Agent skill · software engineering · jeremylongshore
cohere-core-workflow-b
Build a bounded Cohere v2 tool-use loop with JSON Schema, explicit dispatch, result correlation, and approval gates. Use when adding Cohere-powered agents or function calling. Trigger with "Cohere tool use", "Cohere agent", or "Cohere function calling".
Why this skill is useful
Adds executable scripts for multi-step tool-using workflows with Cohere API that enhance the AI's capabilities.
What it needs
Requires npm installed locally. Requires cohere account access. About 2k tokens when loaded. Last updated 2026-08-07. 2,604 stars on the source repository.
What this skill does
Cohere Tool-Using Agent Loop Overview Let the model propose typed tool calls while application code validates, authorizes, executes, correlates, and limits every side effect. 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 Define each v2 tool as a function with JSON Schema parameters. Read proposed calls from the response message and correlate results with toolcallid. Append the assistant tool-call message and tool results to the application-managed messages history. Command A+ was the current high-capability tool-use candidate on the review date; resolve availability before pinning it. 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. Define a minimal tool allowlist, strict schemas, timeouts, and side-effect classifications. 2. Resolve a live tool-capable model and submit the user message plus tool definitions. 3. Validate tool name, arguments, tenant scope, and approval state before dispatch. 4. Execute read-only calls automatically only if policy allows; pause for consequential writes. 5. Append correlated tool results and continue until content is returned or the iteration budget is exhausted. 6. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills jeremylongshore/cohere-core-workflow-b