CtrlK
BlogDocsLog inGet started
Tessl Logo

code-explorer

Use this skill when exploring, analyzing, or understanding project/code structure. Required for tasks like "analyze project", "explore codebase", "understand how X works".

65

Quality

78%

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

Fix and improve this skill with Tessl

tessl review fix ./lib/clacky/default_skills/code-explorer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 compact, well-structured read-only exploration skill with a clear ordered workflow and concrete tool guidance. The main gaps are minor redundancy between the Restrictions section and the read-only restatement, and the absence of full example command invocations.

Suggestions

Merge the redundant read-only statements in 'Your Restrictions' into a single line to tighten conciseness toward level 5.

Add one concrete example invocation for `grep` (e.g. a pattern/flag example) to push actionability toward fully copy-paste-ready guidance.

DimensionReasoningScore

Conciseness

The body is lean and tool-focused, but has minor redundancy such as 'NO modifications: You CANNOT use write or edit tools' restated by 'Read-only: Your role is to ANALYZE, not to change', placing it at the efficient-with-trimmable-bits level 4 rather than the every-token-earns-its-place level 5.

4 / 5

Actionability

It names specific tools and gives a concrete command form ('run `glob` with `**/*`', 'use `grep`', 'use `file_reader`'), which is mostly executable guidance, but lacks full example invocations for grep/file_reader so it does not reach the copy-paste-ready level 5.

4 / 5

Workflow Clarity

The workflow is a strictly ordered 5-step sequence ('follow this order strictly') with clear progression, but it has no validation/feedback checkpoints; since the skill is read-only and non-destructive these are not strictly required, so it sits at the clear-sequence-minor-gaps level 4 rather than level 3.

4 / 5

Progressive Disclosure

The skill is under 50 lines, requires no external references, and is organized into clearly labeled sections (Mission, Restrictions, Workflow, Rules), matching the guideline that such skills can score 5 with well-organized sections alone.

5 / 5

Total

17

/

20

Passed

Description

78%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 well-constructed description that clearly answers both what the skill does and when to use it, with natural trigger phrases. Its main weakness is that the named actions ('exploring, analyzing, understanding') are abstract verbs rather than concrete operations.

Suggestions

Replace generic verbs with concrete operations, e.g. 'List files, search code patterns, and trace how modules work' to lift specificity toward level 4-5.

Add a few more natural trigger synonyms such as 'navigate code' or 'read code' to broaden trigger term coverage.

DimensionReasoningScore

Specificity

The description names the domain ('project/code structure') and three actions ('exploring, analyzing, or understanding'), but these are generic abstract verbs rather than concrete distinct operations, matching the 'Names domain and 1-2 concrete actions' anchor and falling below the multi-specific-action level 4 anchor.

3 / 5

Completeness

It explicitly states the 'what' ('exploring, analyzing, or understanding project/code structure') and the 'when' via an explicit 'Use this skill when...' clause plus 'Required for tasks like...' with concrete trigger phrases, matching the level 5 anchor.

5 / 5

Trigger Term Quality

It provides three natural phrases users would actually say ('analyze project', 'explore codebase', 'understand how X works'), giving good keyword coverage, but it lacks a few synonyms (e.g. 'navigate', 'read code') so it does not reach the comprehensive level 5 anchor.

4 / 5

Distinctiveness Conflict Risk

Code exploration is a clear niche with distinct triggers, but it has minor overlap risk with general coding agents that also explore code, so it sits at level 4 rather than the minimal-conflict level 5 anchor.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
clacky-ai/openclacky
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.