continuous-learning-v2

Sistema de aprendizaje basado en instintos que observa sesiones mediante hooks, crea instintos atómicos con puntuación de confianza y los evoluciona en skills/comandos/agentes. v2.1 agrega instintos con alcance de proyecto para prevenir contaminación entre proyectos.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is strongly actionable with concrete config and commands, but it is a monolithic single file lacking bundle references and its setup workflow omits validation checkpoints.

Suggestions

Add a verification step to the quick-start workflow, e.g. confirming the hook is registered and that observations.jsonl is written after a first tool use.

Split detailed material (full hook configuration, scope-decision guide, changelog tables) into reference files under references/ and link to them one level deep.

Tighten the two changelog tables and the ASCII flow diagram, or move them to a reference file, to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The body is substantive and avoids explaining concepts Claude knows, but the dual v2.0/v1 changelog tables and the large ASCII flow diagram could be tightened to earn every token.	2 / 3
Actionability	Provides copy-paste-ready settings.json hook blocks, a concrete command list (/instinct-status, /evolve, etc.), a real migration command, and a complete YAML instinct example.	3 / 3
Workflow Clarity	The pipeline is sequenced and quick-start is a clear 2-step flow, but the fragile hook-setup workflow lacks validation checkpoints (e.g. verifying hooks registered or observations.jsonl written), capping it at 2.	2 / 3
Progressive Disclosure	Sections are well-organized, but everything is inline in one ~230-line file with no bundle files present; referenced paths (scripts/migrate-homunculus.sh, hooks/observe.sh) do not resolve to an actual bundle.	2 / 3
	Total	9 / 12 Passed

Description

67%

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 states concrete capabilities and occupies a distinct niche, but it omits an explicit 'when to use' trigger clause and leans on architectural jargon over natural user phrasing.

Suggestions

Add an explicit trigger clause, e.g. 'Úsalo cuando quieras aprendizaje automático de sesiones de Claude Code o gestionar instintos/comportamientos aprendidos.'

Replace some architectural jargon ('instintos atómicos', 'alcance de proyecto') with natural phrasing a user would actually say when invoking the skill.

Front-load the user-facing purpose before the v2.1 changelog detail so the trigger is immediately apparent.

Dimension	Reasoning	Score
Specificity	Names multiple concrete actions — 'observa sesiones mediante hooks', 'crea instintos atómicos con puntuación de confianza', 'evoluciona en skills/comandos/agentes' — matching the multiple-specific-actions anchor.	3 / 3
Completeness	Clearly states what the system does but lacks any 'Use when...' / 'Cuándo usar' trigger clause, which per the guidelines caps completeness at 2.	2 / 3
Trigger Term Quality	Terms like 'instintos', 'hooks', 'alcance de proyecto' are architectural jargon; a user would more naturally say 'aprendizaje automático' or 'recordar patrones', so common variations are missing.	2 / 3
Distinctiveness Conflict Risk	The instinct-based learning niche with project scoping is clearly distinct and unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Commit: 4130457

Reviewed: 1 day 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.