CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

80

Quality

100%

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

100%

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, highly actionable recovery procedure: exact ccb commands with flags, explicitly sequenced gates with validation checkpoints and blocked-state feedback loops, and clean sectioning with no concept fluff. It assumes Claude's competence and every section carries operational value.

DimensionReasoningScore

Conciseness

The body is lean operational prose with no basic-concept explanations (it assumes Claude knows tmux/daemon graphs); the only repetition is brief safety cross-references ("busy checks pass", Red Lines), which earn their place at decision points rather than padding, so it sits at the lean-and-efficient anchor not the could-be-tightened anchor at 2.

3 / 3

Actionability

It is dense with exact, copy-paste-ready commands and flags ("ccb ps", "ccb queue --detail <agent|all>", "ccb reload --dry-run", "ccb restart <agent>", "ccb fault clear <rule_id|all>"), matching the fully-executable anchor rather than the pseudocode/incomplete anchor at 2.

3 / 3

Workflow Clarity

A 6-step Recovery Gates checklist and a 9-step Provider/API flow are explicitly sequenced with validation checkpoints ("ccb config validate", "ccb reload --dry-run") and feedback loops ("If `ccb restart <agent>` returns `blocked` or `failed`, report the blockers"), meeting the clear-sequence-with-validation anchor; validation is present for the destructive ops so the cap-at-2 rule does not apply.

3 / 3

Progressive Disclosure

No bundle files exist and the skill is a single self-contained file organized into clear sections (Recovery Gates, Provider/API Recovery, Supported Actions, Handoffs, Red Lines) with no nested references; the procedural content is appropriately kept inline, matching the well-organized-sections anchor rather than the content-that-should-be-separate-is-inline anchor at 2.

3 / 3

Total

12

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description: it names concrete recovery targets and actions, pairs them with an explicit "Use when" trigger using natural user phrasing, and occupies a clearly distinct CCB-specific niche. It uses third-person imperative voice with no first/second person and avoids vague fluff.

DimensionReasoningScore

Specificity

Enumerates 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"), matching the multiple-specific-actions anchor rather than the domain-plus-some-actions anchor at 2.

3 / 3

Completeness

It explicitly states what the skill does (Recover ...) and when to use it via an explicit "Use when ..." trigger, so it clears the both-what-and-when bar rather than the implied-when anchor at 2.

3 / 3

Trigger Term Quality

The "Use when the user asks to fix, recover, restart if safe, clear context, reload, remount, or keep work going after provider/API failure" clause gives broad, natural phrasing a user would actually say, meeting the good-coverage anchor rather than the some-keywords-missing anchor at 2.

3 / 3

Distinctiveness Conflict Risk

The CCB runtime-recovery niche with CCB-specific trigger terms is clearly distinguishable and unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

12

/

12

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.