understand-knowledge

Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./understand-anything-plugin/skills/understand-knowledge/SKILL.md

Quality

Content

77%

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

The body is a well-sequenced, actionable workflow with strong validation and safety guards. Its main gaps are minor redundancy in the $UA_DIR resolution and referenced bundle scripts that are not actually shipped alongside the SKILL.md.

Suggestions

Define $UA_DIR once (e.g., in a short setup note) and reference it in Phase 5 rather than repeating the full shell snippet verbatim.

Ship the referenced parse-knowledge-base.py and merge-knowledge-graph.py in a scripts/ bundle (or note where they live) so the one-level-deep references resolve to real files.

Consider collapsing Phase 2 ('SCAN (already done)') into a one-line pointer to the scan-manifest contents, since it largely restates Phase 1's script output.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence (no basic-concept padding), but the $UA_DIR resolution snippet is duplicated verbatim in Phase 1 and Phase 5 and Phase 2 restates what the parse script already did — tightening opportunities that keep it below the every-token-earns-its-place anchor at 3.	2 / 3
Actionability	Provides fully executable commands ('python3 "<SKILL_DIR>/parse-knowledge-base.py" "<TARGET_DIR>"', the merge script), a concrete meta.json template, an explicit validation checklist, and a guarded cleanup script — copy-paste ready.	3 / 3
Workflow Clarity	Five clearly sequenced phases with explicit validation (Phase 5 edge/node checks), error feedback loops (Phase 1 script-failure handling, Phase 3 batch-failure continuation), and a guard against 'rm -rf /intermediate', matching the clear-sequence-with-validation anchor.	3 / 3
Progressive Disclosure	References to the bundled scripts and the article-analyzer subagent are well-signaled and one level deep, but the referenced files (parse-knowledge-base.py, merge-knowledge-graph.py) are not present in the bundle, so navigation would break — matching the 'references present but not cleanly resolvable' anchor rather than the fully-realized structure at 3.	2 / 3
	Total	10 / 12 Passed

Description

60%

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 specific and domain-distinctive but omits any explicit 'when to use' trigger, capping both completeness and trigger-term quality. Adding a 'Use when…' clause with natural user phrasing would lift the weakest dimensions.

Suggestions

Append a 'Use when the user asks to analyze or visualize a Karpathy-style LLM wiki, extract entities/relationships, or build a knowledge graph from wiki markdown' clause to provide explicit trigger guidance.

Soften jargon in the trigger phrasing by including natural terms users would actually say (e.g., 'wiki', 'knowledge base', 'knowledge graph', 'entity extraction') alongside 'Karpathy-pattern'.

Distinguish from the sibling dashboard skill by naming the output ('interactive knowledge graph dashboard') versus the dashboard's rendering role.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'entity extraction, implicit relationships, and topic clustering' plus 'generate an interactive knowledge graph' — matching the multi-action anchor rather than the single-domain anchor at 2.	3 / 3
Completeness	Clearly states what the skill does, but there is no 'Use when…' clause or equivalent explicit trigger guidance, which caps completeness at 2 per the judging guidelines.	2 / 3
Trigger Term Quality	Contains some natural terms ('knowledge graph', 'knowledge base') but leans on jargon ('Karpathy-pattern LLM wiki', 'implicit relationships') and omits common user variations, so it falls short of the full-coverage anchor at 3.	2 / 3
Distinctiveness Conflict Risk	The Karpathy-wiki niche is fairly specific, but the absence of explicit triggers and the existence of a sibling /understand-dashboard skill leave overlap risk, matching the 'somewhat specific but could overlap' anchor.	2 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: Egonex-AI/Understand-Anything
Path: understand-anything-plugin/skills/understand-knowledge/SKILL.md
Commit: 6ae7187

Reviewed: 4 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.