continuous-learning

[OBSOLETO - usar continuous-learning-v2] Extractor de skill por hook Stop v1 heredado. v2 es un superconjunto estricto con aprendizaje basado en instintos, con alcance de proyecto y hooks confiables. No invocar v1; dirigir solicitudes de aprendizaje continuo, aprendizaje de sesión y extracción de patrones a continuous-learning-v2.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Advisory

Suggest reviewing before use

Quality

Content

50%

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 clearly organized reference for an obsolete v1 skill with useful configuration snippets, but it carries significant inline research/comparison material that inflates its token budget without serving the skill's current function. The core executable (evaluate-session.sh) is referenced but not provided, and validation steps for the extraction workflow are absent.

Suggestions

Move the Homunculus comparison table and 'Mejoras Potenciales v2' research notes into a separate archived doc and link to it, keeping the SKILL.md body focused on the v1 Stop-hook workflow.

Bundle or inline the evaluate-session.sh script so the central hook command is actually executable rather than a dangling reference.

Add a validation/checklist step to the extraction workflow (e.g., verify extracted patterns against ignore_patterns before writing to ~/.claude/skills/learned/) to lift workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with clear sections, but it includes substantial content that does not earn its place for an obsolete skill: a full Homunculus comparison table and 'Mejoras Potenciales v2' notes that restate concepts and research findings rather than guiding the user's current task.	2 / 3
Actionability	It provides concrete, copy-paste-ready configuration blocks (the config.json fields, the Stop hook settings.json snippet, and the evaluate-session.sh command path), but the referenced evaluate-session.sh script is never bundled or shown, leaving the central executable step incomplete.	2 / 3
Workflow Clarity	The 'Cómo Funciona' section lists a clear three-step sequence (evaluar, detectar, extraer), but there are no validation or verification checkpoints for the extraction/editing of learned skills, which the rubric expects for batch or destructive-style operations.	2 / 3
Progressive Disclosure	The content is well-sectioned and mostly inline-appropriate with a single one-level reference ('docs/continuous-learning-v2-spec.md'), but that referenced spec file is not present in the bundle and the comparison/research material that could live in a separate file is kept inline.	2 / 3
	Total	8 / 12 Passed

Description

22%

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 dominated by an obsolescence/deprecation notice that redirects to continuous-learning-v2, leaving it without a concrete capability statement or usable activation triggers for this skill itself. It functions as a tombstone rather than a functional skill description, which fails most rubric dimensions even though the redirect intent is clear.

Suggestions

If the skill is genuinely retired, keep only a one-line tombstone; otherwise rewrite the description to state concrete actions (e.g., 'Extracts reusable patterns from ended Claude Code sessions via a Stop hook') before the redirect note.

Add an explicit 'Use when...' clause tied to the v1 Stop-hook workflow so the 'what' and 'when' are both answerable instead of only the deprecation directive.

Replace first/second-person redirect phrasing with third-person capability language to preserve a usable description while still flagging v2 as preferred.

Dimension	Reasoning	Score
Specificity	The description describes no concrete actions of this skill; it is dominated by an obsolescence notice and a directive to use a different skill ('Extractor de skill por hook Stop v1 heredado', 'No invocar v1'), naming only a vague inherited category rather than specific capabilities.	1 / 3
Completeness	It explicitly states the skill is obsolete and should not be invoked, so it answers neither 'what does this do' nor 'when should Claude use it' in a usable way; the 'when' is an explicit 'do not use' instruction, capping completeness well below a usable trigger.	1 / 3
Trigger Term Quality	It does include some natural terms a user might say ('aprendizaje continuo', 'aprendizaje de sesión', 'extracción de patrones'), but these point the user away from this skill toward v2 rather than serving as activating triggers for v1.	2 / 3
Distinctiveness Conflict Risk	The strong deprecation framing makes it unlikely to be selected for the wrong skill, but it shares the 'continuous learning / pattern extraction' niche with continuous-learning-v2, so it is not clearly distinct and could overlap with v2 if the deprecation directive were ignored.	2 / 3
	Total	6 / 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.