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. v2.1 adds project-scoped instincts to prevent cross-project contamination.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Quality

Content

77%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with clear, sequenced workflows and concrete commands, but it is monolithic and carries inline version-history and reference material that could be split into separate files.

Suggestions

Move the version-comparison tables (v1/v2/v2.1) into a CHANGELOG or deprecated section, or remove legacy-version rows from the main overview.

Extract the Scope Decision Guide, Confidence Scoring reference, and full File Structure into reference files under references/ linked one level deep from SKILL.md.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with useful tables and diagrams, but the inline 'What's New in v2.1' and 'v2 vs v1' version-history tables are time-sensitive padding not relegated to a deprecated section.	2 / 3
Actionability	Provides copy-paste-ready hook settings.json, concrete /instinct-* commands, mkdir snippets, and a config.json example — fully executable guidance.	3 / 3
Workflow Clarity	Quick Start is explicitly sequenced, the ASCII pipeline shows the observe→detect→evolve flow, and promotion offers a --dry-run validation checkpoint for a batch/destructive operation.	3 / 3
Progressive Disclosure	A monolithic ~360-line SKILL.md keeps reference-grade content (scope guide, confidence tables, full file structure) inline; only script paths are split out and no references/ files exist to offload detail.	2 / 3
	Total	10 / 12 Passed

Description

67%

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 omits explicit use-when triggers and leans on project-specific jargon rather than natural user keywords.

Suggestions

Append a 'Use when ...' clause naming natural triggers (e.g., 'Use when setting up automatic session learning, extracting learned behaviors, or managing project vs global patterns').

Soften jargon by pairing internal terms ('instincts', 'homunculus') with plain-language equivalents a user would actually say.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "observes sessions via hooks", "creates atomic instincts with confidence scoring", "evolves them into skills/commands/agents" — matching the multi-action anchor.	3 / 3
Completeness	Clearly answers what the skill does, but lacks any "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Relevant terms exist but lean heavily on internal jargon ("instinct", "confidence scoring", "project-scoped instincts") that a user would not naturally utter; missing common variations.	2 / 3
Distinctiveness Conflict Risk	The instinct-based, hook-driven, project-scoped framing carves a clear niche unlikely to trigger for unrelated skills.	3 / 3
	Total	10 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: affaan-m/everything-claude-code
Commit: 4130457

Reviewed: 4 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.