skill-creator-linter

Internal tool (not user-invocable). Called by meta-skill-creator as a DAG step (kind: agent) to lint a candidate meta-skill SKILL.md against G1 (parse + reference check + xml_escape grep + structural lint) and G2 (scheduler dry-run with stub executors). Deterministic, sub-second, no LLM. Returns JSON diagnostics.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./src/opensquilla/skills/bundled/skill-creator-linter/SKILL.md

Quality

Content

86%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 lean, well-structured, and action-oriented with executable commands and clear validation gates, with only minor gaps in the fallback's concreteness and the absence of a specific diagnostic-driven recovery loop.

Dimension	Reasoning	Score
Conciseness	The body is roughly 30 lines with no padding and no explanation of concepts Claude already knows; the G1 rules table and each section are lean and every token earns its place, matching the anchor for lean and efficient content.	5 / 5
Actionability	Provides copy-paste ready commands ('uv run python {baseDir}/scripts/lint.py ...') and concrete rule specs (specific function names, grep pattern, output schema), matching the anchor for mostly executable guidance with minor gaps; not a 5 because the fallback ('run parse_meta_plan in a Python REPL') lacks exact code and G2 describes internals rather than a Claude action.	4 / 5
Workflow Clarity	The single action (run the linter) is unambiguous with G1/G2 as validation gates and a fallback recovery path, matching the anchor for a clear sequence with most checkpoints present; not a 5 because there is no specific 'if diagnostic X, do Y' loop beyond the generic fallback.	4 / 5
Progressive Disclosure	Under 50 lines with well-organized sections (G1 rules, G2 dry-run, Usage, Output, Fallback) and a single one-level reference to the real bundle file scripts/lint.py with no nested references, matching the simple-skills allowance for a 5 on well-organized short content.	5 / 5
	Total	18 / 20 Passed

Description

47%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 specific and highly distinctive with concrete, well-scoped actions, but it is dominated by internal jargon with no natural user trigger terms and lacks an explicit 'Use when...' trigger clause, capping completeness.

Suggestions

Add an explicit 'Use when...' or equivalent trigger clause so the 'when' is not only implied by orchestration context.

Introduce at least one natural-language keyword (e.g. 'validate', 'check') alongside the G1/G2 jargon to improve trigger-term quality.

Surface the concrete checks as a short enumerated list rather than a parenthetical bundle to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'parse + reference check + xml_escape grep + structural lint' and 'scheduler dry-run with stub executors' plus 'Returns JSON diagnostics' — matching the anchor for several specific actions with minor gaps; not a 5 because the actions are bundled parenthetically rather than cleanly and comprehensively enumerated.	4 / 5
Completeness	The 'what' is clear (lints a candidate meta-skill SKILL.md against G1/G2, returns JSON diagnostics) but the 'when' is only weakly implied via 'Called by meta-skill-creator as a DAG step' rather than an explicit 'Use when...' trigger, so per the guideline it caps at 3; not a 4 because the when is not an explicit user trigger condition.	3 / 5
Trigger Term Quality	The terms present — 'DAG step (kind: agent)', 'G1', 'G2', 'scheduler dry-run', 'stub executors', 'xml_escape grep' — are pure technical/internal jargon a user would never naturally say, matching the anchor for no natural keywords; not a 2 because no genuinely natural phrase dominates.	1 / 5
Distinctiveness Conflict Risk	It occupies a clear, narrow niche (linting candidate meta-skill SKILL.md against G1/G2) and is marked user-invocable: false / disable-model-invocation: true, giving minimal conflict risk, matching the anchor for a clear niche with distinct triggers.	5 / 5
	Total	13 / 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: TokenRhythm/opensquilla
Path: src/opensquilla/skills/bundled/skill-creator-linter/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.