explore-codebase

Navigate and understand codebase structure using the knowledge graph

Quality

73%

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 ./skills/explore-codebase/SKILL.md

Quality

Content

93%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 content is a tight, highly actionable exploration workflow built around concrete MCP tool names and query patterns, with token efficiency baked in as a first-class concern. The only minor gap is the absence of explicit validation checkpoints, which is acceptable for read-only exploration but keeps workflow clarity at 4.

Dimension	Reasoning	Score
Conciseness	The body is lean throughout — numbered tool calls, terse tips, and explicit 'Token Efficiency Rules' with 'detail_level=minimal' and token targets — with no over-explanation of concepts Claude already knows, matching 'Lean and efficient; assumes Claude's competence; every token earns its place'. Not below 5 because no padding or redundant explanation is present.	5 / 5
Actionability	Concrete executable MCP tool names ('list_graph_stats_tool', 'semantic_search_nodes_tool', 'query_graph_tool') plus specific query patterns ('callers_of', 'callees_of', 'imports_of', 'children_of') cover the common cases, matching 'Fully executable; copy-paste ready code or commands; specific examples cover the common cases'. Not below 5 because guidance is concrete and directly runnable rather than pseudocode.	5 / 5
Workflow Clarity	A clearly sequenced 1–6 exploration process with concrete tools is present, matching 'Clear sequence with most checkpoints present; minor validation gaps'. Not a 5 because there are no explicit validation/feedback checkpoints (e.g. verify the graph covers the area before drilling in); not capped at 3 because the operations are read-only exploration, not destructive or batch, so the missing-validation cap does not apply.	4 / 5
Progressive Disclosure	At 29 lines with no need for external references and well-organized sections ('Explore Codebase', 'Steps', 'Tips', 'Token Efficiency Rules'), this meets the under-50-line simple-skill exception allowing a 5 for clear organization. Not below 5 because structure is clean and no nested or buried references exist.	5 / 5
	Total	19 / 20 Passed

Description

53%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 states a clear purpose but omits any explicit 'Use when...' trigger guidance, capping completeness and leaving trigger-term coverage thin. It is reasonably distinct thanks to the knowledge-graph qualifier. Adding concrete trigger phrases and natural synonyms would materially raise the score.

Suggestions

Add a 'Use when...' clause with concrete triggers, e.g. 'Use when exploring an unfamiliar codebase, tracing call/import relationships, or locating specific functions and classes.'

Include natural user phrasings and synonyms beyond 'codebase structure' — e.g. 'explore', 'browse', 'map', or 'trace the codebase'.

Replace the generic verbs 'Navigate and understand' with several concrete actions (e.g. 'Explore, trace, and map codebase structure via the knowledge graph').

Dimension	Reasoning	Score
Specificity	Quotes 'Navigate and understand codebase structure using the knowledge graph' — it names the domain (codebase structure / knowledge graph) and two actions, matching the anchor 'Names domain and 1-2 concrete actions, but not comprehensive'. Not a 4 because 'navigate' and 'understand' are generic verbs rather than several specific concrete actions; not a 2 because two distinct actions and a named tool substrate are present.	3 / 5
Completeness	A clear 'what' is present but there is no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3 — matching 'Has a clear what but when is missing or only weakly implied'. Not a 4 because 'when' is entirely absent rather than merely implicit; not a 2 because the 'what' is clear rather than vague.	3 / 5
Trigger Term Quality	Keywords 'codebase structure' and 'knowledge graph' are relevant and somewhat natural, but common user phrasings like 'explore', 'browse', or 'map the codebase' and file/extension terms are missing, matching 'Some relevant keywords but missing common variations or synonyms'. Not a 4 because natural-term coverage is thin; not a 2 because more than one generic keyword is present.	3 / 5
Distinctiveness Conflict Risk	'using the knowledge graph' binds the skill to a specific MCP tooling niche, giving 'Mostly distinct; minor overlap risk with closely related skills'. Not a 5 because it could still overlap with general code-exploration skills; not a 3 because the knowledge-graph qualifier is more specific than a broad 'works with code' framing.	4 / 5
	Total	13 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: tirth8205/code-review-graph
Path: skills/explore-codebase/SKILL.md
Commit: b586687

Reviewed: 3 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.