ccb-self-recover

Recover CCB agents, panes, mounts, provider contexts, API/provider failures, config reload aftermath, clear operations, and guarded single-agent restarts. Use when the user asks to fix, recover, restart if safe, clear context, reload, remount, or keep work going after provider/API failure.

Quality

98%

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

96%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, command-dense recovery runbook with explicit gated workflows, validation steps, and red lines — strong across actionability, workflow clarity, and conciseness. The only minor gap is that some material (e.g., the full Supported Actions or Red Lines catalog) could optionally live in a reference file to keep SKILL.md closer to an overview.

Suggestions

Consider moving the full Supported Actions detail or Red Lines catalog into a separate reference file and linking to it, which would tighten SKILL.md toward an overview and could lift progressive_disclosure to 5.

Add a one-line 'Prerequisites' or 'When NOT to use this skill' pointer near the top so the gating intent is discoverable before the reader reaches Recovery Gates.

The Provider/API Recovery flow (9 steps) is dense; a short summary line of the happy path before the numbered steps would aid scanning without adding tokens.

Dimension	Reasoning	Score
Conciseness	The body is lean and bullet-driven with no padding or explanation of concepts Claude already knows; every line (gates, commands, red lines) earns its place and assumes competence.	5 / 5
Actionability	Concrete, copy-paste-ready commands with flags appear throughout ('ccb queue --detail <agent\|all>', 'ccb reload --dry-run', 'ccb restart <agent>', 'ccb fault clear <rule_id\|all>'), covering the common recovery cases.	5 / 5
Workflow Clarity	Multi-step processes (Recovery Gates 1-6, Provider/API Recovery 1-9) are explicitly sequenced with validation checkpoints ('ccb config validate', 'ccb reload --dry-run' before 'ccb reload', busy checks before restart) and feedback loops on 'blocked'/'failed' outcomes — appropriate for a destructive/restart skill.	5 / 5
Progressive Disclosure	Well-organized into clear single-level sections (Recovery Gates, Provider/API Recovery, Supported Actions, Handoffs, Red Lines) with no nested references, but at ~100 lines it slightly exceeds the simple-skill threshold where pure inline structure would score 5.	4 / 5
	Total	19 / 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 a strong, third-person statement that concisely pairs concrete recovery capabilities with explicit natural trigger phrases, covering what and when comprehensively. It is dense but not padded, and occupies a distinct niche.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete recovery targets and actions ('Recover CCB agents, panes, mounts, provider contexts, API/provider failures, config reload aftermath, clear operations, and guarded single-agent restarts'), giving comprehensive coverage with no vague filler.	5 / 5
Completeness	Explicitly answers both what (recover agents/panes/mounts/provider contexts/failures/clear/restarts) and when (concrete 'Use when the user asks to fix, recover, restart if safe...' trigger phrases), with no missing guidance.	5 / 5
Trigger Term Quality	The 'Use when...' clause provides comprehensive natural trigger phrases users would actually say ('fix, recover, restart if safe, clear context, reload, remount, or keep work going after provider/API failure'), including synonyms.	5 / 5
Distinctiveness Conflict Risk	Occupies a clear, narrow CCB self-recovery niche with CCB-specific triggers, making conflict with unrelated skills minimal.	5 / 5
	Total	20 / 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-self-recover/SKILL.md
Commit: 01d5b1c

Reviewed: about 20 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.