CtrlK
BlogDocsLog inGet started
Tessl Logo

evolution

This skill enables makepad-skills to self-improve continuously during development.

46

Quality

49%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/evolution/SKILL.md

The canonical home for this skill is evolution 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 body is well-structured and largely actionable with concrete commands and templates, but it is a monolithic inline document whose referenced bundle files are missing and whose publishing workflow lacks validation checkpoints. Splitting detail into the advertised reference/template files and adding a pre-push validation step would materially raise both workflow clarity and progressive disclosure.

Suggestions

Add an explicit validation checkpoint before the git push/PR step in the Evolution Process (e.g. run the Self-Validation checklist locally and confirm the new content compiles/renders before pushing) to satisfy the destructive/batch-operations feedback-loop expectation.

Actually create the referenced references/ and templates/ bundle directories and move the hook settings.json, contribution templates, and routing tables into them, then link to them from SKILL.md so the main file stays a lean overview.

Trim the duplicated Quick Navigation table and the Personalization/Quality-Guidelines sections, which restate routing guidance and generic DO/DON'T advice already implied elsewhere, to improve token efficiency.

DimensionReasoningScore

Conciseness

The body is mostly efficient table-driven guidance and avoids re-explaining general concepts Claude already knows, but the multi-section layout, the large ASCII skill-file tree, and duplicated routing/personalization tables add padding that could be trimmed, matching 'mostly efficient but includes some unnecessary explanation or could be tightened.'

3 / 5

Actionability

It provides concrete executable commands (git checkout/commit/push, the curl install), a ready-to-paste hooks settings.json, and explicit contribution/correction marker templates, fitting 'mostly executable guidance; concrete code or commands with minor gaps' short of 5 because several pattern slots are unfilled templates rather than complete worked examples.

4 / 5

Workflow Clarity

The Evolution Process is a clear 5-step sequence and Self-Correction follows Detect/Verify/Correct, but the outward-facing git branch-push-PR workflow has no validation checkpoint before publishing, so per the destructive/batch-operations cap workflow clarity cannot exceed 3.

3 / 5

Progressive Disclosure

Section headers and a navigation table give it structure, but ~400 lines of inline content (hook configs, templates, routing tables) that belongs in separate files are inlined, and the advertised references/ and templates/ bundle directories do not actually exist, matching 'some structure but could be better organized; references present but not clearly signaled.'

3 / 5

Total

13

/

20

Passed

Description

41%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 correctly uses third person and targets a distinct niche, but it is too terse: it states only one abstract action and omits any 'when to use' trigger guidance. Adding concrete capabilities and a 'Use when...' clause would lift specificity and completeness.

Suggestions

Add a 'Use when...' clause listing concrete triggers, e.g. 'Use when improving makepad-skills, capturing a solved Makepad error, or adding a reusable widget pattern during development.'

Enumerate concrete actions instead of the single abstract 'self-improve', e.g. 'classifies, formats, and submits skill contributions; auto-corrects wrong skill advice; validates skill content against the current Makepad version.'

Include natural user-facing trigger terms ('add a pattern to makepad-skills', 'fix a skill', 'evolve a skill') so the skill is surfaced on the phrases developers actually say.

DimensionReasoningScore

Specificity

The description names the domain ('makepad-skills to self-improve continuously during development') but offers only one generic abstract action ('self-improve') with no concrete capabilities enumerated, matching the 'names the domain but actions are minimal or generic' anchor rather than the level-3 anchor which requires 1-2 concrete actions.

2 / 5

Completeness

It states a clear 'what' (enable makepad-skills to self-improve during development) but provides no 'when'/'Use when...' trigger guidance, so per the missing-trigger-guidance cap it cannot exceed 3.

3 / 5

Trigger Term Quality

It contains no natural phrases a user would say when needing this skill; 'makepad-skills' and 'self-improve' are technical jargon with none of the common variations or synonyms users actually voice, so it sits at the 'one or two generic keywords; missing the natural phrases' level.

2 / 5

Distinctiveness Conflict Risk

The makepad-skills self-improvement niche is specific and unlikely to collide with unrelated skills, placing it at 'mostly distinct; minor overlap risk' rather than 5 because the terse phrasing leaves the exact trigger scope slightly ambiguous.

4 / 5

Total

11

/

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.