CtrlK
BlogDocsLog inGet started
Tessl Logo

gitnexus-exploring

Use when the user asks how code works, wants to understand architecture, trace execution flows, or explore unfamiliar parts of the codebase. Examples: "How does X work?", "What calls this function?", "Show me the auth flow"

80

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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: concrete resource URIs and tool calls, a sequenced workflow with a validation checkpoint and error-recovery branch, a checklist, and a worked example. The only minor slack is overlap among the Workflow, Checklist, and Example sections.

DimensionReasoningScore

Conciseness

Lean code blocks with arrow-style outputs and token-cost annotations ("~150 tokens") with no concept-explaining fluff, matching the score-3 lean/efficient anchor; mild Workflow/Checklist/Example overlap prevents it from being tighter but each section serves a purpose.

3 / 3

Actionability

Provides concrete resource URIs, executable tool calls (query/context with argument examples), a runnable remediation command, and a fully worked example with real symbol names — copy-paste ready guidance matching the score-3 anchor.

3 / 3

Workflow Clarity

A clear 5-step numbered sequence with per-step outputs, an explicit staleness validation check, an error-recovery branch, and a checklist; operations are read-only so the destructive/batch feedback-loop cap does not apply.

3 / 3

Progressive Disclosure

Self-contained, well-organized into clearly signaled sections with no nested or dead references; as a single-purpose skill with no bundle files, the well-organized structure satisfies progressive disclosure without external references per the rubric scoring notes.

3 / 3

Total

12

/

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, trigger-rich description that names concrete capabilities and gives natural-language example phrasings a user would say. The only minor weakness is the absence of a leading declarative capability sentence before the "Use when" clause.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — "understand architecture", "trace execution flows", "explore unfamiliar parts of the codebase" — matching the score-3 anchor for specific concrete actions rather than the partial coverage at score 2.

3 / 3

Completeness

Answers both what (understand/trace/explore code) and when via an explicit "Use when…" clause with concrete triggers; the trigger clause is present so it is not capped at 2, though it lacks a leading declarative capability sentence.

3 / 3

Trigger Term Quality

Includes natural user phrasings as examples ("How does X work?", "What calls this function?", "Show me the auth flow") giving good coverage of terms a user would actually say, beyond the partial keyword coverage at score 2.

3 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (codebase exploration / execution-flow tracing) with distinct triggers unlikely to fire for unrelated skills, matching the score-3 anchor.

3 / 3

Total

12

/

12

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
mindfold-ai/Trellis
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.