build-graph

Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.

Quality

78%

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/build-graph/SKILL.md

Quality

Content

100%Weight 40%Scale 1-3

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 tight, well-structured instruction-only skill: concrete MCP tool calls with explicit parameters, a clear check-build-verify sequence, and clean sectioning with no padding. It scores at the top of the scale across all four content dimensions.

Dimension	Reasoning	Score
Conciseness	The body is lean with no over-explanation of concepts Claude already knows; each section (Steps, When to Use, Notes) earns its place, matching the 'lean and efficient; every token earns its place' anchor and exceeding the padded level-2 example.	3 / 3
Actionability	It gives concrete, executable guidance — named MCP tools ('list_graph_stats_tool', 'build_or_update_graph_tool') with an explicit parameter ('full_rebuild=True') — fitting 'fully executable... specific examples; copy-paste ready' rather than the vague or pseudocode anchors.	3 / 3
Workflow Clarity	This simple single-purpose skill has a clear three-step sequence (check status -> build -> verify) with an explicit verification step; per the simple-skills note a clear, well-organized single-task workflow scores 3, and graph building is non-destructive so no error-recovery loop is required.	3 / 3
Progressive Disclosure	The skill is under 50 lines with no bundle files and no need for external references, yet is well-organized into clear sections (Steps, When to Use, Notes), which per the guideline earns a 3 on progressive disclosure for such skills.	3 / 3
	Total	12 / 12 Passed

Description

57%Weight 40%Scale 1-3

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 states what the skill does and carves out a distinct niche, but its trigger guidance is thin and operational rather than an explicit 'Use when...' clause, and its action list is not comprehensive. It sits solidly at level 2 on most dimensions with one level-3 strength.

Suggestions

Add an explicit trigger clause, e.g. 'Use when setting up code review for a repository, after major refactors/branch switches, or when the graph seems stale.'

Broaden natural trigger terms to include phrasings users actually say (e.g. 'code review graph', 'index the repo for review', 'refresh the graph').

Expand the action list beyond 'Build or update' to surface concrete capabilities (e.g. parse files, extract nodes/edges, detect languages).

Dimension	Reasoning	Score
Specificity	It names the domain ('code review knowledge graph') and two actions ('Build or update') but stops short of listing multiple specific concrete actions, matching the 'names domain and some actions, but not comprehensive' anchor rather than the comprehensive level-3 example.	2 / 3
Completeness	The 'what' is clear ('Build or update the code review knowledge graph') but the 'when' is only thin operational guidance ('Run this first to initialize') rather than an explicit 'Use when...' trigger clause, so completeness is capped at 2 per the judging guideline.	2 / 3
Trigger Term Quality	It includes relevant terms a user might say ('knowledge graph', 'code review', 'initialize') but leans technical ('hooks keep it updated automatically') and lacks common variations, fitting 'some relevant keywords but missing common variations' rather than full coverage.	2 / 3
Distinctiveness Conflict Risk	The 'code review knowledge graph' niche is specific and unlikely to trigger for unrelated skills, matching the 'clear niche with distinct triggers; unlikely to conflict' anchor; it is well above the somewhat-generic level-2 example.	3 / 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: tirth8205/code-review-graph
Path: skills/build-graph/SKILL.md
Commit: 805c4c6

Reviewed: 9 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.