ccb-diagnose

Diagnose a named CCB managed agent using runtime, job-lineage, and provider evidence.

Quality

76%

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

Fix and improve this skill with Tessl

tessl review fix ./inherit_skills/dsh_skills/ccb-diagnose/SKILL.md

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.

The body is a tight, executable runbook that assumes competence and includes a bounded-repair plus re-check feedback loop, satisfying the destructive-operation validation requirement. Only minor: the workflow could be made slightly more explicit with numbered steps.

Dimension	Reasoning	Score
Conciseness	Lean and efficient with no padding: it assumes Claude's competence and never explains what CCB or tmux is; every line earns its place.	5 / 5
Actionability	Provides copy-paste-ready executable commands (ccb ping/ps/queue/pend/trace/doctor logs) with a concrete $AGENT variable covering the common diagnostic cases.	5 / 5
Workflow Clarity	Clear sequence (authority commands -> trace/logs evidence -> bounded repair -> re-check) with an explicit validation checkpoint ("re-check the same runtime and lineage evidence"), though steps are prose rather than a numbered checklist.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with no need for external references; the single H1 and grouped command block are well-organized enough to score 5 per the simple-skill exception.	5 / 5
	Total	19 / 20 Passed

Description

58%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 and occupies a clear niche, but it omits any explicit "Use when..." trigger guidance, which caps its completeness and slightly weakens trigger-term quality. Adding a natural-language trigger clause would lift the two lowest dimensions.

Suggestions

Append a "Use when..." clause naming concrete trigger phrases (e.g., "Use when diagnosing a stuck or misbehaving CCB managed agent, investigating job lineage, or tracing provider/API errors").

Add natural user-facing synonyms alongside the jargon (e.g., "agent stuck", "job history", "API errors") so the trigger terms match what users actually say.

Optionally note when NOT to use it (e.g., general agent debugging outside CCB) to further reduce conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain ("named CCB managed agent") and several concrete diagnostic actions via three named evidence sources ("runtime, job-lineage, and provider evidence"), with only minor coverage gaps.	4 / 5
Completeness	Clearly states what the skill does ("Diagnose a named CCB managed agent...") but provides no "Use when..." clause or equivalent trigger guidance, capping completeness at 3 per the rubric.	3 / 5
Trigger Term Quality	Includes relevant terms ("diagnose", "agent") but leans on domain jargon ("CCB", "job-lineage", "provider evidence") and misses natural synonyms or variations a user might say.	3 / 5
Distinctiveness Conflict Risk	The "CCB managed agent" niche is highly specific and unlikely to collide with unrelated skills, though the absence of explicit trigger phrases leaves minor overlap risk.	4 / 5
	Total	14 / 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/dsh_skills/ccb-diagnose/SKILL.md
Commit: 18bf0af

Reviewed: 7 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.