ccb-config

Private built-in CCB configuration skill for agentroles.ccb_self. Design, edit, validate, and prepare reloads for .ccb/ccb.config, role bindings, providers, windows, workspaces, tool windows, sidebar, and provider startup inputs. Use only inside ccb_self; non-self agents should delegate CCB config changes to ccb_self.

Quality

84%

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

Quality

Content

100%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.

The body is exemplary: concise, fully actionable, with an explicitly sequenced workflow containing validation gates and error-recovery loops, and clean one-level progressive disclosure to a real reference file.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: scope, forbidden actions, commands, and examples are all crisp with no padding or basic-concept explanation.	5 / 5
Actionability	It provides copy-paste-ready commands (ccb config validate, ccb reload --dry-run, the dated cp backup), concrete TOML binding examples, and a structured handoff block covering common cases.	5 / 5
Workflow Clarity	A 12-step Required Workflow is explicitly sequenced with validation checkpoints (validate, dry-run, gated reload) and a feedback loop (restore on validation failure, stop and ask otherwise) for this destructive/batch operation.	5 / 5
Progressive Disclosure	The SKILL.md is a well-organized overview with one-level-deep, clearly signaled references (references/config-contracts.md, which exists) that offload the detailed contracts rather than inlining them.	5 / 5
	Total	20 / 20 Passed

Description

68%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.

The description is specific, complete, and highly distinct, but relies on internal jargon rather than natural user trigger phrases, which limits discoverability. The usage clause scopes it well but is not a natural 'Use when...' trigger.

Suggestions

Add a natural-language trigger clause (e.g. 'Use when the user asks to change CCB window topology, provider bindings, or reload .ccb/ccb.config') so the skill is discoverable via everyday phrasing.

Reduce reliance on internal identifiers in the lead sentence; pair jargon with plain terms users might actually say.

Move the delegation note into the body and lead the description with the concrete 'what + when' for the intended audience.

Dimension	Reasoning	Score
Specificity	The description enumerates multiple concrete actions ("Design, edit, validate, and prepare reloads") plus a long list of concrete config objects (role bindings, providers, windows, workspaces, tool windows, sidebar, startup inputs), giving comprehensive coverage.	5 / 5
Completeness	It clearly states the 'what' and provides an explicit usage scope ("Use only inside ccb_self; non-self agents should delegate"), though the 'when' is a scoping constraint rather than a natural user-facing trigger.	4 / 5
Trigger Term Quality	Keywords are almost entirely internal/technical jargon ("agentroles.ccb_self", ".ccb/ccb.config", role bindings, providers) with no natural phrases a user would say when requesting this skill.	2 / 5
Distinctiveness Conflict Risk	It defines a sharply private niche scoped to a single role with distinct triggers, making conflict with other skills minimal.	5 / 5
	Total	16 / 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: SeemSeam/claude_codex_bridge
Path: docs/plantree/plans/ccb-self-role/drafts/agentroles.ccb_self/skills/codex/ccb-config/SKILL.md
Commit: 01d5b1c

Reviewed: about 21 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.