill from sibling skills (e.g., versus test-codebase's runtime validation) to reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'Perform a fresh-context scan of code and docs', 'turns verification observations and missing-test gaps into findings', 'Accept optional path and depth parameters' — matching the level-3 anchor of multiple specific concrete actions. It is above level 2 because the actions are enumerated and concrete rather than a domain-plus-partial-actions summary.	3 / 3
Completeness	It clearly states what the skill does but has no 'Use when...' clause or equivalent explicit trigger guidance, so 'when' is only implied. Per the rubric guidelines, a missing trigger clause caps completeness at 2; it is not level 1 because the 'what' is concrete.	2 / 3
Trigger Term Quality	Relevant keywords exist ('scan', 'code and docs', 'findings', 'missing-test gaps') but lean technical and lack common natural phrasings a user would actually say. It is not level 3 (no broad natural-term coverage) and not level 1 (terms like 'scan code and docs' are relevant rather than pure jargon).	2 / 3
Distinctiveness Conflict Risk	The fresh-context scan-to-findings niche is somewhat specific, but it overlaps with sibling review/finding skills (test-codebase, triage-findings) and lacks distinct explicit triggers. It is more specific than the generic level-1 example but does not reach the level-3 clear-niche bar.	2 / 3
	Total	9 / 12 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: 93872a6

Reviewed: 5 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.