CtrlK
BlogDocsLog inGet started
Tessl Logo

coderabbit-incident-runbook

Execute CodeRabbit incident response procedures when reviews stop working or block PRs. Use when CodeRabbit is down, reviews are not posting, PRs are blocked by stale checks, or CodeRabbit is producing incorrect reviews. Trigger with phrases like "coderabbit incident", "coderabbit outage", "coderabbit down", "coderabbit broken", "coderabbit emergency", "coderabbit not reviewing".

59

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured incident runbook with clear severity levels, executable diagnostics, and post-incident recovery, but it is held back by echo-displayed commands in the critical P1 step, padded bash commentary, a destructive action without a pre-execution validation gate, and a monolithic single-file layout with no bundle references.

Suggestions

Make the P1 emergency bypass commands actually executable (or clearly mark them as copy-paste) instead of wrapping them in `echo`, and add an explicit confirm/validation checkpoint before the destructive branch-protection removal.

Tighten the bash blocks by removing echo commentary and parenthetical asides so each block is lean and runnable.

Move detailed config examples and the communication template into reference files under references/ and link to them with signaled markdown links to improve progressive disclosure.

DimensionReasoningScore

Conciseness

The body is mostly operational runbook content without concept over-explanation, but many bash blocks are padded with echo commentary ('Option A: Remove Required Check', parenthetical asides) that could be tightened. Not a 1 because it avoids explaining concepts Claude already knows; not a 3 because the echo-heavy blocks are not lean.

2 / 3

Actionability

Steps 3 and 7 contain real executable `gh api` commands, but the most critical P1 bypass step merely echoes the command (`echo "gh api .../protection --method DELETE"`) instead of running it, so guidance is concrete but not consistently copy-paste ready. Not a 3 because of this executable/pseudocode inconsistency; not a 1 because exact commands are shown.

2 / 3

Workflow Clarity

A clear 7-step severity-ordered sequence with a triage gate (Step 1), recovery (Step 7), and an error-handling table is present, but the destructive branch-protection removal lacks an explicit validation/confirm checkpoint before execution, capping it at 2 per the destructive-operations guidance. Not a 1 because sequencing and verification are clearly present.

2 / 3

Progressive Disclosure

No bundle files exist (references/, scripts/, assets/ absent) and the ~230-line body is monolithic with inline config examples and templates that could be split out; the single cross-skill reference is plain backtick text ('see `coderabbit-data-handling`') rather than a signaled link. Not a 1 because sections are well-organized; not a 3 because the file is far over 50 lines with content that should be separated left inline.

2 / 3

Total

8

/

12

Passed

Description

90%

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, well-targeted description: explicit third-person voice, clear what/when structure, and a rich set of natural trigger phrases. Its only weakness is that it states a single composite action rather than naming several concrete operations.

DimensionReasoningScore

Specificity

Names the domain ('Execute CodeRabbit incident response procedures') but lists trigger conditions rather than enumerating multiple distinct concrete actions, so it stops at 'names domain and some actions'.

2 / 3

Completeness

Clearly answers what it does and includes an explicit 'Use when CodeRabbit is down, reviews are not posting, PRs are blocked...' trigger clause, satisfying both what and when.

3 / 3

Trigger Term Quality

Provides good coverage of natural phrases users would say: 'coderabbit incident', 'coderabbit outage', 'coderabbit down', 'coderabbit broken', 'coderabbit emergency', 'coderabbit not reviewing'.

3 / 3

Distinctiveness Conflict Risk

Targets a narrow CodeRabbit-specific incident niche with distinct, brand-qualified triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

14

/

16

Passed

Repository
jeremylongshore/claude-code-plugins-plus-skills
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.