continuous-learning

Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.

Install with Tessl CLI

npx tessl i github:ysyecust/everything-claude-code --skill continuous-learning

What are skills?

Quality

41%

Does it follow best practices?

Impact

Pending

No eval scenarios have been run

Optimize this skill with Tessl

npx tessl skill review --optimize ./docs/zh-TW/skills/continuous-learning/SKILL.md

SKILL.md

Review

Evals

Discovery

32%

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 communicates the core purpose of pattern extraction and skill creation but lacks explicit trigger guidance for when Claude should select this skill. It uses appropriate third-person voice and avoids vague fluff, but would benefit from natural trigger terms and a clear 'Use when...' clause to help Claude distinguish when to apply this skill.

Suggestions

Add a 'Use when...' clause with explicit triggers like 'when the user asks to save a workflow', 'learn from this session', or 'create a skill from what we just did'

Include natural trigger terms users might say: 'remember this', 'save as template', 'learn this pattern', 'extract skill'

Specify what types of patterns are extracted (e.g., 'command sequences, code transformations, multi-step workflows') to improve specificity

Dimension	Reasoning	Score
Specificity	Names the domain (Claude Code sessions, learned skills) and describes the core action (extract reusable patterns, save as skills), but lacks comprehensive detail about what specific patterns are extracted or what 'learned skills' entails.	2 / 3
Completeness	Describes what the skill does but completely lacks a 'Use when...' clause or any explicit trigger guidance. Per rubric guidelines, missing explicit trigger guidance caps completeness at 2, and this has no 'when' component at all.	1 / 3
Trigger Term Quality	Includes some relevant terms like 'patterns', 'Claude Code sessions', and 'skills', but misses common variations users might say such as 'learn from session', 'save workflow', 'remember how to', or 'create skill from'.	2 / 3
Distinctiveness Conflict Risk	The concept of extracting patterns from sessions is somewhat specific, but 'reusable patterns' and 'skills' are broad terms that could overlap with other automation, templating, or learning-related skills.	2 / 3
	Total	7 / 12 Passed

Implementation

50%

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

This skill provides a reasonable overview of a continuous learning system with good configuration examples and hook setup instructions. However, it lacks the actual implementation code for the core functionality (evaluate-session.sh), includes tangential research notes that should be in a separate file, and misses validation steps for the extraction workflow.

Suggestions

Provide the actual evaluate-session.sh script or at minimum show the core pattern detection logic that Claude should execute

Move the 'Comparison Notes' and 'Potential v2 Enhancements' sections to a separate RESEARCH.md or ROADMAP.md file

Add validation steps: how to verify extracted skills are valid, what to do when pattern detection produces low-quality results

Include an example of what a learned skill output looks like (the expected format saved to ~/.claude/skills/learned/)

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but includes some unnecessary content like the comparison notes section which adds bulk without directly helping Claude execute the skill. The Chinese text is appropriate if targeting Chinese users, but the research notes and 'potential v2 enhancements' are tangential.	2 / 3
Actionability	Provides concrete JSON configuration examples and hook setup, but the core functionality (evaluate-session.sh) is referenced without showing its implementation. The skill describes what happens but doesn't provide the actual extraction logic or executable code for pattern detection.	2 / 3
Workflow Clarity	The 3-step workflow (evaluate → detect → extract) is listed but lacks validation checkpoints. No guidance on what to do if pattern detection fails, how to verify extracted skills are valid, or how to handle edge cases like insufficient session content.	2 / 3
Progressive Disclosure	References external resources (Longform Guide, /learn command, v2 spec file) but the comparison notes section is inline when it could be in a separate file. The structure is reasonable but the research/comparison content bloats the main skill file.	2 / 3
	Total	8 / 12 Passed

Validation

100%

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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Reviewed: 5 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.