skillify

The meta skill. Turn any raw feature into a properly-skilled, tested, resolvable unit of agent capability. Cross-modal eval is the recommended Phase 3 quality gate: 3 frontier models from different providers critique the output, you iterate to quality, THEN write tests that lock in the proven-good behavior.

Quality

63%

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 ./skills/skillify/SKILL.md

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 with executable commands and an exceptionally clear phased workflow including validation feedback loops. Its main weakness is conciseness/progressive disclosure: it is a long monolithic file that could offload detailed reference material into bundle files.

Suggestions

Move the cross-modal eval reference detail (default model table, provider configuration, cost expectations) into a references/ file and keep SKILL.md as a concise overview with a one-level-deep link, improving both conciseness and progressive_disclosure.

Trim the worked example to the essential before/after score delta and decision, cutting redundant narrative to recover token budget.

Consider condensing the cost-expectations and cycles/guardrail sections into a short bulleted summary since the command already prints cost estimates.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and avoids explaining concepts Claude already knows, but at ~290 lines it includes sections that could be tightened (cost expectations, provider configuration, the verbose worked example), matching anchor 2 'mostly efficient but could be tightened' rather than the lean anchor-3.	2 / 3
Actionability	It provides copy-paste-ready commands ('gbrain eval cross-modal --task ... --output ...', 'bun test test/<skill>.test.ts', 'gbrain skillify check ... --json \| jq ...'), a copyable frontmatter template, and concrete pass criteria, matching anchor 3 'fully executable code/commands; copy-paste ready'.	3 / 3
Workflow Clarity	Phases 0-7 are clearly sequenced with explicit validation checkpoints (pass criteria, cycle-until-pass with <=3 cycles, KNOWN_GAPS fallback) and feedback loops for the eval gate, matching anchor 3 'clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	The skill is well-sectioned but monolithic: no references/scripts/assets bundle files exist and all detail (cross-modal eval mechanics, cost tables, provider config) lives inline in a ~290-line SKILL.md, matching anchor 2 'content that should be separate is inline' rather than a one-level-deep referenced structure.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 a clear purpose and domain but relies on coined/technical terms and omits an explicit 'Use when' trigger clause, leaving the 'when to use' answer only implied. It is specific enough to be useful but not comprehensive or maximally natural.

Suggestions

Add an explicit 'Use when...' clause naming natural user situations, e.g. 'Use when you have a raw feature that should become a reusable, tested, resolvable skill.'

Replace or supplement coined terms ('skillify', 'cross-modal eval') with plain-language phrasings a user would actually say to reduce jargon and improve trigger_term_quality.

Sharpen the action list with concrete verbs (e.g. 'audit missing skill items, run cross-model quality eval, write unit/integration tests, register resolver triggers') to lift specificity toward 3.

Dimension	Reasoning	Score
Specificity	The description names several actions ('Turn any raw feature into a properly-skilled, tested, resolvable unit', 'cross-modal eval...critique', 'write tests') but the verbs stay abstract compared to the anchor-3 example of multiple concrete actions; it is closer to 'Names domain and some actions' than to a fully concrete list.	2 / 3
Completeness	It clearly answers 'what' the skill does, but there is no explicit 'Use when...' or equivalent trigger guidance, so per the judging guidelines completeness is capped at 2 ('Has what, but when is missing or only implied').	2 / 3
Trigger Term Quality	Terms like 'skillify', 'cross-modal eval', and 'write tests' are relevant but lean technical; common natural variations a user would say are only partially covered, matching the anchor-2 'some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The meta-skill niche is somewhat specific, but generic-sounding triggers ('make this proper', 'add tests and evals') and the noted overlap with /cross-modal-review mean it 'could still overlap with similar skills', matching anchor 2 rather than a clearly distinct niche.	2 / 3
	Total	8 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	14 / 16 Passed

Repository: garrytan/gbrain
Path: skills/skillify/SKILL.md
Commit: 3fafb69

Reviewed: about 19 hours 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.