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

58%

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

Fix and improve this skill with Tessl

tessl review fix ./docs/es/skills/continuous-learning-v2/SKILL.md

Quality

Content

57%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 well-structured with actionable commands and concrete setup instructions, but it is a single monolithic file with no progressive disclosure into reference files, and its batch/destructive workflows (evolve, promote) lack explicit validation checkpoints.

Suggestions

Move the version-comparison tables, scope decision guide, and confidence-scoring details into reference files (e.g., SCOPE.md, CHANGELOG.md) and link to them one level deep from SKILL.md.

Add explicit validation/feedback-loop steps to the evolve and promote workflows (e.g., confirm cluster contents before evolving, review affected instintos before promote).

Trim the duplicated feature descriptions between the intro, the v2.1 table, and the v2 table to reduce token overhead.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient, using tables, diagrams, and code blocks instead of prose, but includes some redundant explanation such as the two version-comparison tables and repeated feature restatements that could be tightened.	3 / 5
Actionability	It provides concrete executable guidance — slash commands, a complete settings.json hook block, file paths, and a migration command — with only minor gaps such as the illustrative non-executable instinct YAML.	4 / 5
Workflow Clarity	Setup and project-detection steps are sequenced, but the core evolution and promotion workflows (batch/destructive operations) lack explicit validation checkpoints and feedback loops, capping this at 3.	3 / 5
Progressive Disclosure	The skill has clear section structure but is a monolithic ~230-line SKILL.md with all content inline and no bundle files or external references signaled, so content that could live in separate files is inlined.	3 / 5
	Total	13 / 20 Passed

Description

58%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 concretely describes what the system does across several actions but omits any explicit 'Use when...' trigger guidance, relying on internal vocabulary rather than natural user phrases. It is specific and distinct, yet not comprehensive on the 'when' dimension.

Suggestions

Add an explicit 'Use when...' clause naming natural user triggers (e.g., 'Use when you want Claude Code to learn from your sessions, extract reusable behaviors, or manage project-specific vs global patterns').

Replace or supplement internal jargon ('instintos', 'homunculus') with terms users would naturally say, such as 'learned behaviors', 'patterns', or 'project conventions'.

Include common synonyms and file/concept extensions (e.g., 'confidence thresholds', 'export/import learned patterns') to broaden natural keyword coverage.

Dimension	Reasoning	Score
Specificity	The description names the domain and several concrete actions ('observa sesiones mediante hooks', 'crea instintos atómicos con puntuación de confianza', 'los evoluciona en skills/comandos/agentes'), with only minor coverage gaps.	4 / 5
Completeness	It gives a clear 'what' but lacks any 'when' or 'Use when...' trigger guidance, which caps completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	It includes some relevant keywords ('instintos', 'hooks', 'alcance de proyecto') but these are internal jargon rather than natural phrases a user would say, and common synonyms are missing.	3 / 5
Distinctiveness Conflict Risk	The instinct-based learning niche with project-scope isolation is mostly distinct from generic memory skills, with only minor overlap risk.	4 / 5
	Total	14 / 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-v2/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.