continuous-learning
[DEPRECATED - use continuous-learning-v2] Legacy v1 stop-hook skill extractor. v2 is a strict superset with instinct-based, project-scoped, hook-reliable learning. Do not invoke v1; route continuous learning, session learning, and pattern extraction requests to continuous-learning-v2.
51
56%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/continuous-learning/SKILL.mdQuality
Discovery
89%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 is a deprecation redirect description, and it serves that purpose well. It clearly communicates that this skill should not be used and provides explicit routing to the replacement skill (continuous-learning-v2) with good trigger term coverage. The specificity of the actual skill capabilities is somewhat weak since the description focuses on deprecation rather than describing what the skill does, but this is appropriate for a deprecated skill.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names some actions like 'stop-hook skill extractor', 'pattern extraction', and 'session learning', but the description is primarily about deprecation routing rather than describing concrete capabilities. The actual actions of the skill are only vaguely referenced. | 2 / 3 |
Completeness | Clearly answers both 'what' (legacy v1 stop-hook skill extractor, now deprecated) and 'when' (explicitly states 'Do not invoke v1; route continuous learning, session learning, and pattern extraction requests to continuous-learning-v2'). The 'when' guidance is explicit and actionable. | 3 / 3 |
Trigger Term Quality | Includes several natural trigger terms users or Claude might use: 'continuous learning', 'session learning', 'pattern extraction', and the explicit v1/v2 naming. These terms effectively redirect to the correct skill. | 3 / 3 |
Distinctiveness Conflict Risk | Very clearly distinguished as a deprecated v1 skill with explicit routing instructions to v2. The deprecation notice and explicit 'do not invoke' language make it highly unlikely to conflict or be incorrectly selected over the v2 version. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
22%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a deprecated skill that should be minimal but instead contains extensive archival content, research comparisons, and vague workflow descriptions. The deprecation notice at the top is well-written, but the remaining content wastes tokens on a skill that explicitly tells users not to use it. The actionable guidance that does exist (hook setup JSON, config JSON) is undermined by the missing core implementation script and lack of validation steps.
Suggestions
Replace the entire body with a concise 5-10 line deprecation notice that points to continuous-learning-v2, removing all archival documentation that serves no actionable purpose.
If archival content must be retained, move it to a separate ARCHIVE.md or CHANGELOG.md file and reference it with a single link.
Add the actual evaluate-session.sh script content or at minimum describe what it should do with executable code, if this skill is meant to remain functional.
Add validation steps to the workflow: how to verify the hook is installed correctly, how to confirm patterns were extracted, and how to handle extraction failures.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is deprecated yet contains extensive archival documentation, comparison tables, research notes, and explanations that serve no actionable purpose. The entire body could be replaced with a 2-3 line deprecation notice pointing to v2. The comparison notes and pattern type tables are especially wasteful for a deprecated skill. | 1 / 3 |
Actionability | The skill does provide concrete JSON configuration examples and a specific hook setup command, which are copy-paste ready. However, the core script `evaluate-session.sh` is never shown or explained, and the actual pattern extraction logic is entirely absent—Claude wouldn't know how to implement the session evaluation. | 2 / 3 |
Workflow Clarity | The 3-step 'How It Works' section is extremely vague ('Checks if session has enough messages', 'Identifies extractable patterns', 'Saves useful patterns') with no validation checkpoints, no error handling, and no feedback loops. For a hook-based system that writes files, there should be verification steps. | 1 / 3 |
Progressive Disclosure | There are references to external files like `docs/continuous-learning-v2-spec.md` and `config.json`, and the content is organized with clear sections. However, no bundle files are provided, the referenced paths may not exist, and the inline comparison table and research notes bloat what should be a lean deprecation notice with a pointer to v2. | 2 / 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.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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
- Commit
928076c
- 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.