CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

74

Quality

92%

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

The canonical home for this skill is ccb-diagnose in SeemSeam/claude_codex_bridge

SKILL.md
Quality
Evals
Security

Quality

Content

85%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 structured operational runbook with executable commands, an explicit verification checkpoint, feedback loops, and clear guardrails. It is slightly verbose in places and some recovery steps are conditional rather than literal commands, which keeps actionability and conciseness at 4 rather than 5.

Suggestions

Tighten the interpretation rules and recovery bullets: convert 'use ... only when ...' conditionals into a short decision table or literal guarded command snippets to push actionability to 5.

Trim explanatory clauses in the Deep Pane Diagnosis and Classify sections (e.g. merge redundant 'pane text is evidence, not authority' statements) to improve conciseness.

Consider moving the long state-classification taxonomy into a short reference table to reduce inline density while keeping it one level deep.

DimensionReasoningScore

Conciseness

Operational and mostly lean — no padding explaining what tmux/CCB is, and lists earn their tokens — but a few classification/interpretation rules and recovery conditions could be tightened further. Not a 5 because some explanatory clauses remain that could be trimmed.

4 / 5

Actionability

Provides concrete executable `command ccb ...` and `tmux -S ... capture-pane` blocks plus an exact result shape and a state taxonomy. Falls just short of 5 because several recovery bullets are conditional ('use ... only when ...') rather than copy-paste-ready commands.

4 / 5

Workflow Clarity

A clear 6-step sequence with an explicit Verify step (re-run smallest relevant checks), a validate→fix→retry feedback loop, and a Red Lines guardrail section; validation checkpoints are present for the bounded restart/clear operations.

5 / 5

Progressive Disclosure

Single SKILL.md with no bundle files, well-sectioned under clear headers and no nested references; per the simple/no-bundle guidance, well-organized sections suffice for a top score.

5 / 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 concrete, complete, and well-triggered: it states multiple specific actions and gives explicit, natural 'Use for ...' conditions including symptom phrases users would actually say. It is a strong, low-conflict description.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Diagnose a named CCB agent', 'deep read-only pane inspection', 'apply bounded recovery', 'verify the result', 'request authorization before submitting a redacted GitHub issue' — giving comprehensive, non-abstract coverage.

5 / 5

Completeness

Explicitly answers both 'what' (diagnose, recover, verify, report) and 'when' via a clear 'Use for ...' clause with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases a user would say ('stuck, disconnected, not continuing, not replying, or showing provider errors') plus concrete command forms ('$ccb_diagnose agentname', '$ccb-diagnose agentname') give comprehensive coverage with synonyms.

5 / 5

Distinctiveness Conflict Risk

A narrow CCB-agent maintenance niche with domain-specific, distinctive triggers; minimal overlap risk with unrelated skills.

5 / 5

Total

20

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

Total

15

/

16

Passed

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.