test-evidence-storage

Use when changing test evidence collection, publication, paths, retention, or scratch-directory cleanup.

Quality

78%

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-evidence-storage/SKILL.md

Quality

Content

61%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.

A dense, expert-level architecture note that assumes Claude's competence and points to concrete files, functions, and tests rather than explaining basics. Its main weaknesses are verbose sentence packing and the absence of a sequenced workflow with checkpoints.

Suggestions

Break the long compound-sentence bullets into shorter sub-bullets or a short table so each invariant (fail-closed rules, trusted-only keys, cleanup layers) is scannable.

Add a brief ordered 'When modifying evidence handling' checklist with explicit validation steps (e.g., run the named regression tests, confirm config fails closed) to give the knowledge a workflow spine.

Trim justifying asides like '94% of observed accumulation' unless they change the action; keep only the rule and the file/test pointer.

Dimension	Reasoning	Score
Conciseness	Information-dense with no padding of basic concepts Claude already knows, but long compound sentences and explanatory asides (e.g., "that litter was 94% of observed accumulation") could be tightened; mostly efficient but not lean.	3 / 5
Actionability	Highly concrete guidance pointing to exact files, functions, config keys, and regression test names (e.g., internal/evidence_publish.go, test.evidence.store_in_repo, TestPushStep_DoesNotPublish...); not a 5 because there are no copy-paste code/commands, though that is acceptable for an instruction-only skill.	4 / 5
Workflow Clarity	This is a reference/knowledge skill describing system mechanisms and invariants rather than a multi-step workflow, so there is no sequenced process or Claude-facing validation checkpoints; fail-closed behavior is described as system behavior, not as steps to follow.	3 / 5
Progressive Disclosure	Under 50 lines with no external references needed, organized into two clear bold section headers with bulleted facts; not a 5 because the bullets are dense walls of prose that would benefit from sub-structure or shorter points.	4 / 5
	Total	14 / 20 Passed

Description

87%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.

A tight, well-constructed description that explicitly pairs a concrete what with a Use-when trigger and occupies a distinct niche. The only weakness is repetitive verb usage across the listed action areas.

Dimension	Reasoning	Score
Specificity	Lists several concrete change targets ("test evidence collection, publication, paths, retention, or scratch-directory cleanup") under one verb, giving broad niche coverage; not a 5 because the actions share a single repetitive verb rather than multiple distinct concrete actions.	4 / 5
Completeness	Explicitly answers both what (changing evidence collection/publication/paths/retention/scratch cleanup) and when ("Use when changing...") with concrete trigger phrases, matching the anchor 5 example pattern.	5 / 5
Trigger Term Quality	Includes natural domain phrases users would say ("test evidence", "retention", "scratch-directory cleanup", "publication") with good coverage; not a 5 because it lacks synonyms or file-extension variants, though the specialized niche has few.	4 / 5
Distinctiveness Conflict Risk	The "test evidence" + "scratch-directory cleanup" niche is highly specific with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning

	Total	14 / 16 Passed

Repository: kunchenguid/no-mistakes
Path: .agents/skills/test-evidence-storage/SKILL.md
Commit: 14e8dd1

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.