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

61%

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

53%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 well-structured deprecation stub whose archived v1 documentation is concrete and executable, but whose cross-references are all dangling (the extraction script and v2 spec file are absent from the bundle) and whose comparison/research section is padding. As a self-contained archive notice it works, but as a navigable skill it does not.

Suggestions

Remove or relocate the 'Notas de Comparación (Investigación: Ene 2025)' and 'Mejoras Potenciales v2' sections to the v2 spec file; they describe another skill's design and add ~30 lines of padding to a deprecated archive.

Fix the dangling references: either include `evaluate-session.sh` (and `config.json`) in a `scripts/` bundle or remove the hook-setup and config blocks that instruct Claude to use them.

Add a validation step to the 'Cómo Funciona' workflow (e.g., verifying a learned skill was written correctly before the session ends) to close the checkpoint gap in the extraction sequence.

Dimension	Reasoning	Score
Conciseness	The archived v1 docs are mostly tight (config JSON, hook snippet, pattern table), but the "Notas de Comparación (Investigación: Ene 2025)" section — a Homunculus feature table and a "Mejoras Potenciales v2" list — is research padding about v2's design that belongs in the v2 spec, not here. This is 'mostly efficient but includes some unnecessary explanation or could be tightened', not a 2, since the deprecated material is properly quarantined under a clearly marked archive heading.	3 / 5
Actionability	Concrete, copy-paste-ready artifacts dominate: the full `config.json` example, the `~/.claude/settings.json` hooks block, and the pattern-types table. It is not a 5 because the hook command points to `~/.claude/skills/continuous-learning/evaluate-session.sh` and the footer cites `docs/continuous-learning-v2-spec.md`, neither of which exists in this skill's bundle — minor gaps in executability.	4 / 5
Workflow Clarity	"Cómo Funciona" lists a real sequence (evaluar sesión -> detectar patrones -> extraer skills) with a concrete threshold ("10+ mensajes"), but there are no validation or error-recovery checkpoints and the extraction script that the workflow depends on is absent. This fits 'steps listed but validation gaps' rather than 4, whose 'most checkpoints present' bar is unmet.	3 / 5
Progressive Disclosure	No references/, scripts/, or assets/ directories exist, so every external pointer in the body — `evaluate-session.sh`, `config.json`, `/learn`, and `docs/continuous-learning-v2-spec.md` — is a dangling reference, leaving navigation non-functional; the inlined v2 comparison research is content that clearly belongs in a separate file. It avoids a 1 because nothing is nested two levels deep and the single file itself is sectioned.	2 / 5
	Total	12 / 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.

An effective deprecation/redirect description: it clearly states what v1 was, explicitly says not to invoke it, and routes natural user phrasings to v2. Its main weakness is that v1's own capabilities are barely described, though for a deprecated stub this matters less.

Dimension	Reasoning	Score
Specificity	The description names the domain and one concrete capability — "Extractor de skill por hook Stop v1 heredado" (legacy v1 skill extractor via Stop hook) — plus v2's traits ("aprendizaje basado en instintos, con alcance de proyecto y hooks confiables"), but coverage of v1's actual actions is minimal, matching the anchor 'names domain and 1-2 concrete actions, but not comprehensive'. It is not a 4 because it does not list several specific actions of the skill itself.	3 / 5
Completeness	Both parts are present: what it is ("Extractor de skill por hook Stop v1 heredado") and explicit when-guidance ("No invocar v1; dirigir solicitudes ... a continuous-learning-v2"), with concrete trigger phrases. It is not a 5 because the 'what' is thin — the v1 capabilities are only implied by the name, never enumerated.	4 / 5
Trigger Term Quality	It enumerates the natural phrases a user would say when routing requests — "aprendizaje continuo, aprendizaje de sesión y extracción de patrones" — plus "hook Stop" and the v2 name, giving good keyword coverage. It falls short of 5 because synonyms and English-language variations are absent, so a few natural terms are missing.	4 / 5
Distinctiveness Conflict Risk	The deprecation framing explicitly separates v1 from v2 and forbids invoking v1, creating a clear niche with distinct routing. It stays at 4 rather than 5 because it deliberately shares the exact trigger terms of the closely related continuous-learning-v2, a minor overlap risk inherent to redirect stubs.	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: c70874f

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.