copilot-expert

Use cuando reportes/investigues bug del copilot module: loops infinitos, cards faltantes, conversaciones vacías al refresh, extracción que falla, trazas que mienten, tools que no ejecutan, costos disparados, routing equivocado, prompt cache roto, mutaciones que no persisten, channel format ignorado, voseo en outputs. Activa también para extender (agregar provider, tool, workflow, channel, KB chunk) sin romper invariantes. Triggers: 'bug copilot', 'loop copilot', 'card no aparece', 'conversación vacía', 'documento no extrae', 'agente no responde', 'tool no ejecuta', 'trazas mienten', 'tokens burned', 'extract_document_to_fields falla', 'propose_field_updates no persiste', 'format_for_channel ignored', 'voseo en respuesta', 'cache hit rate', 'cuántos tokens', 'agregar provider', 'agregar workflow', 'agregar tool transversal', 'agregar canal'.

Quality

85%

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

Quality

Content

80%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 content is exceptionally actionable with concrete commands, SQL, and well-sequenced workflows backed by real reference bundles. Its main weakness is conciseness: the SKILL.md carries heavy phase-history and registry detail that could live in reference files.

Suggestions

Move the F0-F11 phase map, registry enumerations, and budget/plan-default tables into a reference file (e.g. references/copilot-architecture.md) and link from SKILL.md to shrink the inline token footprint.

Trim dated hotfix breadcrumbs (e.g. 'PR-1 PI-1.1 hotfix 2026-05-01') or relocate them to a 'historical gotchas' reference so the main body stays evergreen.

Consolidate the duplicated diagnostic ordering between the 'Diagnóstico' section and the 'Anchor — qué hago primero' section into a single canonical sequence.

Dimension	Reasoning	Score
Conciseness	The body is densely information-rich and largely free of explaining concepts Claude already knows, but it is extremely long and crammed with phase-by-phase history, registry enumerations, and dated gotchas that push the token budget past what a lean overview needs.	3 / 5
Actionability	Provides concrete, copy-paste-ready SQL queries, bash pytest commands, exact file paths, and step-by-step procedures (diagnostic order, bug-fix protocol) that are directly executable.	5 / 5
Workflow Clarity	Multi-step processes are strictly sequenced with numbered orders, validation checkpoints (RED→GREEN, quality gates, pre-cierre checklist), and explicit feedback loops for error recovery across debugging and extension flows.	5 / 5
Progressive Disclosure	Two real one-level-deep reference bundles exist and are clearly signaled in an SSoT table and a final 'Project invariants' section; however a large amount of reference-grade detail (phase map, registry lists, budget tables) remains inlined in SKILL.md rather than split out.	4 / 5
	Total	17 / 20 Passed

Description

90%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 comprehensive and tightly scoped to the copilot module, answering both what and when with a dense, natural trigger-phrase list. Its only soft spot is that it lists symptoms more than the literal actions the skill performs.

Dimension	Reasoning	Score
Specificity	Lists many concrete symptom domains (loops infinitos, cards faltantes, conversaciones vacías al refresh, extracción que falla, trazas que mienten, etc.) and concrete extension tasks (agregar provider/tool/workflow/channel/KB chunk); minor gaps in phrasing the actions themselves rather than only symptoms.	4 / 5
Completeness	Explicitly answers 'what' ('Use cuando reportes/investigues bug del copilot module' + extension scope) and 'when' with a concrete 'Triggers:' clause of phrases; both halves are present and concrete.	5 / 5
Trigger Term Quality	Includes a dense, explicit 'Triggers:' list of natural phrases users would say ('card no aparece', 'conversación vacía', 'tool no ejecuta', 'tokens burned', 'cache hit rate', 'agregar provider', etc.) covering many synonyms and symptom phrasings.	5 / 5
Distinctiveness Conflict Risk	Scoped tightly to the copilot module's specific bug classes and extension points, with distinctive trigger phrases unlikely to fire for unrelated skills; minimal conflict risk.	5 / 5
	Total	19 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 2 missing, 1 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: alpacapurpura/luana-method
Path: claude/skills/copilot-expert/SKILL.md
Commit: caa08df

Reviewed: ~22 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.