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".

64

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/saas-packs/coderabbit-pack/skills/coderabbit-incident-runbook/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%Weight 40%Scale 1-3

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

A well-organized incident runbook with useful severity tiers and mostly concrete commands, but it leans on echo-described rather than executed steps for the most critical (P1) actions and lacks validation checkpoints around destructive branch-protection changes.

Suggestions

In Step 2 (P1), replace 'echo "gh api ..."' descriptions with actual executable commands guarded by confirmation prompts, so the emergency bypass is copy-paste runnable.

Add explicit validation checkpoints before and after destructive operations (e.g. confirm branch protection is currently active before DELETE, verify restore succeeded after PUT).

Trim concept-padding (e.g. 'Since CodeRabbit is a managed SaaS service...') and the full communication template could be moved to a referenced file to reduce inline tokens.

DimensionReasoningScore

Conciseness

Mostly efficient with concrete scripts per severity level, but includes redundant inline echo statements describing commands instead of running them, plus a lengthy communication template and concept-padding ('Since CodeRabbit is a managed SaaS service...') that could be tightened.

2 / 3

Actionability

Provides concrete gh/curl commands, but P1 Step 2 only echoes commands (e.g. 'echo "gh api ... DELETE"') instead of executing them, and the branch-protection restore uses --field flags with JSON that may not parse, leaving key actions instructive rather than copy-paste executable.

2 / 3

Workflow Clarity

Steps are clearly sequenced by severity with a quick-triage decision tree, but destructive operations (removing branch protection, admin merge) lack explicit validation checkpoints before execution and the post-incident restore has no verify-success feedback loop, capping it at 2.

2 / 3

Progressive Disclosure

Content is well-sectioned by severity level but is a single monolithic SKILL.md with no bundle files; the one external pointer ('see coderabbit-data-handling') is a bare reference rather than a clearly signaled one-level-deep navigation structure.

2 / 3

Total

8

/

12

Passed

Description

100%Weight 40%Scale 1-3

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-scoped description that clearly conveys both purpose and trigger conditions using concrete, natural language. Minor padding from the redundant 'Trigger with phrases like' line could be trimmed but does not meaningfully weaken it.

DimensionReasoningScore

Specificity

Lists multiple concrete actions (incident response, triage when reviews stop posting, bypass when PRs are blocked, addressing incorrect reviews) tied to specific CodeRabbit failure modes rather than vague language.

3 / 3

Completeness

Explicitly states what it does ('Execute CodeRabbit incident response procedures') and when to use it ('Use when CodeRabbit is down...') with explicit trigger guidance, satisfying both the what and the when.

3 / 3

Trigger Term Quality

Provides natural trigger phrases a user would actually say ('coderabbit incident', 'coderabbit down', 'coderabbit broken', 'coderabbit emergency', 'coderabbit not reviewing') with good variation coverage.

3 / 3

Distinctiveness Conflict Risk

Scoped to a single named SaaS service (CodeRabbit) with distinctive trigger phrases, making it unlikely to fire for unrelated incident-response or review skills.

3 / 3

Total

12

/

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.