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

22%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Critical

Do not install without reviewing

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/continuous-learning-v2/SKILL.md

Quality

Content

27%

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

This skill is a comprehensive reference document masquerading as a SKILL.md. It contains useful information about the instinct-based learning system but is far too verbose, mixing marketing copy, architectural explanations, version history comparisons, and operational instructions into a single long file. The actionable content (hook setup, CLI commands) is buried among explanatory material that Claude doesn't need, and critical validation steps for verifying the system is working correctly are absent.

Suggestions

Cut the file to ~80 lines: keep only Quick Start (hook setup + commands) and essential config. Move version comparison tables, scope decision guide, confidence scoring details, file structure, and architecture diagrams to separate referenced files.

Remove sections that explain concepts to Claude rather than instruct it: 'Why Hooks vs Skills', the v1-vs-v2 comparison table, the 'What's New' sections, and the marketing tagline.

Add validation checkpoints: after enabling hooks, show how to verify observations are being captured (e.g., 'Run a command, then check observations.jsonl has new entries'); after running /evolve, show how to verify output.

Clarify the relative path to instinct-cli.py and observe.sh — the commands reference these scripts but their location relative to the skill root is ambiguous without bundle context.

Dimension	Reasoning	Score
Conciseness	Extremely verbose at ~300+ lines. Includes extensive comparison tables (v1 vs v2, v2 vs v2.1), explains concepts Claude already understands (what hooks are, why deterministic > probabilistic), includes marketing-style copy ('teaching Claude your patterns, one project at a time'), and repeats information across sections (scope info appears in multiple places). The 'Why Hooks vs Skills' section explains something Claude doesn't need justified.	1 / 3
Actionability	Provides concrete JSON config for hooks setup and bash commands for directory creation and CLI usage, which is good. However, the instinct-cli.py commands reference a script without showing its location relative to the skill, the YAML instinct format is illustrative rather than executable, and the actual observation/analysis pipeline is described abstractly (ASCII diagram) rather than with concrete implementation steps.	2 / 3
Workflow Clarity	The Quick Start provides a reasonable 3-step sequence (enable hooks → init directories → use commands), and the promotion workflow has clear steps. However, there are no validation checkpoints — no way to verify hooks are firing correctly, no way to confirm observations are being captured, no verification that the observer agent is running. For a system involving background processes and file manipulation, this is a significant gap.	2 / 3
Progressive Disclosure	Everything is in one monolithic file with no references to separate documentation files for detailed topics. The file structure, scope decision guide, confidence scoring details, backward compatibility notes, and version comparison tables could all be in separate referenced files. The content that should be a quick overview is instead a comprehensive reference document. No bundle files are provided to offload detail into.	1 / 3
	Total	6 / 12 Passed

Description

17%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This description reads like an internal architecture summary or release note rather than a functional skill description. It is heavy on jargon ('atomic instincts', 'confidence scoring', 'cross-project contamination') without explaining what concrete value it provides to the user or when Claude should invoke it. The lack of natural trigger terms and a 'Use when...' clause makes it very difficult for Claude to correctly select this skill.

Suggestions

Add an explicit 'Use when...' clause describing the scenarios that should trigger this skill, e.g., 'Use when the user wants to automatically learn patterns from sessions and generate reusable skills or commands.'

Replace jargon with natural language trigger terms users would actually say, such as 'learn from sessions', 'auto-generate skills', 'pattern recognition', or 'session observation'.

Rewrite the description to focus on user-facing outcomes rather than internal architecture, e.g., 'Automatically learns recurring patterns from coding sessions and generates reusable skills, commands, and agents. Supports project-scoped learning to keep patterns isolated per project.'

Dimension	Reasoning	Score
Specificity	Names some actions like 'observes sessions via hooks', 'creates atomic instincts with confidence scoring', and 'evolves them into skills/commands/agents', but these are domain-specific jargon rather than concrete user-facing actions. The description is more about internal architecture than what it concretely does for the user.	2 / 3
Completeness	While there is a partial 'what' (though expressed in abstract/architectural terms), there is no 'Use when...' clause or any explicit guidance on when Claude should select this skill. The description reads more like a changelog entry than a skill description.	1 / 3
Trigger Term Quality	The description uses highly specialized jargon ('atomic instincts', 'confidence scoring', 'hooks', 'cross-project contamination') that users would almost never naturally say. There are no natural trigger terms a user would use when needing this skill.	1 / 3
Distinctiveness Conflict Risk	The highly specialized terminology ('instinct-based learning', 'atomic instincts') makes it somewhat distinctive, but the vagueness of what it actually does ('evolves them into skills/commands/agents') could overlap with other meta-learning or skill-management tools.	2 / 3
	Total	6 / 12 Passed

Validation

81%

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 — 9 / 11 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	9 / 11 Passed

Repository: affaan-m/everything-claude-code
Commit: ec92b52

Reviewed: about 2 hours 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.