Update to Kolena

{
  "description": "Use when creating or improving a Kolena Agent by designing or revising its Prompts, settings, dependencies, and controls, or diagnosing inaccurate Results. Not for simply processing documents with an existing Agent.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 272
    },
    {
      "relative_path": "references/prompt-design.md",
      "size_in_bytes": 4395
    }
  ],
  "name": "agent-authoring",
  "skill_md_contents": "---\nname: agent-authoring\ndescription: >-\n  Use when creating or improving a Kolena Agent by designing or revising its Prompts, settings, dependencies, and\n  controls, or diagnosing inaccurate Results. Not for simply processing documents with an existing Agent.\n---\n\n# Agent authoring\n\nBuild a reusable Agent that produces the user's intended business output, not merely an empty Agent. Own the Prompt\ndesign; ask the user for domain rules, exceptions, and disputed answers rather than asking them to write Prompts. If\nthey want to word instructions themselves, point them to\n[Writing Effective Prompts](https://docs.agents.kolena.com/writing-effective-prompts). Use the `process-documents` skill\nwhen the task is only to process documents with an existing Agent.\n\nWhen choosing or changing Prompt types, settings, dependencies, or controls, or diagnosing Results, read\n[Prompt design for Kolena Agents](references/prompt-design.md).\n\n## Establish the target and requirements\n\n- Resolve the intended Workspace before writing. If it is ambiguous, ask; do not switch Workspaces to work around an\n  error. For an existing Agent, read its current configuration with `kolena_get_agent` and inspect relevant Runs and\n  Results when the request concerns its behavior.\n- Establish what documents belong in one Run, the desired output, and how people will use it. Distinguish documents\n  supplied per Run from standing Prompt Documents. Ask focused questions where missing business rules or required\n  inputs would materially change the Agent; do not infer them from one sample or a convenient nearby value.\n\n## Design and change\n\n- Use the smallest Prompt set that meets the requirement. Add Document Filters, Conditionals, dependencies, or\n  processing modes when they solve an actual input or output problem; do not optimize credits at the expense of\n  untested correctness.\n- Treat earlier tool results as snapshots. Before editing after a pause, a reported out-of-band change, or a conflicting\n  result, re-read the Agent. If an intervening change affects the planned edit, reconcile it with the user rather than\n  silently overwriting it.\n- After related writes, read the Agent back to confirm saved instructions, configurations, and dependencies. If a write\n  is not yet reflected, check again before treating it as failed. Do not report a change as verified solely because a\n  write call succeeded.\n\n## Verify as the task warrants\n\n- A Prompt edit can make existing Results, including dependent Results, out of date; it does not recompute them.\n  When testing is useful and authorized, prefer representative existing Runs and known-correct answers. New Runs and\n  re-running Prompts consume credits. Use `process-documents` for test-Run upload and retrieval mechanics when needed.\n  Do not assume every authoring task needs a new Run or a fixed iteration loop, and do not start broad or repeated\n  billable recomputation without clear user direction.\n- Diagnose a Result before revising its Prompt. Distinguish failed, skipped, empty, human-corrected, and plausible but\n  wrong values, and check whether its `prompt_version` matches the Prompt's current `version` in `kolena_get_agent`.\n  Without a Validation against a Ground Truth, or known-correct answers from the user, describe observations rather\n  than claiming measured accuracy.\n\n## Features to set up in Kolena\n\nThese tools can't configure the features below yet. When one would serve the user's goal, recommend it, say it is set up\nin Kolena, and link the Agent's `web_url` and the feature's guide where one is linked below. Don't leave it out, or\nsubstitute something weaker, without telling the user.\n\n- **[Prompt Documents](https://docs.agents.kolena.com/prompts#attaching-files):** files attached to a Prompt as\n  reference material it uses on every Run, such as a rate card, policy, or checklist.\n- **Agent Guidelines:** instructions applied across all of an Agent's Prompts. `kolena_get_agent` returns existing ones;\n  keep new Prompts consistent with them.\n- **[Agent Validation](https://docs.agents.kolena.com/how-to/measuring-accuracy):** scores an Agent's output against a\n  Ground Truth, a set of known-correct answers, from the Agent's Validation tab. Runs are matched to the Ground Truth by\n  `user_defined_id`, so give test Runs one the user supplies. It may need to be enabled for the user's organization.\n- **[Output Templates](https://docs.agents.kolena.com/templated-outputs):** a document or spreadsheet filled with a\n  Run's Results. Each Prompt's `template_alias` is its placeholder.\n- **[Integrations](https://docs.agents.kolena.com/connections):** bring documents into an Agent automatically, or send\n  its Results elsewhere, for recurring work.\n\nIf the Kolena tools are missing or a call fails authentication, tell the user to connect or sign in to Kolena again; do\nnot infer that an Account has no Agents or Runs. Finish by naming what changed, what was actually checked, and which\nbusiness decisions or uncertainties remain.\n"
}