second-brain
Personal knowledge base powered by Ensue for capturing and retrieving understanding. Use when user wants to save knowledge, recall what they know, manage their toolbox, or build on past learnings. Triggers on "save this", "remember", "what do I know about", "add to toolbox", "my notes on", "store this concept".
86
73%
Does it follow best practices?
Impact
96%
2.90xAverage score across 6 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/data/1/SKILL.mdQuality
Discovery
82%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 solid description that excels in trigger term coverage and completeness, with explicit 'Use when' and 'Triggers on' clauses that make selection criteria clear. The main weaknesses are moderate vagueness in the specific capabilities (what concrete operations does it perform beyond 'capturing and retrieving'?) and some overlap risk with generic note-taking or memory skills. Adding more concrete action verbs would strengthen it.
Suggestions
Replace vague capability phrases like 'capturing and retrieving understanding' with specific concrete actions such as 'create tagged knowledge entries, search notes by topic, organize concepts into categories, link related ideas'.
Add distinguishing details about what makes this different from generic note-taking—e.g., mention Ensue-specific features, structured knowledge formats, or unique retrieval capabilities to reduce conflict risk with similar skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('personal knowledge base') and some actions ('capturing and retrieving understanding'), but the specific concrete actions are limited. 'Save knowledge', 'recall', 'manage toolbox', and 'build on past learnings' are somewhat vague and don't describe precise operations like 'create tagged notes', 'search by topic', or 'export entries'. | 2 / 3 |
Completeness | Clearly answers both 'what' (personal knowledge base for capturing and retrieving understanding) and 'when' (explicit 'Use when' clause with specific trigger scenarios and a 'Triggers on' list). Both components are present and explicit. | 3 / 3 |
Trigger Term Quality | Includes a strong set of natural trigger phrases users would actually say: 'save this', 'remember', 'what do I know about', 'add to toolbox', 'my notes on', 'store this concept'. These are realistic, varied, and cover multiple ways a user might invoke this skill. | 3 / 3 |
Distinctiveness Conflict Risk | The knowledge base / note-taking domain is reasonably specific, but terms like 'save this', 'remember', and 'my notes on' could overlap with general note-taking, bookmark, or memory/context skills. The 'Ensue' branding and 'toolbox' terminology add some distinctiveness, but the core concept could still conflict with similar personal knowledge or note management skills. | 2 / 3 |
Total | 10 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable skill with concrete API commands and clear structure for a personal knowledge base system. Its main weaknesses are moderate verbosity (the four content format templates take significant space and could be externalized) and missing validation/error-handling steps in the workflows. The intent mapping table and namespace structure are strong organizational elements.
Suggestions
Move the detailed content format templates (Concepts, Toolbox, Patterns, References) to a separate FORMATS.md file and reference it from the main skill, reducing the main file's token footprint.
Add explicit validation steps to the save workflow: check for duplicates via discover_memories before creating, and verify the entry was saved correctly after create_memory.
Add error handling guidance for API operations (e.g., what to do if the API call fails, how to retry, how to handle rate limits).
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but includes some unnecessary verbosity. The philosophy section and content format templates are somewhat lengthy - Claude doesn't need extensive template scaffolding for concepts/toolbox/patterns/references when briefer examples would suffice. The anti-patterns section restates things already implied by the interaction rules. | 2 / 3 |
Actionability | Provides fully executable bash commands for all API operations with concrete JSON arguments. The namespace structure, content formats, intent mapping table, and setup instructions are all specific and copy-paste ready. Claude knows exactly what commands to run and what format to use. | 3 / 3 |
Workflow Clarity | The saving workflow has a clear 4-step sequence (confirm, draft, save, confirm), and the intent mapping table provides clear action mappings. However, there are no validation checkpoints or error recovery steps for API operations - what happens if create_memory fails? What if a duplicate exists? The 'check if it exists first' anti-pattern is mentioned but not integrated into the workflow with explicit steps. | 2 / 3 |
Progressive Disclosure | The content is well-organized with clear sections and headers, but it's quite long (~180 lines) and could benefit from splitting detailed content format templates and API reference into separate files. Everything is inline in a single document when the format templates and API operations could be referenced externally. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%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 |
metadata_field | 'metadata' should map string keys to string values | Warning |
Total | 9 / 11 Passed | |
- Repository
- majiayu000/claude-skill-registry
- Commit
632759f
- 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.