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

58%

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

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 v1 core content (config, hook setup, pattern types) is concrete and usable, but the body is dragged down by ~40 lines of v2 comparison/research padding, a hook script reference with no corresponding file, and a workflow with no validation or verification steps. For a deprecated archival skill it should be far leaner.

Suggestions

Delete the "Comparison Notes (vs Homunculus)" and "Potential v2 Enhancements" sections — they duplicate docs/continuous-learning-v2-spec.md and belong there, not in this skill.

Add the missing evaluate-session.sh to the bundle (or an inline minimal version), and a step verifying the Stop hook fires correctly after setup.

Expand "How It Works" into an executable sequence with explicit checkpoints (e.g., how a pattern is validated before being saved to ~/.claude/skills/learned/), instead of one-line descriptions.

Dimension	Reasoning	Score
Conciseness	The "Why Stop Hook?" rationale, the "Comparison Notes (Research: Jan 2025)" table, and the "Potential v2 Enhancements" list (~40 lines) restate v2 planning material the file itself says lives in docs/continuous-learning-v2-spec.md — whole padded sections that don't earn their place in a deprecated skill. Not 3 because the verbosity is entire sections rather than incidental sentences; not 1 because the v1 core (config, hook setup, pattern table) is reasonably tight.	2 / 5
Actionability	Copy-pasteable config.json and settings.json hook blocks and a concrete pattern-types table are present, but the hook invokes ~/.claude/skills/continuous-learning/evaluate-session.sh which does not exist in the bundle, and "How It Works" describes rather than instructs. Concrete guidance exists but key executable details are missing.	3 / 5
Workflow Clarity	A three-step "How It Works" sequence exists but the steps are vague descriptions ("Checks if session has enough messages") with no validation checkpoints, no hook-verification step after setup, and no error-recovery loop. Not 4 because checkpoints are entirely absent rather than minor gaps.	3 / 5
Progressive Disclosure	Section headers give reasonable structure, but the research/comparison material that clearly belongs in a separate file is inlined, and the only external reference (docs/continuous-learning-v2-spec.md) is not a real file in the bundle and is not clearly signaled as a bundle path.	3 / 5
	Total	11 / 20 Passed

Description

73%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 a well-executed deprecation pointer: it states what the legacy skill was, gives explicit trigger phrases, and cleanly resolves the conflict with its v2 replacement. Its main weakness is thin coverage of the v1 skill's actual capabilities, though that is largely inherent to a deprecated-redirect description.

Dimension	Reasoning	Score
Specificity	"Legacy v1 stop-hook skill extractor" names the domain plus one concrete action, and the routing directive is explicit, but the description never states what v1 actually does (hook setup, config, pattern extraction) — matching the 'domain and 1-2 concrete actions, not comprehensive' anchor.	3 / 5
Completeness	It has both a 'what' ("stop-hook skill extractor") and an explicit 'when' ("when continuous learning... is requested, route to continuous-learning-v2 instead"), but the 'what' side is thin and archival rather than concretely describing capabilities, so it falls just below the top anchor.	4 / 5
Trigger Term Quality	"continuous learning, session learning, or pattern extraction" are natural phrases a user would say, giving good keyword coverage, though common variations like "learned skills" or "skill extraction" are missing.	4 / 5
Distinctiveness Conflict Risk	The intentional overlap with continuous-learning-v2 is explicitly resolved by "Do not invoke v1... route to continuous-learning-v2 instead", giving a clear niche with distinct triggers and minimal conflict risk.	5 / 5
	Total	16 / 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: 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.