ccb-diagnose

Diagnose a named CCB agent by combining authoritative runtime and job lineage with deep read-only pane inspection, apply bounded recovery when evidence supports it, verify the result, and request authorization before submitting a redacted GitHub issue. Use for `$ccb_diagnose agentname`, `$ccb-diagnose agentname`, or reports that a CCB agent is stuck, disconnected, not continuing, not replying, or showing provider errors.

Quality

94%

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

88%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 content is a tightly written, actionable CCB diagnostic runbook with explicit validation checkpoints and safety red lines. Its only real gap is progressive disclosure: everything lives inline with no external reference files, though the internal structure is strong.

Suggestions

Consolidate the repeated 'evidence is not authority' / 'evidence only' reminders into one authoritative section to trim repeated tokens across conciseness.

Consider extracting the pane-state classification taxonomy and the incident-bundle redaction rules into a reference file referenced once, improving progressive_disclosure toward the top anchor.

Tighten the bounded-recovery bullet list by grouping the three 'only when trace proves...' repair conditions into a single guarded table to reduce redundancy.

Dimension	Reasoning	Score
Conciseness	The body is dense and domain-specific with no generic concept explanations, but safety emphases (authority vs evidence, 'evidence only', red-line restatements) recur across sections and could be tightened slightly.	4 / 5
Actionability	Provides copy-paste-ready executable commands throughout — 'command ccb ping ccbd', the tmux capture-pane fallback, 'command ccb repair ack ...', and 'gh issue create ...' — covering the common diagnostic and recovery cases.	5 / 5
Workflow Clarity	A clear six-step sequence (Establish Authority → Deep Pane Diagnosis → Classify → Bounded Recovery → Verify → Incident Bundle) with an explicit verification section, feedback loops after repair, and explicit red lines for destructive actions.	5 / 5
Progressive Disclosure	Well-organized with clear section headers and a cohesive self-contained runbook, but it is monolithic — all content is inline in SKILL.md with no bundle files or external references, so the overview-to-detail split is only internal.	4 / 5
	Total	18 / 20 Passed

Description

100%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 third-person, concrete, and tightly scoped to a CCB agent diagnosis workflow with explicit trigger guidance. It scores at the top of every dimension with no vague fluff or over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'Diagnose a named CCB agent by combining authoritative runtime and job lineage with deep read-only pane inspection, apply bounded recovery when evidence supports it, verify the result, and request authorization before submitting a redacted GitHub issue' — covering diagnose, inspect, recover, verify, and report comprehensively.	5 / 5
Completeness	Explicitly answers both 'what' (diagnose/inspect/recover/verify/request authorization) and 'when' via a 'Use for ...' clause with concrete trigger phrases, matching the top anchor.	5 / 5
Trigger Term Quality	Includes natural user-report phrasings ('stuck, disconnected, not continuing, not replying, or showing provider errors') plus invocation forms ('$ccb_diagnose agentname', '$ccb-diagnose agentname'), giving comprehensive synonym coverage of how users actually describe the problem.	5 / 5
Distinctiveness Conflict Risk	Targets a clear CCB-specific niche with distinct invocation tokens and provider/agent failure triggers, making conflict with unrelated skills minimal.	5 / 5
	Total	20 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: SeemSeam/claude_codex_bridge
Path: inherit_skills/claude_skills/ccb-diagnose/SKILL.md
Commit: 20ac0ec

Reviewed: 2 days 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.