OpenAgentSkill Agent Integration Kit
Version: openagentskill-agent-integration-kit-v1

Purpose:
Let an AI agent resolve a task into the right reusable skill, compare alternatives, review trust signals, and install with a safe handoff.

Canonical:
- Page: https://www.openagentskill.com/agent/integration-kit
- API: https://www.openagentskill.com/api/agent/integration-kit
- Resolve API: https://www.openagentskill.com/api/agent/resolve
- Manifest: https://www.openagentskill.com/.well-known/agent-manifest.json
- llms.txt: https://www.openagentskill.com/llms.txt

Recommended Flow:
1. Read /llms.txt or /.well-known/agent-manifest.json.
2. Choose the Codex, Claude Code, or Cursor template for the active agent surface.
3. Call /api/agent/resolve with task, agent, max_risk, and optional min_stars.
4. Read recommendation.best_skill, recommendation.install, recommendation.risk, and agent_handoff.
5. If auto_install_allowed is false, ask for human approval before installing.
6. Fetch /api/agent/evals and /api/agent/skills/{slug} before production use.
7. Install in a sandbox or low-risk workspace first.

Supported Agents:
- Codex: Coding agent / local workspace
  Resolve: https://www.openagentskill.com/api/agent/resolve?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=codex&max_risk=medium
  Best for: repo-aware implementation, code review, debugging, web automation setup
  Setup:
    - Add the copy prompt to your Codex project instructions or paste it before a task.
    - Call the Resolve API with the current task and agent=codex.
    - Read agent_handoff.review_checklist before installing a third-party skill.
    - Install only in the active workspace after reporting files and commands that will be touched.

- Claude Code: Claude Code skill workflow
  Resolve: https://www.openagentskill.com/api/agent/resolve?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=claude-code&max_risk=medium
  Best for: local skill instructions, project workflows, documentation-heavy tasks
  Setup:
    - Paste the copy prompt into Claude Code custom instructions or the start of a new task.
    - Call the Resolve API with agent=claude-code.
    - Use install targets only after audit and eval checks are acceptable.
    - Keep the skill scoped to the project and summarize activation steps.

- Cursor: Cursor rules / agent instructions
  Resolve: https://www.openagentskill.com/api/agent/resolve?task=scrape%20pricing%20pages%20and%20extract%20structured%20data&agent=cursor&max_risk=medium
  Best for: project rules, repeatable coding workflows, IDE assistant guidance
  Setup:
    - Paste the copy prompt into Cursor rules or the agent chat before a workflow.
    - Call the Resolve API with agent=cursor.
    - Turn the selected skill into a narrow project rule only when the safety gate allows it.
    - Keep generated rules task-scoped and avoid broad always-on instructions.


Stable 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.