continuous-learning

[DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor. v2 is a strict superset with instinct-based, project-scoped, hook-reliable learning. Do not invoke v1: when continuous learning, session learning, or pattern extraction is requested, route to continuous-learning-v2 instead.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/continuous-learning/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 body delivers concrete config and hook-setup guidance but is padded with archival and research-comparison content that inflates token cost. Workflow sequencing lacks validation checkpoints, and progressive disclosure is weakened by missing bundle files and inlined material that should be split out.

Suggestions

Move the 'Comparison Notes (Research: Jan 2025)' and v2 enhancement sections into a separate archived reference file to reduce token load, or remove them given the skill is deprecated.

Add an explicit validation/checkpoint step (e.g., confirm extracted patterns meet extraction_threshold before writing to ~/.claude/skills/learned/) so the batch extraction workflow clears the workflow-clarity cap.

Either bundle the referenced evaluate-session.sh under scripts/ and the v2 spec under references/, or remove the dangling references so progressive-disclosure navigation is resolvable one level deep.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with config and hook JSON blocks that earn their place, but padded with a 'Why Stop Hook?' section explaining benefits Claude already knows and a 'Research: Jan 2025' comparison block that is largely archival filler.	3 / 5
Actionability	Provides concrete config.json contents, a copy-paste settings.json hook snippet, and explicit file paths, with only a minor gap (the referenced evaluate-session.sh is not bundled).	4 / 5
Workflow Clarity	The three-step How It Works sequence is present but lacks validation or feedback checkpoints for a batch session-analysis operation, which the rubric caps at 3.	3 / 5
Progressive Disclosure	Section headers provide some structure, but no bundle files exist (references/, scripts/, assets/ absent) while the body references an unbundled v2 spec and script, and large archival/comparison sections are inlined that belong in separate files.	3 / 5
	Total	13 / 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.

The description is explicit about what the skill is and when it should trigger, including clear deprecation routing to v2. It is mostly distinct and includes natural trigger terms, though it frames capability through a deprecation lens rather than enumerating concrete extraction actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('Legacy v1 stop-hook skill extractor') and a couple concrete actions (extract patterns, route requests to v2, suppress v1 invocation), but does not enumerate the extraction capabilities comprehensively.	3 / 5
Completeness	Clearly states what it is ('Legacy v1 stop-hook skill extractor') and an explicit when clause ('when continuous learning, session learning, or pattern extraction is requested'), but the 'what' is framed as a deprecation redirect rather than a positive capability statement.	4 / 5
Trigger Term Quality	Includes natural trigger phrases users would say ('continuous learning', 'session learning', 'pattern extraction'), with good keyword coverage though missing some synonyms or extension variations.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (legacy v1 extractor) with an explicit routing directive to v2 that minimizes conflict risk, though the dual v1/v2 identity introduces minor overlap surface.	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
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: 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.