CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-navigation

Use this skill when exploring an unfamiliar codebase, tracing code paths, or answering questions about how the system works. Read before writing, and build a mental model of the architecture before making changes.

64

Quality

76%

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 ./memory_data/skills/codebase-navigation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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 concise, well-organized, and clearly sequenced for a simple read-only navigation skill. Its main weakness is actionability: it offers strategy and pointers rather than executable commands or worked examples.

Suggestions

Add one or two concrete executable examples, e.g. a sample glob/grep invocation for finding an entry point or tracing a function definition.

Show a tiny worked trace (entry point -> import -> data model -> test) to make the sequence immediately actionable.

DimensionReasoningScore

Conciseness

The body is lean and pithy ('Find the data model first — it shapes everything else'; 'Read tests: they document expected behavior better than comments') and assumes Claude's competence without padding or explaining basic concepts.

3 / 3

Actionability

It names concrete entry-point files (`main.py`, `__init__.py`, `index.ts`, `App.tsx`) and tools (glob, grep), but the guidance stays at strategy level with no executable commands or copy-paste examples.

2 / 3

Workflow Clarity

The numbered 'Exploration strategy' (1–5) gives a clear, well-sequenced process for a read-only task; the simple-skill note permits a 3 here since no validation checkpoints apply to non-destructive exploration.

3 / 3

Progressive Disclosure

At under 50 lines with no need for external references, the well-organized sections (Exploration strategy, Efficient search, Anti-patterns) satisfy the rubric's simple-skill allowance for progressive disclosure.

3 / 3

Total

11

/

12

Passed

Description

67%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 is well-structured with an explicit trigger and clear domain, but its capabilities are phrased at a strategy level rather than as concrete actions and its trigger vocabulary is only moderately complete.

Suggestions

Replace abstract verbs with concrete actions, e.g. 'Map entry points, trace imports, locate the data model, and read tests to understand behavior'.

Add natural trigger variations users actually say, such as 'understand the code', 'get oriented in a repo', or 'read before changing'.

Narrow the trigger to reduce overlap, e.g. 'Use before modifying unfamiliar code, not for routine edits in a known codebase.'

DimensionReasoningScore

Specificity

Names the domain and several actions ('exploring an unfamiliar codebase, tracing code paths', 'build a mental model of the architecture'), but these are abstract strategy phrases rather than the multiple concrete actions exemplified by the score-3 anchor.

2 / 3

Completeness

It answers both what the skill does and when to use it via an explicit 'Use this skill when ...' trigger clause, satisfying the rubric's completeness bar.

3 / 3

Trigger Term Quality

It includes some natural phrases a user might say ('exploring an unfamiliar codebase', 'how the system works'), but coverage of common variations (e.g. 'understand the code', 'read the code', 'orient myself') is incomplete.

2 / 3

Distinctiveness Conflict Risk

The navigation/understanding framing is somewhat specific, but the broad 'exploring a codebase' scope could overlap with general coding and code-reading skills.

2 / 3

Total

9

/

12

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
aiming-lab/MetaClaw
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.