understand

Analyze a codebase to produce an interactive knowledge graph for understanding architecture, components, and relationships

Quality

71%

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/SKILL.md

Quality

Content

81%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 an exceptionally actionable, well-sequenced multi-phase workflow with strong validation and error-recovery structure. Its main weakness is conciseness: sizable inline scripts and verbose rationale could be externalized to bundled files.

Suggestions

Move the inline Phase 6 validation Node script and the Phase 7 fingerprint-input generator into `scripts/*.cjs` files in the bundle and reference them by path, cutting substantial inline tokens.

Consider extracting the trailing "Reference: KnowledgeGraph Schema" node/edge/weight tables into a `references/schema.md` file linked from the body.

Trim verbose rationale parentheticals (e.g. issue-number callouts) to one-line comments where the operational instruction alone is enough for Claude to act.

Dimension	Reasoning	Score
Conciseness	The 858-line body is mostly necessary operational detail, but it inlines a ~65-line Node validation script and a fingerprint-input generator that belong in bundled script files, and carries several verbose rationale paragraphs (issue references) that could be trimmed; externalizing the inline scripts would materially cut tokens without losing guidance.	3 / 5
Actionability	Guidance is fully executable throughout: exact bash commands, precise script paths (e.g. `node "<SKILL_DIR>/compute-batches.mjs"`), complete copy-paste inline scripts, JSON schemas, and decision tables cover the common cases with no pseudocode or abstract hints.	5 / 5
Workflow Clarity	Phases 0-7 are explicitly sequenced with validation checkpoints (Phase 6 inline validation, Phase 7 fingerprint gate "must succeed before meta.json is written"), feedback loops (fix then re-validate), gate checks, and retry-once error recovery.	5 / 5
Progressive Disclosure	Clear one-level-deep references to `agents/.md`, `languages/.md`, `frameworks/.md`, `locales/.md`, and bundled scripts are well signaled, but the inline validation script and the trailing KnowledgeGraph schema tables are content that would be better placed in separate reference files, and the reviewed bundle ships no bundled files alongside SKILL.md.	4 / 5
	Total	17 / 20 Passed

Description

61%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 clearly conveys what the skill produces (an interactive architecture knowledge graph) but omits any explicit "when to use it" trigger guidance, which is its main weakness. Trigger-term and distinctiveness are solid though not maximal.

Suggestions

Add a "Use when..." clause naming concrete triggers, e.g. "Use when the user wants to understand, explore, or map a codebase's architecture, components, and relationships, or mentions a knowledge graph."

List 1-2 more concrete actions or synonyms (e.g. "explore", "navigate", "map code structure") to lift specificity and trigger-term coverage toward comprehensive.

Tighten distinctiveness by contrasting with adjacent skills, e.g. note it builds an interactive architecture graph rather than reviewing or refactoring code.

Dimension	Reasoning	Score
Specificity	Names the domain and one concrete action ("Analyze a codebase to produce an interactive knowledge graph"), but it is a single deliverable rather than a list of multiple specific actions, so it is not comprehensive enough for a 4.	3 / 5
Completeness	It has a clear "what" (produce a knowledge graph) but no "Use when..." clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Natural terms users say ("codebase", "architecture", "components", "relationships") are present, but common synonyms like "explore", "navigate", "code map", or "code structure" are missing, so it falls short of comprehensive 5-level coverage.	4 / 5
Distinctiveness Conflict Risk	The architecture knowledge-graph niche is mostly distinct with minimal conflict risk, though "Analyze a codebase" is broad enough to overlap slightly with general code-analysis or code-review skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (859 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: Egonex-AI/Understand-Anything
Path: understand-anything-plugin/skills/understand/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.