continuous-learning-v2

Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.

Quality

52%

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/zh-TW/skills/continuous-learning-v2/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.

The body is action-oriented and lays out a clear pipeline, but it is a monolithic single-file document with no real progressive disclosure to separate reference files, and its batch/learning operations omit validation checkpoints. Bundle files referenced in the text do not exist alongside the skill.

Suggestions

Move the full config.json reference, instinct YAML schema, and file-structure map into separate reference files (e.g., CONFIG.md, INSTINCT-SCHEMA.md) and link to them from a concise overview.

Add explicit validation/verification checkpoints for batch operations — e.g., after /evolve clustering, verify generated skills/commands/agents are well-formed before promoting them.

Either ship the referenced hooks/observe.sh, hooks/hooks.json, and agents/start-observer.sh as bundle files or remove the references, since they currently point to non-existent paths.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete config and code blocks, but the v1/v2 comparison table, philosophy section ("為何 Hooks vs Skills"), and inlined full config reference add length that could be trimmed.	3 / 5
Actionability	Provides executable bash commands, hooks JSON registration, an instinct YAML example, and a full config.json, though commands like /evolve and /instinct-status are listed without implementation detail.	4 / 5
Workflow Clarity	The observe → pattern-detect → instinct → evolve pipeline is sequenced via the ASCII diagram, but batch/auto-approve operations (auto_approve_threshold, /evolve clustering) lack validation checkpoints, capping workflow_clarity at 3.	3 / 5
Progressive Disclosure	No bundle reference files exist, yet the body is a ~260-line monolith inlining a full config schema, instinct YAML schema, and file-structure map; references to hooks/observe.sh and agents/start-observer.sh point to files absent from the bundle.	2 / 5
	Total	12 / 20 Passed

Description

51%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 conveys concrete capabilities and a distinct niche, but it is written in technical jargon rather than natural trigger terms and omits any explicit "Use when..." guidance. Completeness is capped at 3 for the missing trigger clause.

Suggestions

Add an explicit "Use when..." clause naming natural triggers (e.g., "Use when you want Claude to learn from your session patterns and build reusable instincts/skills").

Replace jargon-heavy phrases ("atomic instincts with confidence scoring") with language users would actually say, and include common synonyms.

Tighten the capability list toward the highest-value actions so it reads as comprehensive rather than enumerative.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "observes sessions via hooks", "creates atomic instincts with confidence scoring", "evolves them into skills/commands/agents" — but lacks the fine-grained coverage of a 5.	4 / 5
Completeness	Has a clear "what" but no "Use when..." trigger clause, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Keywords are technical jargon ("atomic instincts", "confidence scoring", "hooks") rather than phrases a user would naturally say; only generic terms like "learning system" and "skills/commands/agents" appear.	2 / 5
Distinctiveness Conflict Risk	The instinct-based learning niche is mostly distinct with only minor overlap risk against generic learning/memory skills.	4 / 5
	Total	13 / 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/zh-TW/skills/continuous-learning-v2/SKILL.md
Commit: e04ea0b

Reviewed: 2 days 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.