CtrlK
BlogDocsLog inGet started
Tessl Logo

hivemind-graph

Query the local code graph (functions, classes, calls, imports) through the Deeplake mount at memory/graph/. Use when the user asks structural questions about the codebase — "what calls X?", "what does Y import?", "where is Z defined?", "what is the architecture / which subsystems exist?". The graph is an AST-derived map of the repo, queried as files (no build needed — it rebuilds automatically).

76

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

The canonical home for this skill is hivemind-graph in activeloopai/hivemind

SKILL.md
Quality
Evals
Security

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.

A tight, highly actionable skill body: executable commands, a clear decision-tree workflow with a source-verification checkpoint, and well-organized sections with no padding. The only minor gap is that validation lives partly in a separate anti-patterns section rather than inline as explicit checkpoints.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence: it explains only this tool's specifics (never what an AST or function is), and the Path cheat sheet is a maximally efficient command-plus-comment block where every token earns its place.

5 / 5

Actionability

Fully executable, copy-paste-ready `cat` commands with clear placeholders (`<pattern>`, `<handle>`, `<from>/<to>`) and inline comments on output cover every common query case (index, query, find, show, neighborhood, impact, path, layers, tour).

5 / 5

Workflow Clarity

A clear five-step decision-tree sequence with a verify-in-source checkpoint (step 5) and anti-pattern feedback loops, but validation is a single distributed step plus a separate section rather than the inline validate→fix→retry structure of the top anchor.

4 / 5

Progressive Disclosure

A well-organized single file with clear sections (When to use / When NOT to use / Path cheat sheet / Workflow / Anti-patterns), no nested references, and no content that needs splitting out — navigation is easy and nothing is buried.

5 / 5

Total

19

/

20

Passed

Description

95%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.

A strong description that pairs a concrete statement of capability with explicit, natural trigger phrases. The only minor gap is that the action vocabulary is essentially a single verb (query) applied to several objects rather than a spread of distinct actions.

DimensionReasoningScore

Specificity

"Query the local code graph (functions, classes, calls, imports)" names the domain plus several concrete queryable objects, but the action collapses to a single verb (query) rather than multiple distinct actions, leaving minor coverage gaps.

4 / 5

Completeness

It explicitly answers both what ("Query the local code graph... an AST-derived map of the repo, queried as files") and when ("Use when the user asks structural questions about the codebase") with concrete trigger phrases.

5 / 5

Trigger Term Quality

Verbatim quoted user utterances — "what calls X?", "what does Y import?", "where is Z defined?", "what is the architecture / which subsystems exist?" — are exactly the natural phrases a user would say when they need this skill, covering the main structural-question variations.

5 / 5

Distinctiveness Conflict Risk

A clear niche — structural/relational code-graph queries through the Deeplake mount — with triggers (calls/imports/definitions/architecture) distinct from generic search or file-reading skills, giving minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
activeloopai/hivemind
Reviewed

Table of Contents

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.