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

56%

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 ./docs/es/skills/continuous-learning/SKILL.md

Quality

Content

42%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 archived v1 documentation is concretely configured (config + hook setup are copy-paste ready) but is dragged down by a verbose research/comparison section, a missing core script, and a workflow without validation checkpoints. As a deprecated artifact it is serviceable, but as an active skill it is inefficient and incomplete.

Suggestions

Move the 'Notas de Comparación (Investigación: Ene 2025)' section and Homunculus table into a separate archived-notes file, keeping SKILL.md focused on what is needed to run or understand v1.

Bundle or inline the evaluate-session.sh script (or at minimum its core detection/extraction logic) so the central behavior is executable rather than described at a high level.

Add an explicit validation/review checkpoint to the 'Cómo Funciona' workflow (e.g. confirm extracted skill quality before saving when auto_approve=false), turning the three steps into a feedback-loop sequence.

Dimension	Reasoning	Score
Conciseness	The body is noticeably verbose: the 'Notas de Comparación (Investigación: Ene 2025)' section with a full Homunculus feature table and a five-item v2 improvements list is research padding that does not help Claude execute the archived v1 skill.	2 / 5
Actionability	It provides concrete, copy-paste-ready config.json and Stop-hook settings.json blocks, but the central extraction logic ('Identifica patrones extraíbles', 'Guarda patrones útiles') stays high-level and the referenced evaluate-session.sh is not bundled.	3 / 5
Workflow Clarity	The three-step 'Cómo Funciona' sequence is present but lacks validation checkpoints for a batch extraction operation, and the auto_approve=false review flow implied by the config is never described in the workflow.	3 / 5
Progressive Disclosure	Section headers give reasonable structure, but the comparison/research content is inlined instead of split out, and the reference to docs/continuous-learning-v2-spec.md points to a file that is not present in the bundle.	3 / 5
	Total	11 / 20 Passed

Description

70%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 well-constructed deprecation redirect: it clearly identifies the legacy skill, explains the v2 superset relationship, and gives explicit trigger-to-v2 routing. It is held back from a top score because it describes the redirect more comprehensively than the skill's own capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain and a concrete mechanism ('Extractor de skill por hook Stop v1 heredado') plus a redirect action, but does not comprehensively list the skill's own capabilities, focusing instead on deprecation/redirect framing.	3 / 5
Completeness	It states what v1 is (Stop-hook skill extractor) and gives explicit when/redirect guidance ('dirigir solicitudes de aprendizaje continuo, aprendizaje de sesión y extracción de patrones a continuous-learning-v2'), but the 'when' is framed as a deprecation redirect rather than a clean active-use trigger.	4 / 5
Trigger Term Quality	It includes several natural trigger phrases a user would say ('aprendizaje continuo', 'aprendizaje de sesión', 'extracción de patrones'), though a few synonyms are missing and no file extensions apply to this meta-skill.	4 / 5
Distinctiveness Conflict Risk	The niche is clear and the description actively manages the v1/v2 overlap ('No invocar v1; dirigir ... a continuous-learning-v2'), leaving only minor conflict risk with the closely related v2 skill.	4 / 5
	Total	15 / 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
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: docs/es/skills/continuous-learning/SKILL.md
Commit: d8409a4

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.