ccc

This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code'.

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

The canonical home for this skill is ccc in cocoindex-io/cocoindex-code

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.

An excellent, concise SKILL.md body: executable commands, a clear init recovery loop, and clean progressive disclosure to two verified reference files. The only gap is minor validation checkpoints in the search/index workflow.

Suggestions

Add a brief validation step after `ccc index` (e.g., run `ccc status` or confirm 'indexing complete') before retrying a search, to close the workflow-clarity gap toward 5.

Optionally note a quick daemon-health check (`ccc daemon status`) as a fallback when searches fail unexpectedly, strengthening the error-recovery feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, with executable commands and operational guidance rather than concept explanations or library tutorials; every section earns its tokens.	5 / 5
Actionability	Provides copy-paste-ready commands for the common cases (search, language/path filters, pagination, init error recovery) plus a concrete sed fallback for terminal-only contexts.	5 / 5
Workflow Clarity	The init flow has a clear error-recovery feedback loop (failure -> init -> index -> retry) and pagination is well sequenced, but there are minor validation gaps such as confirming the index built successfully or daemon health before searching.	4 / 5
Progressive Disclosure	The body is a clear overview that defers bulk detail to two real, well-signaled, one-level-deep reference files (management.md, settings.md), both verified to exist, with content appropriately split.	5 / 5
	Total	19 / 20 Passed

Description

82%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, well-structured description that clearly states purpose, when to trigger, and concrete trigger phrases tied to a distinct tool. The main weakness is specificity, where the listed actions are slightly abstract and not fully enumerated.

Suggestions

Consider listing the concrete capabilities more explicitly (e.g., 'semantic search, index building, freshness updates, and status/diagnostics') to lift specificity from a 3 to a 4-5.

Add a couple more natural trigger variations users might say, such as 'look up code', 'where is X defined', or 'search for usages of', to round out trigger-term coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and concrete actions ('code search', 'indexing the codebase after changes', answering about the index), but the action list is short and somewhat abstract rather than a comprehensive enumeration.	3 / 5
Completeness	Explicitly answers both 'what' (semantic code search and indexing) and 'when' via 'should be used when...' plus a concrete 'Trigger phrases include' list.	5 / 5
Trigger Term Quality	Explicit trigger phrases ('search the codebase', 'find code related to', 'update the index', 'ccc', 'cocoindex-code') provide good natural keyword coverage including product synonyms, though a few common phrasings like 'look up code' are absent.	4 / 5
Distinctiveness Conflict Risk	Tied to a specific named tool (ccc / cocoindex-code) and a clear niche (semantic search over the current codebase), giving distinct triggers with minimal overlap risk.	5 / 5
	Total	17 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: Jamie-BitFlight/claude_skills
Path: .agents/skills/ccc/SKILL.md
Commit: 4e1e73b

Reviewed: ~13 hours ago

Table of Contents

Discovery Implementation Validation

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.