test-codebase

Run or inspect the relevant validation paths and turn failures, regressions, or missing coverage into findings. Accept optional `path` and `depth` parameters and default to `path=infer`, `depth=deep`. Confirm effective variables before starting.

Quality

70%

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/test-codebase/SKILL.md

Quality

Content

80%

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

The body is lean, directive, and actionable with a clear sequenced workflow and well-organized sections. Its main weakness is progressive disclosure: the two referenced shared files do not exist, and the workflow lacks an explicit validation/retry loop, capping those two dimensions at the mid level.

Suggestions

Create the referenced `../shared/references/findings.schema.md` and `findings.lifecycle.md` (or remove the dangling references) so navigation is grounded in real files.

Add an explicit validate→fix→retry checkpoint to the workflow, e.g. re-run the narrow validation after a fix and only record a finding once the failure reproduces.

Consolidate the duplicated `path`/`depth` defaults between the Path Input / Depth sections and Workflow step 1 to tighten the remaining redundancy.

Dimension	Reasoning	Score
Conciseness	The body is lean and directive with no concept explanations Claude already knows; not level 2 because there is no padded prose, only minor default-value repetition between sections.	3 / 3
Actionability	Concrete guidance names specific outputs (`path/findings.md`) and handoff skills (`triage-findings`, `resolve-findings`) plus enumerated capture categories; per the instruction-only note, absence of code is not penalized when guidance is actionable, so this clears level 2.	3 / 3
Workflow Clarity	A clear six-step sequence with a blocker checkpoint exists, but there is no explicit validate→fix→retry loop or result-verification gate; not level 3 because the rubric requires explicit validation steps and feedback loops.	2 / 3
Progressive Disclosure	Sections are well-organized and the two shared references are clearly signaled one level deep, but the cited files (`../shared/references/findings.schema.md`, `findings.lifecycle.md`) do not exist on disk and no bundle files are present; not level 3 because the navigation points at dangling references.	2 / 3
	Total	10 / 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 conveys concrete capabilities and a clear testing/findings niche, but omits any explicit "Use when..." trigger guidance and leans on internal jargon ("validation paths", "effective variables") over natural user phrasings. This caps completeness and trigger-term quality at the mid level.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks to run tests, check for regressions, or find missing coverage."

Replace jargon like "validation paths" and "effective variables" with natural terms users would say ("run the tests", "check coverage").

Keep the concrete actions but pair them with the trigger clause so both "what" and "when" are explicit.

Dimension	Reasoning	Score
Specificity	Names several concrete actions — "Run or inspect the relevant validation paths and turn failures, regressions, or missing coverage into findings" — matching the multiple-specific-actions anchor; not level 2 because it lists distinct actions rather than just naming the domain.	3 / 3
Completeness	It states what the skill does but has no "Use when..." clause or equivalent explicit trigger, so per the rubric guideline completeness is capped at 2; not level 3 because the "when" guidance is entirely absent.	2 / 3
Trigger Term Quality	"regressions" and "missing coverage" are natural user terms, but "validation paths", "effective variables", and "findings" are internal jargon with no common user variations; not level 3 because coverage of natural phrasings is partial.	2 / 3
Distinctiveness Conflict Risk	The validation/findings niche is somewhat specific and unlikely to collide with unrelated skills, but without explicit triggers it could overlap with general test-running skills; not level 3 because distinct triggers are missing.	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/test-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.