meta-skill-creator

Use this meta-skill instead of answering directly only when the current user explicitly asks to create, compose, synthesize, or propose a new meta-skill that orchestrates multiple existing skills. It uses multi-skill orchestration for intent clarification, optional history mining, trigger-collision checks, linting, smoke/runtime gates, preview, and optional proposal persistence. Do not use it for creating a normal standalone skill, asking how meta-skills work, analyzing pasted skill lists, or discussing existing meta-skills.

Quality

89%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

78%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 tight, well-structured overview with strong failure-handling guidance and concrete paths, though the core multi-step DAG itself is encoded in the frontmatter rather than narrated in the markdown. It is efficient and actionable for an orchestrator skill.

Suggestions

Remove changelog framing ('It now separates...') and state the three modes as a flat fact to tighten conciseness.

Add a brief in-body sequence of the main DAG phases (clarify → assemble → collision/lint → smoke → preview → persist) so the primary workflow is legible without parsing the YAML.

Make the read_file verification step an explicit numbered checkpoint in the Fallback flow rather than only a prohibition.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence, but carries minor changelog-style framing ('It now separates preview-only, persisted-proposal, and fully gated modes') that could be trimmed; not a 5 because of those small padded spots.	4 / 5
Actionability	Concrete paths and commands are present ('~/.opensquilla/proposals/<id>/', 'opensquilla meta accept <id>', 'read_file tool') with actionable fallback directives, but the main orchestration steps live in frontmatter rather than as executable guidance in the body.	4 / 5
Workflow Clarity	The Fallback sub-process is a clear numbered sequence with an explicit 'Stop. Do NOT improvise' checkpoint and read_file validation, but the primary DAG workflow is summarized in prose rather than sequenced in the body (it resides in the YAML composition block).	4 / 5
Progressive Disclosure	The body is under 50 lines, needs no external bundle references (none exist), and is organized into a clear overview plus a Fallback section, satisfying the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

100%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 concrete, trigger-rich, and explicitly bounded with both positive and negative use conditions, cleanly answering what, when, and what-not. It is among the strongest examples in the reference set.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'intent clarification, optional history mining, trigger-collision checks, linting, smoke/runtime gates, preview, and optional proposal persistence' — with comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what (multi-skill orchestration pipeline) and when ('Use this meta-skill... only when the current user explicitly asks to create...'), reinforced by negative triggers ('Do not use it for...').	5 / 5
Trigger Term Quality	Covers natural synonyms users would say — 'create, compose, synthesize, or propose a new meta-skill that orchestrates multiple existing skills' — giving comprehensive keyword coverage for the niche.	5 / 5
Distinctiveness Conflict Risk	The negative boundary clause ('Do not use it for creating a normal standalone skill, asking how meta-skills work, analyzing pasted skill lists, or discussing existing meta-skills') carves a clear niche with minimal conflict risk.	5 / 5
	Total	20 / 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
skill_md_line_count	SKILL.md is long (592 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/meta-skill-creator/SKILL.md
Commit: 94ac35e

Reviewed: 4 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.