skillify

The meta skill. Turn any raw feature into a properly-skilled, tested, resolvable unit of agent capability. Idempotent: running on an existing skill improves it (bug fix, new input, quality pass) instead of starting from scratch. Every skill declares an EVAL CONTRACT (its goal + skill-specific dimensions + hard-fails) so the cross-modal eval judges THIS skill's real purpose, not generic slop. Cross-modal eval runs BEFORE tests: 3 frontier models from different providers critique the output against the contract, you iterate to quality, THEN write/update tests that lock in the proven-good behavior. NO-REGRESSION LAW: any edit to a skill must score >= the previous iteration's eval — forward only, never back. For skills that back a scheduled job, an edit MUST re-run a representative task and eval it before shipping.

Quality

76%

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

81%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 a well-sequenced, highly actionable meta-skill with explicit validation gates and feedback loops, and clear one-level references to related skills. Its only notable weakness is conciseness — recurring restatements of the no-regression law and a few over-explanatory asides could be trimmed.

Suggestions

Deduplicate the no-regression law: state it once in the Contract section and reference it (e.g., 'see Phase 3.5') elsewhere rather than restating the full rule in Phase 3.5, Anti-Patterns, and Quality Gates.

Trim explanatory asides that restate concepts Claude already knows (e.g., 'Tests lock in behavior. If the behavior is mediocre, tests lock in mediocrity.') down to the skill-specific implication.

Consider extracting the 15-item checklist and/or the provider/cost tables into a reference file so SKILL.md reads as a leaner overview, lifting progressive_disclosure toward 5.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and skill-specific, but the no-regression law is restated four times (frontmatter, Contract, Phase 3.5, Anti-Patterns) and a few explanatory asides ('Tests lock in behavior. If the behavior is mediocre, tests lock in mediocrity.') restate concepts Claude already grasps, so it could be tightened.	3 / 5
Actionability	Provides fully executable, copy-paste-ready commands (gbrain eval cross-modal --task ... --dimensions ... --output ..., gbrain skillify check, gbrain check-resolvable --json, bun test, jq recipes) plus complete frontmatter, bug-fix, and hard-rule templates and two concrete worked examples covering common cases.	5 / 5
Workflow Clarity	Phases 0-7 form a clear sequence with explicit validation checkpoints (Phase 7 Verify commands, Phase 3.5 no-regression compare logic) and feedback loops (eval -> fix -> re-eval, cycle until pass <=3), including the destructive/batch skill-edit re-verify loop required by the rubric.	5 / 5
Progressive Disclosure	Section headers organize the content and external references (skills/RESOLVER.md, skills/conventions/cron-via-minions.md, skills/cron-scheduler/SKILL.md, skills/minion-orchestrator/SKILL.md) are one level deep and clearly signaled, but no bundle files exist and the whole skill is a single large file with some cross-section redundancy, leaving minor organization gaps.	4 / 5
	Total	17 / 20 Passed

Description

71%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 is highly specific and distinctive, naming a comprehensive set of concrete capabilities for a meta-skill. Its main weakness is the missing explicit 'Use when...' trigger guidance inside the description, which caps completeness despite the separate triggers field.

Suggestions

Add an explicit 'Use when...' clause to the description (e.g., 'Use when the user says skillify, asks to check skill completeness, or wants to add tests and evals to a feature') so trigger guidance lives in the description itself rather than only the triggers field.

Surface a few more natural trigger synonyms in the description prose (e.g., 'skillify', 'turn this into a skill', 'make this proper') to lift trigger-term coverage toward comprehensive.

Tighten the distinctiveness framing by clarifying in one phrase how skillify differs from /cross-modal-review so the meta-skill niche reads as fully non-overlapping.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions ('Turn any raw feature into a properly-skilled, tested, resolvable unit', 'declares an EVAL CONTRACT', '3 frontier models from different providers critique the output', 'write/update tests that lock in the proven-good behavior', 're-run a representative task and eval it'), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	The 'what' is clear and concrete, but the description contains no explicit 'Use when...' clause or equivalent trigger guidance inline; triggers live only in a separate frontmatter field, so per the judging guideline completeness is capped at 3.	3 / 5
Trigger Term Quality	Natural trigger terms like 'skillify', 'properly-skilled', 'cross-modal eval', 'tests and evals' are present and a rich triggers list exists, but the description body itself does not enumerate the synonym/extension breadth of the anchor-5 example. It sits clearly above the anchor-3 ('Works with PDF files') level but just short of comprehensive synonym coverage.	4 / 5
Distinctiveness Conflict Risk	'skillify', 'the meta skill', 'EVAL CONTRACT', and 'no-regression law' carve a distinct niche with minimal conflict risk, but the body itself notes an overlap relationship with /cross-modal-review, leaving minor overlap risk with that closely related skill.	4 / 5
	Total	16 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (642 lines); consider splitting into references/ and linking	Warning
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	13 / 16 Passed

Repository: garrytan/gbrain
Path: skills/skillify/SKILL.md
Commit: 055ac6c

Reviewed: about 2 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.