Star0

Agent Integration Kit

Add OpenAgentSkill to your agent.

Use these copy-paste templates and API contracts to let Codex, Claude Code, Cursor, or another agent resolve tasks into reusable skills before building from scratch.
Open text kitTry resolveOpenAPI
3
Agent templates
9
Stable fields
v1
Kit version
API
Install handoff

Canonical flow

The minimum contract for agent adoption.

Agents should not scrape the UI or pick random repositories. They should call the resolver, inspect the handoff, then install only after the safety gate is acceptable.

01

Read /llms.txt or /.well-known/agent-manifest.json.

02

Choose the Codex, Claude Code, or Cursor template for the active agent surface.

03

Call /api/agent/resolve with task, agent, max_risk, and optional min_stars.

04

Read recommendation.best_skill, recommendation.install, recommendation.risk, and agent_handoff.

05

If auto_install_allowed is false, ask for human approval before installing.

06

Fetch /api/agent/evals and /api/agent/skills/{slug} before production use.

Copy templates

Codex, Claude Code, and Cursor setup.

JSON contract

Coding agent / local workspace

Codex

repo-aware implementation / code review / debugging / web automation setup

1Add the copy prompt to your Codex project instructions or paste it before a task.
2Call the Resolve API with the current task and agent=codex.
3Read agent_handoff.review_checklist before installing a third-party skill.
4Install only in the active workspace after reporting files and commands that will be touched.

Prompt

You are using OpenAgentSkill as the skill resolution layer for Codex.
Before building a custom workflow from scratch, call the Resolve API with the user task.
Resolve endpoint: https://www.openagentskill.com/api/agent/resolve?task={USER_TASK}&agent=codex&max_risk=medium
Use recommendation.best_skill as the default only after checking recommendation.risk, safety_gate, and agent_handoff.review_checklist.
If auto_install_allowed is false, ask for human approval before installing.
If blocked is true or risk notes mention secrets, shell, token, or network risk, do not auto-install.
Return the selected skill, install command, alternatives, risk summary, and next action before changing files.

Claude Code skill workflow

Claude Code

local skill instructions / project workflows / documentation-heavy tasks

1Paste the copy prompt into Claude Code custom instructions or the start of a new task.
2Call the Resolve API with agent=claude-code.
3Use install targets only after audit and eval checks are acceptable.
4Keep the skill scoped to the project and summarize activation steps.

Prompt

You are using OpenAgentSkill as the skill resolution layer for Claude Code.
Before building a custom workflow from scratch, call the Resolve API with the user task.
Resolve endpoint: https://www.openagentskill.com/api/agent/resolve?task={USER_TASK}&agent=claude-code&max_risk=medium
Use recommendation.best_skill as the default only after checking recommendation.risk, safety_gate, and agent_handoff.review_checklist.
If auto_install_allowed is false, ask for human approval before installing.
If blocked is true or risk notes mention secrets, shell, token, or network risk, do not auto-install.
Return the selected skill, install command, alternatives, risk summary, and next action before changing files.

Cursor rules / agent instructions

Cursor

project rules / repeatable coding workflows / IDE assistant guidance

1Paste the copy prompt into Cursor rules or the agent chat before a workflow.
2Call the Resolve API with agent=cursor.
3Turn the selected skill into a narrow project rule only when the safety gate allows it.
4Keep generated rules task-scoped and avoid broad always-on instructions.

Prompt

You are using OpenAgentSkill as the skill resolution layer for Cursor.
Before building a custom workflow from scratch, call the Resolve API with the user task.
Resolve endpoint: https://www.openagentskill.com/api/agent/resolve?task={USER_TASK}&agent=cursor&max_risk=medium
Use recommendation.best_skill as the default only after checking recommendation.risk, safety_gate, and agent_handoff.review_checklist.
If auto_install_allowed is false, ask for human approval before installing.
If blocked is true or risk notes mention secrets, shell, token, or network risk, do not auto-install.
Return the selected skill, install command, alternatives, risk summary, and next action before changing files.

Stable fields

What an agent should read from Resolve.

These fields are intended as the stable integration surface for tools. The UI can change; this contract should stay predictable.

Response fields

  • recommendation.best_skill
  • recommendation.install
  • recommendation.why_recommended
  • recommendation.risk
  • recommendation.alternatives
  • agent_handoff.platform_templates
  • agent_handoff.review_checklist
  • agent_handoff.api_sequence
  • policy_decision

Safety rules

  • Do not auto-install when safety_gate.blocked is true.
  • Do not auto-install when recommendation.install.auto_install_allowed is false.
  • Escalate for human approval when shell, env, token, network, license, or unclear maintenance risk appears.
  • Prefer a lower-risk alternative when the selected skill has high risk notes.