graph-controls-designer

Disena controles falsificables para graphs y arneses: METHOD observable obligatorio (sin method el estado es 'No ejecutado', nunca un puntaje), falsification_test ejercitado antes de que 'Pasó' signifique algo, satisfacibilidad al nacer (pass, regression o debt_budget decreciente) y proxies que reportan lo que miden. Usar al pedir 'disena controles', 'criterios verificables', 'gate que pueda fallar', 'metricas sin puntajes inventados'. NO para estrategia de testing de software (testing-strategy) ni escenarios BDD (bdd-full-spectrum).

Quality

79%

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 ./plugins/claude-native-toolkit/skills/graph-controls-designer/SKILL.md

Quality

Content

71%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.

A concise, well-structured instruction skill with a clear sequenced procedure and a real validation checkpoint. The main weakness is progressive disclosure: the generated Packet block lists bundle layers that do not exist in this packet.

Suggestions

Trim or regenerate the Packet block so it only lists bundle directories that actually exist (references/, scripts/, assets/), or mark the absent layers as not-included for this packet.

Add an explicit fix-and-revalidate feedback loop after the validation step (e.g., 'si hay hallazgos: corrige y re-valida hasta cero') to lift workflow clarity toward 5.

Move or remove the cross-skill schema path ('.../graph-spec-compiler/scripts/../assets/control.schema.json') so the inline reference resolves within reach and is clearly signaled.

Dimension	Reasoning	Score
Conciseness	The body is lean and domain-specific ('Un control sin metodo... es decoracion verde'), assuming Claude's competence without explaining basic concepts; minor explanatory asides like the 'Modo de fallo' notes keep it just below a 5.	4 / 5
Actionability	Provides a concrete executable command ('python3 ${CLAUDE_PLUGIN_ROOT}/skills/graph-spec-compiler/scripts/validate_graph_spec.py --controls <controls.json>') and a numbered procedure; the remaining instructional steps are appropriately actionable for an instruction-only skill with minor gaps.	4 / 5
Workflow Clarity	A clear 5-step Procedimiento with an explicit validation checkpoint (step 4: 'Valida el set ... cero hallazgos'), but no explicit error-recovery feedback loop (fix-and-revalidate) holds it below 5.	4 / 5
Progressive Disclosure	The real one-level reference 'references/asimetria-y-satisfacibilidad.md' exists and is well-placed, but the Packet block advertises bundle directories (knowledge/, prompts/, examples/, agents/) that are not present in this bundle, creating misleading navigation.	3 / 5
	Total	15 / 20 Passed

Description

87%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.

A strong, specific description that clearly states what the skill does, when to use it with natural trigger phrases, and where its boundaries lie relative to neighboring skills. Its only weakness is jargon density that slightly limits plain-language accessibility.

Dimension	Reasoning	Score
Specificity	Lists several concrete capabilities — 'METHOD observable obligatorio', 'falsification_test ejercitado', 'satisfacibilidad al nacer', 'proxies que reportan lo que miden' — giving comprehensive coverage of the domain, though the dense jargon keeps it just below a perfect 5.	4 / 5
Completeness	Explicitly answers both what ('Disena controles falsificables para graphs y arneses...') and when ('Usar al pedir...') with concrete trigger phrases, plus negative guidance on what not to use it for.	5 / 5
Trigger Term Quality	Includes natural user phrases ('disena controles', 'criterios verificables', 'gate que pueda fallar', 'metricas sin puntajes inventados') that a user would actually say, with good coverage but a few obvious synonyms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche with distinct triggers and explicitly disambiguates from adjacent skills ('NO para estrategia de testing de software (testing-strategy) ni escenarios BDD (bdd-full-spectrum)'), minimizing conflict risk.	5 / 5
	Total	18 / 20 Passed

Validation

68%

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 — 11 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
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
referenced_paths_exist	Referenced path issues: 1 missing	Warning

	Total	11 / 16 Passed

Repository: JaviMontano/claude-plugins
Path: plugins/claude-native-toolkit/skills/graph-controls-designer/SKILL.md
Commit: e8f986b

Reviewed: 3 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.