understand-chat

Use when you need to ask questions about a codebase or understand code using a knowledge graph

Quality

72%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

Quality

Content

75%Weight 40%Scale 1-5

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 concrete grep/git commands and explicit freshness-validation checkpoints plus error-recovery guidance. It is efficient and well-structured, falling just short of top marks due to illustrative (not fully copy-paste) grep patterns and a sizable inlined schema block.

Suggestions

Replace the illustrative grep examples in step 4 with exact, copy-paste-ready commands (e.g., a concrete `grep -nE '"name"|"summary"|"tags"' .ua/knowledge-graph.json` form) to push actionability to 5.

Consider moving the full graph-structure schema into a `references/graph-schema.md` with a one-line pointer, leaving only the field names Claude must grep against inline, to improve progressive disclosure.

Tighten the freshness-check prose into a compact checklist so each validation branch reads as an explicit checkpoint rather than a paragraph.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with concrete grep/git commands and no padding about what a knowledge graph or git is; only minor stretches (the freshness prose) could be trimmed. Matches the 4 anchor of efficient with minor trim opportunities; not a 5 because some explanatory sentences in the freshness step could be tighter.	4 / 5
Actionability	Provides concrete, executable bash (the UA_DIR assignment) and a copy-paste git/grep command block with required pathspecs, plus specific field names to search. Mostly executable with minor gaps (grep patterns are illustrative rather than exact one-liners). Matches the 4 anchor; not a 5 because the node-search grep examples are not fully copy-paste-ready exact commands.	4 / 5
Workflow Clarity	A clearly numbered 7-step sequence with an explicit freshness-validation checkpoint, error-recovery guidance (warn / suggest /understand, continue instead of blocking), and feedback loops for the git-diff checks. Matches the 4 anchor with most checkpoints present; not a 5 because the validation branching in step 2 is dense and a couple of checkpoints are implicit rather than crisp checklist items.	4 / 5
Progressive Disclosure	Single self-contained SKILL.md with well-organized sections and no nested external references; the inlined graph-structure schema is appropriate but a sizable block that could optionally live in a reference file. Good structure per the 4 anchor; not a 5 because the structure reference block is inlined bulk that could be split out for navigation.	4 / 5
	Total	16 / 20 Passed

Description

70%Weight 40%Scale 1-5

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 concise, uses proper third-person trigger phrasing, and clearly states both what the skill does and when to use it. It is strong but stops short of enumerating multiple specific capabilities or synonyms, which keeps it at the 4 level rather than 5.

Suggestions

Add 1-2 more concrete capabilities (e.g., 'trace dependencies, map call chains, locate where a concept is implemented') to lift specificity toward 5.

Include natural synonyms or file/directory cues (e.g., 'knowledge graph', 'code map', '.ua/knowledge-graph.json') to broaden trigger-term coverage.

Tighten the 'when' clause to name a specific scenario (e.g., 'when you need to answer code-structure questions without re-reading the whole repo') to sharpen completeness.

Dimension	Reasoning	Score
Specificity	Names the domain ("codebase", "knowledge graph") and 1-2 concrete actions ("ask questions", "understand code"), but does not enumerate a comprehensive set of capabilities, matching the anchor that names the domain with 1-2 concrete actions. Not a 4 because no broader list of specific actions is given; not a 2 because the actions are concrete rather than minimal.	3 / 5
Completeness	Explicitly answers both what ("ask questions about a codebase or understand code using a knowledge graph") and when ("Use when you need to...") with a concrete trigger phrase. Matches the 4 anchor where both are present but the 'when' could be more specific; not a 5 because the 'what' is general rather than enumerating multiple concrete operations.	4 / 5
Trigger Term Quality	Includes natural user phrases ("ask questions about a codebase", "understand code") plus the distinctive "knowledge graph" keyword; a few natural synonyms or variations are missing. Good keyword coverage with minor gaps, matching the 4 anchor; not a 5 because it lacks synonyms or extensions for thorough coverage.	4 / 5
Distinctiveness Conflict Risk	The knowledge-graph-based code-understanding niche is distinct with clear triggers, only a minor overlap risk with general code-Q&A tools. Mostly distinct per the 4 anchor; not a 5 because 'ask questions about a codebase' is broad enough to risk some overlap with generic code skills.	4 / 5
	Total	15 / 20 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-chat/SKILL.md
Commit: ba450c4

Reviewed: ~16 hours 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.