CtrlK
BlogDocsLog inGet started
Tessl Logo

codebase-exploration

Explore and understand codebases using SocratiCode semantic search, dependency graphs, and context artifacts. Use when exploring code, understanding architecture, finding functions/types, analysing dependencies, searching database schemas or API specs, or when socraticode/codebase_search tools are available. Activates when the user asks about code structure, wants to find where a feature lives, or needs to understand how code is organised.

68

Quality

83%

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

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 well-structured, action-oriented skill body that defers detail to a single real reference file and avoids concept padding. The main opportunities are trimming mild repetition, adding a concrete invocation example, and making validation checks explicit rather than implied.

Suggestions

Consolidate the 'search before reading' guidance so it is stated once rather than repeated across steps 1 and 3, and prune goal→tool table rows that restate the workflow text.

Add at least one concrete codebase_search invocation snippet (with example arguments) so the guidance is copy-paste ready, lifting actionability toward a 5.

Make validation explicit in the workflow (e.g., 'Run codebase_graph_status before relying on graph results; if not ready, wait or trigger a build') rather than leaving it as an implicit checkpoint.

DimensionReasoningScore

Conciseness

Lean and tactical with no over-explanation of concepts Claude already knows, but the 'search before reading' principle is restated across steps 1 and 3 and the goal→tool table partly duplicates the workflow prose, keeping it just below a 5.

4 / 5

Actionability

Concrete tool names, parameters (fileFilter, languageFilter, minScore default 0.10, mode interactive), and an explicit grep-vs-search decision rule give mostly executable guidance, though the absence of literal invocation examples/snippets keeps it from a 5.

4 / 5

Workflow Clarity

A clear 6-step numbered sequence with a status-check fallback and an indexing-recovery hint; validation is implicit (graph_status/codebase_status checks) rather than explicit gating, which is the minor gap versus a 5.

4 / 5

Progressive Disclosure

A well-organized ~70-line overview with a single clearly-signaled one-level-deep reference to references/tool-reference.md (verified to exist) for full parameter details — a textbook clean split for a skill of this size.

5 / 5

Total

17

/

20

Passed

Description

88%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, concrete description that explicitly covers capabilities and triggers with natural user phrasing. It is held back only by slightly less-than-exhaustive trigger synonym coverage and a moderately broad niche with minor overlap risk.

DimensionReasoningScore

Specificity

Lists multiple concrete capabilities — semantic search, dependency graphs, context artifacts, finding functions/types, analysing dependencies, and searching database schemas/API specs — giving comprehensive coverage rather than the minor gaps of a 4.

5 / 5

Completeness

Explicitly answers both 'what' (the capabilities) and 'when' via two concrete trigger clauses ('Use when…' and 'Activates when…'), matching the anchor for clearly answering both.

5 / 5

Trigger Term Quality

Strong natural phrases ('exploring code', 'understanding architecture', 'find where a feature lives', 'understand how code is organised') plus a tool-name trigger, but coverage is slightly less exhaustive than the synonym-and-extension completeness of a 5.

4 / 5

Distinctiveness Conflict Risk

The SocratiCode niche and tool-name trigger keep it mostly distinct with minimal conflict risk, but 'codebase exploration' is a broad enough niche to risk minor overlap with general code-reading skills, keeping it just below a 5.

4 / 5

Total

18

/

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
giancarloerra/SocratiCode
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.