understand-knowledge
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.
61
72%
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 ./understand-anything-plugin/skills/understand-knowledge/SKILL.mdQuality
Discovery
67%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 is strong on specificity and distinctiveness, clearly naming concrete actions and occupying a unique niche. However, it lacks an explicit 'Use when...' clause which limits its completeness score, and the trigger term 'Karpathy-pattern' is specialized jargon that may not match how users naturally phrase requests.
Suggestions
Add a 'Use when...' clause, e.g., 'Use when the user wants to visualize relationships in a wiki knowledge base, generate a knowledge graph, or analyze interconnections between wiki entries.'
Include more natural trigger terms users might say, such as 'visualize wiki', 'graph visualization', 'map relationships', 'wiki analysis', or 'connected notes'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'analyze a wiki knowledge base', 'generate an interactive knowledge graph', 'entity extraction', 'implicit relationships', and 'topic clustering'. | 3 / 3 |
Completeness | Clearly answers 'what does this do' (analyze wiki, generate knowledge graph with entity extraction, relationships, clustering), but lacks an explicit 'Use when...' clause or trigger guidance for when Claude should select this skill. | 2 / 3 |
Trigger Term Quality | Includes some relevant keywords like 'knowledge graph', 'entity extraction', 'topic clustering', and 'wiki knowledge base', but the term 'Karpathy-pattern' is niche jargon that most users wouldn't naturally say. Missing common variations like 'visualize', 'graph visualization', 'wiki analysis', or 'LLM notes'. | 2 / 3 |
Distinctiveness Conflict Risk | The combination of 'Karpathy-pattern LLM wiki knowledge base' and 'interactive knowledge graph' is highly specific and unlikely to conflict with other skills. This occupies a very clear niche. | 3 / 3 |
Total | 10 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, highly actionable skill with a clear five-phase workflow that includes validation, error handling, and graceful degradation. Its main weakness is moderate verbosity in the detection description section and the lack of verifiable bundle files for the referenced scripts and subagent. The workflow clarity is strong with explicit checkpoints and error recovery paths.
Suggestions
Trim the 'What It Detects' section — the detection logic is already encoded in the parse script, so a one-line description of the pattern plus the external link would suffice.
Ensure bundle files (parse-knowledge-base.py, merge-knowledge-graph.py, article-analyzer agent definition) are provided alongside the SKILL.md to support the referenced paths.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is mostly efficient and avoids explaining basic concepts, but includes some unnecessary detail like the full description of the Karpathy pattern detection signals and the Notes section that partially repeats information already conveyed in the workflow. The 'What It Detects' section is somewhat redundant given the instructions already describe the detection process. | 2 / 3 |
Actionability | The skill provides concrete, executable commands (python3 scripts, rm -rf cleanup), specific file paths, exact JSON output formats, and clear parameters for subagent dispatch. Each phase has precise, actionable steps with specific tool invocations and expected outputs. | 3 / 3 |
Workflow Clarity | The five-phase workflow is clearly sequenced with explicit validation (Phase 5 step 2 validates edges and nodes), error handling (Phase 1 step 2 handles detection failure, Phase 3 step 5 handles batch failures gracefully), and a clear feedback path. The concurrency model (3 batches) and batch sizing (10-15 articles) are specified. The cleanup and reporting steps provide closure. | 3 / 3 |
Progressive Disclosure | The content references bundled scripts (parse-knowledge-base.py, merge-knowledge-graph.py) and a subagent (article-analyzer) but no bundle files were provided to verify these exist. The skill is somewhat monolithic — the 'What It Detects' section and the detailed subagent dispatch instructions could potentially be split into referenced files. However, the phased structure provides reasonable internal organization. | 2 / 3 |
Total | 10 / 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
- Lum1104/Understand-Anything
- Commit
26edf61
- 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.