gamma-incident-runbook
Manage incident response for Gamma integration issues. Use when experiencing production incidents, outages, or need systematic troubleshooting procedures. Trigger with phrases like "gamma incident", "gamma outage", "gamma down", "gamma emergency", "gamma runbook".
80
77%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./plugins/saas-packs/gamma-pack/skills/gamma-incident-runbook/SKILL.mdQuality
Discovery
89%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a solid skill description with excellent trigger terms and completeness. The explicit 'Use when' clause and enumerated trigger phrases make it easy for Claude to select appropriately. The main weakness is that the specific capabilities (what actions the skill actually performs during incident response) could be more concrete.
Suggestions
Add specific concrete actions the skill performs, e.g., 'diagnose connection failures, check service health, escalate alerts, execute recovery steps' to improve specificity.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names the domain (incident response for Gamma integration) and mentions some actions (troubleshooting procedures), but doesn't list specific concrete actions like 'diagnose connection failures, escalate alerts, restart services, check logs'. | 2 / 3 |
Completeness | Clearly answers both 'what' (manage incident response for Gamma integration issues) and 'when' (experiencing production incidents, outages, or need systematic troubleshooting), with explicit trigger phrases listed. | 3 / 3 |
Trigger Term Quality | Includes strong natural trigger terms: 'gamma incident', 'gamma outage', 'gamma down', 'gamma emergency', 'gamma runbook', plus general terms like 'production incidents', 'outages', and 'troubleshooting procedures'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | The 'Gamma integration' qualifier and specific trigger phrases like 'gamma incident', 'gamma runbook' create a clear niche that is unlikely to conflict with other skills. The scope is well-bounded. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
64%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid incident runbook with highly actionable, executable commands across multiple well-defined scenarios. Its main weaknesses are the lack of explicit validation/verification steps after mitigation actions (critical for incident response), and the monolithic structure that could benefit from splitting into separate files per scenario. Some sections like communication templates and the prerequisites list add bulk without much value for Claude.
Suggestions
Add explicit verification steps after each mitigation action (e.g., after enabling throttling, check that error rates are decreasing; after deploying backup key, verify requests succeed).
Split individual incident scenarios into separate referenced files (e.g., scenario-5xx.md, scenario-rate-limit.md) to reduce the main SKILL.md size and improve progressive disclosure.
Remove or significantly trim the communication templates and prerequisites sections — Claude can generate these on demand and they consume tokens without adding unique procedural value.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is reasonably structured but includes some unnecessary elements like the prerequisites section (Claude knows what access is needed), the communication templates (boilerplate Claude can generate on demand), and the severity table which is organizational policy rather than actionable technical guidance. The core diagnostic and response sections are fairly efficient. | 2 / 3 |
Actionability | The skill provides concrete, executable bash commands for every diagnostic step and incident scenario. Commands are copy-paste ready with real endpoints, curl flags, grep patterns, and jq filters. Each scenario has specific, ordered actions with actual commands rather than vague instructions. | 3 / 3 |
Workflow Clarity | Steps are clearly sequenced within each scenario and the diagnostic flow is logical (check status → review metrics → review logs). However, there are no explicit validation checkpoints or feedback loops — for instance, after enabling throttling or circuit breakers, there's no 'verify the mitigation is working' step. For incident response involving production systems, this is a notable gap. | 2 / 3 |
Progressive Disclosure | The content is a long monolithic document (~200 lines) that could benefit from splitting scenarios into separate files. The 'Next Steps' reference to gamma-data-handling is good, but there are no bundle files to support progressive disclosure. The internal structure with clear headers helps navigation but the document is heavy for a single SKILL.md. | 2 / 3 |
Total | 9 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 9 / 11 Passed | |
- Commit
3a2d27d
- 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.