CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-optimizer

Self-evolving skill optimization via SkillOpt-paper-grounded text-space optimizer.

53

Quality

60%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-optimizer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

77%

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

The body is highly actionable and clearly sequenced with strong validation checkpoints for a destructive/batch operation. Its main weaknesses are verbatim repetition of guard rules across sections and a monolithic structure with no progressive disclosure to bundle files.

Suggestions

De-duplicate the bundled-skill mutation and --split 1:1:1 / D_sel>=5 rules: state each once in Iron Law and reference it from the bootstrap, decision-tree, and Anti-Patterns sections instead of restating.

Move the stable reference material (benchmark JSONL schema, rule-check vocabulary, runSkillOpt contract) into a references/ file linked from the body to slim the main SKILL.md and give it a true one-level-deep structure.

DimensionReasoningScore

Conciseness

The body is information-dense and assumes Claude's competence (no basic-concept explanations), but load-bearing rules — bundled-skill mutation guards and the --split 1:1:1 / D_sel>=5 warning — are restated verbatim across Iron Law, the bootstrap section, the decision tree, and Anti-Patterns, so not every token earns its place.

2 / 3

Actionability

Guidance is fully executable: concrete commands (gbrain skillopt X --bootstrap-from-skill --split 1:1:1), the exact benchmark JSONL line shape, the rule-check vocabulary, and the runSkillOpt contract return shape — all copy-paste ready.

3 / 3

Workflow Clarity

The pipeline diagram sequences pre-flight gates, baseline eval, per-epoch steps, and final test eval with explicit validation checkpoints (median-of-3 + epsilon=0.05, D_sel>=5, cost preflight, DB lock), and the bootstrap flow gives numbered steps with a review/strengthen/delete-sentinel checkpoint before re-running.

3 / 3

Progressive Disclosure

Sections are well-organized with a clear Related-skills pointer and a one-level tutorial-doc reference, but the ~175-line body is monolithic with no offloading to bundle files (references/, scripts/, assets/ are absent), so content that could be split — benchmark schema, rule-check reference, contract — stays inline.

2 / 3

Total

10

/

12

Passed

Description

42%

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 identifies a distinct, specialized niche but is written in technical jargon with no natural user keywords and no explicit use-when guidance. It reads as a tagline rather than a routing description.

Suggestions

Add a 'Use when...' clause stating concrete trigger conditions (e.g. 'Use when the user wants to improve an existing skill against a benchmark or bootstrap one for a new skill').

Rewrite in third-person action voice with concrete verbs (e.g. 'Optimizes a skill's SKILL.md body against a benchmark via validation-gated, budget-capped text-space edits') and drop 'SkillOpt-paper-grounded' jargon from the description.

Surface natural user phrasings the user would actually say ('optimize this skill', 'make the skill better') into the description, not just the triggers: list.

DimensionReasoningScore

Specificity

Names a concrete domain and mechanism ("Self-evolving skill optimization", "text-space optimizer") but lists no concrete actions — closer to 'Names domain and some actions' than the vague 'Helps with documents' anchor at 1, yet not the multi-action list required for 3.

2 / 3

Completeness

It states a (vague) 'what' but has no 'Use when...' or equivalent explicit 'when' guidance, so per the guidelines completeness is capped at 2 ('Has what, but when is missing or only implied').

2 / 3

Trigger Term Quality

The description contains only technical jargon ("SkillOpt-paper-grounded", "text-space optimizer") with no natural keywords a user would say, matching the 'No natural keywords; technical jargon' anchor; natural triggers live only in the separate triggers: list, not the description.

1 / 3

Distinctiveness Conflict Risk

The niche is clearly distinct — a meta-skill that optimizes other skills — making it unlikely to trigger for the wrong skill, even though the description lacks explicit trigger phrasing.

3 / 3

Total

8

/

12

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
garrytan/gbrain
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.