Update to Kowalah

{
  "description": "Take an idea or an ask to the Kowalah team properly — check what already exists, test it against the AI vision, score it, and submit it. Use for \"I need help with\", \"raise this with Kowalah\", \"we should look into\", \"I've got an idea about\", or when a review turns up a gap somebody wants to act on.",
  "included_files": [],
  "name": "raise-opportunity",
  "skill_md_contents": "---\nname: raise-opportunity\ndescription: Take an idea or an ask to the Kowalah team properly — check what already exists, test it against the AI vision, score it, and submit it. Use for \"I need help with\", \"raise this with Kowalah\", \"we should look into\", \"I've got an idea about\", or when a review turns up a gap somebody wants to act on.\n---\n\n# Raise an opportunity\n\n`kowalah_create_opportunity` is the single entry point for everything a client might want\nhelp with — a quick question, a piece of work for the Kowalah team, a new initiative, a\nproject to scope. **The user does not need to decide in advance which it is.** They\ndescribe what they are trying to do; Kowalah triages from there. Anyone in the organisation\ncan raise one, at any role.\n\nThis skill is the four things to do before submitting. Skipping them is how thin,\nunscoreable opportunities end up in the queue.\n\n## Read the model before you ask\n\nThe operating model already holds the owners, the steps, the timings, the constraints, the\nquality bars and the work in flight. **Ask the user only for what it doesn't have.**\nQuestioning someone about a process the model already describes wastes their time and\ntells them you didn't look.\n\nWhere the model is missing something, that absence is usually the finding — say what isn't\nrecorded rather than quietly filling the gap from conversation.\n\n## 1. Check the library first\n\n**`kowalah_find_accelerator`** before anything else. The library holds proven skills,\nplugins, prompts, guides and templates: the organisation's own accelerators plus Kowalah's\nlibrary, each result tagged with a `scope` of `organization` or `kowalah`.\n\nEach result lists an edition per AI platform, with how to get it (download, read or\nwatch, open a link, copy a prompt), how to use it, and a `url` to its page in the Kowalah\napp, where files are downloaded. If the ask is about a step in their operating model, pass\nits `process_step_id` to find what fits that step. A result with `access: \"preview\"` is\none their plan shows only in outline: say what it does and pass on the note about the\nfull library, rather than guessing at its contents. **If there is a\nmatch, the right outcome is the user using it today — not an opportunity raised for\nsomething that already exists.** Say what you found, offer it, and only continue if it\ngenuinely does not fit.\n\nSearch on the problem, not the solution. Someone asking for \"an AI tool to summarise\nsupplier contracts\" should be searched as \"contract review\" and \"supplier\" separately —\nthe useful match is rarely phrased the way the ask is.\n\n## 2. Get the description to something real\n\nThe server enforces a minimum length, but the bar that matters is higher than the one it\nchecks. A one-line opportunity wastes everyone's time and is slower to triage.\n\nIf the first message is thin, ask:\n\n- What is the goal — what changes if this works?\n- What would good look like?\n- What context should Kowalah know that isn't obvious? Systems, constraints, who is\n  involved, what has already been tried.\n\nWrite it up as a paragraph or more. Keep the user's own words for the goal; they are\nusually more precise than a tidied-up version.\n\n## 3. Test it against the vision\n\nIf the organisation has a vision map — the `vision` block on\n`kowalah_get_operating_model`, or `kowalah_get_vision` — **name in the `content` which\nguiding principle this serves and which KPI it moves.**\n\nSeveral clients make this their own programme success measure: *every use case names the\nKPI it moves before it starts.* This tool is where that gets enforced, so do it properly.\n\nEach principle carries its defining attributes as an assertion plus a counter-clause — *\"It\nmoves a business KPI.\" / \"Not a good idea in search of one.\"* **Apply both halves.** The\ncounter-clause is the useful one; it is what lets you tell the user their idea is a good\nidea in search of a problem without it being your opinion.\n\n**If it does not obviously serve any principle, say so to the user before submitting. That\nis a real signal, not a blocker.** Plenty of worthwhile work sits outside the current\nvision, and surfacing the mismatch is more useful than quietly forcing a fit.\n\nIf `lastUpdatedAt` shows the vision map is well over a year old, note that alongside the\nmismatch. \"This doesn't fit the vision, but the vision hasn't been revisited since last\nMarch\" is a fairer thing to put in front of a triage team than either half alone.\n\nSkip this step entirely when no vision map exists.\n\n## 4. Score it\n\nICE — impact, confidence, ease, each 1–10, with a short rationale for each. Technically\noptional in the schema; **expected in practice.** Unscored opportunities are slower to\ntriage and give the team nothing to weigh them against. Skip only if the user explicitly\ndeclines.\n\nFor `impact`, use the slot that fits — the point is a number the business recognises:\n\n- **business** — *\"£2M annual cost reduction in supplier spend\"*\n- **productivity** — *\"200 hours/week saved across support\"*\n- **adoption** — *\"drive ChatGPT login rate from 15% to 60%\"*\n\nThe composite is computed server-side. Partial scores are accepted, but push for all three\nnumbers plus a rationale each. Do not invent the numbers — ask. \"What would this be worth\nif it worked?\" is a question the user can usually answer, and their answer is better than\nyour estimate.\n\n## Before you call the tool\n\n- **Which organisation?** `organization_id` is required. If the user belongs to more than\n  one, ask — do not guess. `kowalah_get_update` with no query lists their organisations.\n- **Is this a response to a Kowalah discovery?** Check `pending_discoveries` in the\n  `kowalah_get_update` home view. If it is, pass that `discovery_id` — it links the\n  response to the brief, stamps the opportunity with the discovery and its project, and\n  marks the audience invite responded. Anchor the impact rationale to the discovery's\n  `business_value_context`.\n- **Is it about a process the user cannot edit?** Then the right tool is\n  `kowalah_propose_process_change`, not this one — it files the opportunity against the\n  process (optionally pinned to one step) so the owner can pick it up.\n- **Optional but useful:** `department`, `source_note` (*\"raised at yesterday's leadership\n  meeting\"*), `requested_project_id`.\n- **`requested_target_type`** — `deliverable` or `expert_request` — only if the user has a\n  strong view on the form of help. **Omit it if they are unsure.** Guessing here pre-empts\n  a decision Kowalah makes together with the client, and a wrong guess is worse than no\n  guess.\n\n## After\n\n**Tell the user the opportunity number.** It is how they refer back to it — `kowalah_get_update`\nwith that number brings up its status. The response also returns their recent opportunities,\nso they can see their queue; worth showing if they have several in flight.\n"
}