CtrlK
BlogDocsLog inGet started
Tessl Logo

ccb-self-diagnose

Diagnose CCB runtime, mounted daemon graph, tmux namespace and panes, provider context, queue/inbox/trace, replies/artifacts, config drift, and storage boundaries. Use when the user asks what is broken, which agent is stuck, whether CCB is mounted, why a reply did not arrive, or what to check first.

76

Quality

94%

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

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 body is a tightly written, read-only triage procedure with concrete commands, sequenced validation checkpoints, and a clear reporting template. Its only weakness is mild redundancy of the authority-vs-residue caution and a long single-file footprint that could benefit from a reference file.

Suggestions

Consolidate the repeated 'tmux/disk residue is not configured-agent authority' caution into a single statement in the Red Lines or Evidence Model section to remove triplication.

Extract the Failure Domains taxonomy and Named-Agent Pane Deep Dive state list into a references file, keeping SKILL.md as an overview that signals the one-level-deep reference.

DimensionReasoningScore

Conciseness

Mostly lean and free of concepts Claude already knows, but the authority caution ('do not treat tmux/disk residue as configured-agent authority') is restated across the Evidence Model, Named-Agent section, and Red Lines, which could be consolidated.

4 / 5

Actionability

Provides fully executable, flag-specific commands throughout (e.g. 'ccb queue --detail all', 'ccb pend --inbox --detail <agent>', 'ccb trace <job_id|message_id|attempt_id|reply_id>') plus a copy-paste reporting template and named hand-off targets.

5 / 5

Workflow Clarity

Clear six-step core workflow and pane deep dive with explicit validation checkpoints (capture-compare normalized fingerprints to classify frozen vs progress; read full artifact or report blocker; validate then dry-run reload before trusting the graph).

5 / 5

Progressive Disclosure

Well-organized into clearly headed sections (Evidence Model, Core Workflow, Pane Deep Dive, Failure Domains, Reporting, Red Lines) with no nested references and easy navigation, though the skill is fairly long and entirely inline with no bundle files to offload detail.

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 exemplary: third-person voice, comprehensive concrete capabilities, and natural trigger phrases that clearly answer both what and when. It occupies a distinct niche with minimal conflict risk.

DimensionReasoningScore

Specificity

Lists multiple concrete diagnostic targets — 'mounted daemon graph, tmux namespace and panes, provider context, queue/inbox/trace, replies/artifacts, config drift, and storage boundaries' — giving comprehensive coverage rather than vague language.

5 / 5

Completeness

Explicitly answers what ('Diagnose CCB runtime...') and when ('Use when the user asks...') with concrete trigger phrases, matching the anchor for clearly answering both.

5 / 5

Trigger Term Quality

Natural user phrases like 'what is broken', 'which agent is stuck', 'whether CCB is mounted', 'why a reply did not arrive', and 'what to check first' are exactly what a user would say when needing this skill.

5 / 5

Distinctiveness Conflict Risk

The CCB-specific diagnostic niche with distinct triggers ('which agent is stuck', 'whether CCB is mounted') makes it unlikely to fire for unrelated skills.

5 / 5

Total

20

/

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
SeemSeam/claude_codex_bridge
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.