CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

29

Quality

22%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Advisory

Suggest reviewing before use

Optimize this skill with Tessl

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

Quality

Discovery

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 a technical changelog or README summary rather than a skill selection description. It is heavy on internal architecture jargon ('atomic instincts', 'confidence scoring', 'cross-project contamination') but fails to communicate in user-facing terms what it does or when it should be triggered. The absence of a 'Use when...' clause and lack of natural trigger terms make it very difficult for Claude to know when to 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 trigger terms users would actually say, such as 'learn from usage', 'auto-generate skills', 'session patterns', 'adaptive automation'.

Rewrite the 'what' portion to describe user-facing outcomes rather than internal architecture, e.g., 'Automatically learns recurring patterns from coding sessions and generates reusable skills, commands, and agents' instead of 'creates atomic instincts with confidence scoring'.

DimensionReasoningScore

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' (observes sessions, creates instincts, evolves into skills), there is no 'when' clause or any explicit trigger guidance for when Claude should select this skill. The description reads like a changelog/feature summary rather than selection guidance.

1 / 3

Trigger Term Quality

The keywords used ('instinct-based learning system', 'atomic instincts', 'confidence scoring', 'cross-project contamination') are highly technical internal jargon that no user would naturally say when requesting this functionality. There are no natural trigger terms a user would use.

1 / 3

Distinctiveness Conflict Risk

The highly specialized terminology ('instinct-based learning', 'atomic instincts', 'confidence scoring') makes it unlikely to conflict with other skills, but the vagueness of what it actually does could cause confusion about when to select it versus other learning/automation skills.

2 / 3

Total

6

/

12

Passed

Implementation

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 far too verbose for its purpose — it reads more like product documentation or a README than an actionable skill file. It spends significant tokens on version comparison tables, architectural diagrams, and conceptual explanations that don't help Claude execute tasks. The actionable content (hook setup, CLI commands, directory structure) is buried in explanatory prose and could be condensed to roughly one-third the current length.

Suggestions

Cut the v1 vs v2 comparison table entirely and reduce the v2.0 vs v2.1 table to only what's needed for migration — Claude doesn't need product changelog context.

Move the file structure tree, scope decision guide, and confidence scoring table into separate reference files and link to them from a concise overview section.

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

Remove the 'Why Hooks vs Skills' explanation section — Claude doesn't need to understand the design rationale, just how to use the system.

DimensionReasoningScore

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), repeats information across sections (scope guide, promotion criteria appear multiple times), and includes marketing-style content ('teaching Claude your patterns, one project at a time').

1 / 3

Actionability

Provides concrete JSON config for hooks setup, bash commands for directory creation, and CLI commands with arguments. However, much of the content is descriptive/conceptual rather than executable — the instinct YAML model is illustrative, the ASCII flow diagram describes architecture rather than instructing action, and there's no executable code for the core observation/analysis pipeline itself.

2 / 3

Workflow Clarity

The Quick Start provides a numbered sequence (enable hooks → initialize 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 error recovery steps if the observer fails or directories aren't created properly.

2 / 3

Progressive Disclosure

This is a monolithic wall of text with no references to external files for detailed content. The file structure, scope decision guide, confidence scoring details, backward compatibility notes, and comparison tables could all be in separate reference files. Everything is inlined into one massive document with no clear navigation to supporting materials.

1 / 3

Total

6

/

12

Passed

Validation

90%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
affaan-m/everything-claude-code
Reviewed

Table of Contents

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.