Agent skill · marketing growth · jeremylongshore
cohere-incident-runbook
Analyze and mitigate Cohere integration incidents with provider, model, capacity, data, and application evidence plus reversible actions. Use when responding to an outage or serious degradation. Trigger with "Cohere incident", "Cohere outage", or "Cohere on-call".
Why this skill is useful
Adds specific executable scripts for incident response and troubleshooting for the Cohere API that are not widely known.
What it needs
Requires jq, kubectl installed locally. Requires cohere, pagerduty, slack account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Cohere Incident Runbook Overview Restore a safe user experience first, preserve evidence, and distinguish provider incidents from local regressions before making changes. Prerequisites The target repository, runtime, environment, and accountable owner An approved Cohere team and key for any live verification Current quality, security, privacy, capacity, and change-control requirements Tool Discipline Use Read, Glob, and Grep to inspect code, configuration, and evidence. Use WebFetch only for current Cohere primary documentation. Use Write or Edit only when the user requested implementation and the exact target files are known; never write credentials or customer content. Current Contract Check Cohere's status page, but treat service-specific evidence as authoritative for your workload. Separate authentication, billing, throttling, model retirement, provider 5xx, retrieval, and application failures. Use only pre-approved degradation paths such as queueing, cached answers, read-only mode, or an evaluated model route. Never debug by dumping keys, prompts, documents, or unrestricted environment variables. Authentication Use an environment-specific key injected from an approved secret manager. Never print, persist, commit, or place COAPIKEY in an example. Confirm access with the least costly bounded operation appropriate to the task, and treat key creation, rotation, revocation, role changes, and production-capacity requests as owner-approved actions. Instructions 1. Open the incident record and capture start time, impact, environment, endpoint, model, release, and correlation IDs. 2. Check provider status and compare control traffic, regions, models, and recent local changes. 3. Classify the failure and apply the smallest reversible mitigation within the incident authority matrix. 4. Protect data and side effects while monitoring recovery against explicit thresholds. 5. Escalate to Cohere with the redacted debug bundle when provider assistance is required. 6. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/cohere-incident-runbook