graph

Interactive knowledge graph analysis. Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions. Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis".

Quality

88%

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

Quality

Content

77%

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

A highly actionable, well-sequenced skill with executable inline implementations and thorough edge-case handling. Its main weaknesses are length/verbosity and a monolithic structure that does not progressively disclose operation details into separate reference files.

Suggestions

Move the per-operation output templates and the density benchmark tables into a references file (e.g. graph-output-formats.md), keeping SKILL.md as an overview that links to each operation, to improve progressive disclosure.

Tighten the Philosophy section and trim repeated boilerplate in the presentation blocks to reduce token cost without losing the actionable code.

Confirm whether the referenced ops/scripts/graph/*.sh and ops/derivation-manifest.md are intended as skill bundle files; if so, ship them under scripts/ and references/ so the inline code is a true fallback rather than the only path.

Dimension	Reasoning	Score
Conciseness	The body is comprehensive and mostly operational, but ~550 lines with a Philosophy section and lengthy templated output blocks ('--=={ graph health }==--' etc.) could be tightened; not every token earns its place.	2 / 3
Actionability	Each operation ships executable bash and ripgrep patterns (e.g. the orphan/dangling grep loops, 'rg "^{field}:.*{value}"'), copy-paste ready with specific one-liners.	3 / 3
Workflow Clarity	Every operation is explicitly sequenced (Step 1: Collect → Step 2: Interpret) and edge-case recovery is handled ('Did you mean: ...', 'Note not found ...'); operations are read-only so destructive-validation caps do not apply.	3 / 3
Progressive Disclosure	The skill is a single monolithic file with no bundle files (references/scripts/assets absent); it is well-sectioned but content for nine operations is inline rather than split into one-level-deep reference files.	2 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: third-person voice, concrete multi-action capability statement, and an explicit 'Triggers on' clause with both slash-command and natural-language forms. It clearly answers what the skill does and when to invoke it with low conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain and lists multiple concrete actions — 'Routes natural language questions to graph scripts, interprets results in domain vocabulary, and suggests concrete actions' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what (interactive knowledge graph analysis with routing/interpretation/action-suggesting) and when ('Triggers on ...') with explicit trigger guidance.	3 / 3
Trigger Term Quality	'Triggers on "/graph", "/graph health", "/graph triangles", "find synthesis opportunities", "graph analysis"' covers natural slash-command and phrase forms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	The '/graph' command niche is distinct and the listed triggers are specific enough to be unlikely to fire for unrelated skills.	3 / 3
	Total	12 / 12 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (568 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: agenticnotetaking/arscontexta
Path: skill-sources/graph/SKILL.md
Commit: 2acfd5c

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.