Update to Kowalah

{
  "description": "Talk through your own work and find where AI could actually help — grounded in your organisation's AI vision and what already exists, not generic advice. Use for \"where could AI help me\", \"what should I be using AI for\", \"I'm not sure what to automate\", \"help me think about my job\", or when someone has been told to look for AI opportunities and doesn't know where to start.",
  "included_files": [],
  "name": "spot-opportunities",
  "skill_md_contents": "---\nname: spot-opportunities\ndescription: Talk through your own work and find where AI could actually help — grounded in your organisation's AI vision and what already exists, not generic advice. Use for \"where could AI help me\", \"what should I be using AI for\", \"I'm not sure what to automate\", \"help me think about my job\", or when someone has been told to look for AI opportunities and doesn't know where to start.\n---\n\n# Spot opportunities in your own work\n\nFor anyone in a client organisation, whatever their role. Most people who install this\nplugin have no formal position in the operating model — they were told \"have a look at your\nwork and log anything worth doing\". This is that conversation.\n\nThe job is to get from *\"here's what I do all day\"* to either **something they can use\ntoday** or **one well-formed opportunity**. Not a list of twelve ideas.\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## Ground it first — this is what stops it being generic AI advice\n\nBefore asking anything about their work:\n\n1. **`kowalah_get_vision`** — the organisation's AI vision map, in its own words: the vision\n   statement, the guiding principles with their defining attributes, the success measures.\n2. **`kowalah_get_operating_model`** — the unit tree. You are looking for one thing: **is\n   their part of the business already mapped?** If it is, their work is probably already a\n   process with steps and an owner, and the conversation is different.\n\nAnyone can read both of these regardless of role. If either returns `kind: \"empty\"`, carry\non without it — just don't invent a vision that hasn't been written.\n\nIf the model comes back with **one unit and no processes**, and they are the sole `admin`\nof a single organisation with no vision authored, the account is in a new organisation\ncreated at sign-up rather than their company's existing one. Say so before going further,\nbecause it means two different things. For someone starting fresh it is the normal state:\nwhat they log is theirs, in their own organisation, and the conversation carries on. For\nsomeone whose company already works with Kowalah it is the wrong place, and what they log\nwill not reach the colleagues they expect. Ask which it is. Don't be reassured by the\norganisation's name — it is derived from their email domain, so it may well be their\nemployer's name. See the `kowalah-setup` skill.\n\nHaving the vision in hand changes the conversation from \"what could AI do\" to \"what would\nmove the things we said mattered\". Use the principles' own wording when you get to the\ntest; do not paraphrase them into generic AI-strategy language.\n\n## Then talk about their actual work\n\nNot a questionnaire. Ask what they do, then follow the friction.\n\n**Their first answer will usually be a tool** — *\"we should have a chatbot for this\"*,\n*\"could AI write our reports\"*. That is a solution, not a problem, and solutions offered\nfirst are usually the ones that don't survive scrutiny. Take it, then go underneath it:\nwhat makes the current way painful?\n\nQuestions that actually surface things:\n\n- **What do you wait for?** Not what takes you time — what sits there while you can't move.\n  Waiting is invisible on any time sheet and it is usually most of the elapsed time.\n- **What do you redo?** Rework means something upstream isn't right.\n- **What do you chase?** Chasing is pure coordination cost and nobody counts it.\n- **Where do you copy between systems?** Re-keying is the most common real finding and\n  almost nobody volunteers it — it feels too small to mention.\n- **What's the bit you dread?** People are honest about this one, and dread usually tracks\n  either high stakes or high tedium. Both are worth looking at.\n- **What do you do that only you know how to do?** A single point of knowledge is a risk\n  as well as an opportunity.\n\nFollow one thread properly rather than collecting six. A specific, well-understood piece of\nfriction beats a broad wish every time.\n\n## Check whether it already exists\n\n**`kowalah_find_accelerator`** as soon as you have something concrete.\n\nThe library holds proven skills, plugins, prompts, guides and templates: the organisation's\nown accelerators plus Kowalah's library, tagged `organization` or `kowalah`. Each result\nlists an edition per AI platform (how to get it and how to use it), a security summary\n(what it can read or do, and whether a person approves its actions) and a `url` to its page\nin the Kowalah app. When you're looking at a particular step of their work, pass its\n`process_step_id` to find what fits that step.\n\n**If there's a match, the best possible outcome of this conversation is them using it\ntoday.** That is a better result than a well-written opportunity, and it costs nothing.\nSay what you found and offer it.\n\nSearch on the problem, not their proposed solution. Someone asking for \"an AI tool to\nsummarise supplier contracts\" should be searched as \"contract review\" and \"supplier\"\nseparately.\n\n## Test it against the vision\n\nIf a vision map exists, apply it before going further.\n\nEach principle carries its defining attributes as an assertion plus a counter-clause —\n*\"It moves a business KPI.\" / \"Not a good idea in search of one.\"* **Both halves are the\ntest.** The counter-clause is the one that does the work: it lets you tell someone their\nidea is a good idea in search of a problem without it being your opinion.\n\nGlance at `lastUpdatedAt` before leaning on it hard. If the vision is a year or more old,\napply it as written but hold it more loosely — and if a good idea fails a stale principle,\nthat is worth saying out loud rather than using it to close the conversation.\n\nName the principle it serves and the KPI it moves. If it serves none, **say so** — plenty\nof worthwhile work sits outside the current vision, and the mismatch is more useful\nsurfaced than quietly forced to fit.\n\n## Where it goes\n\nThree routes. Pick one; don't offer all three.\n\n**They can use an accelerator today** → hand it over and stop. Done.\n\n**It's about a process that's already in the operating model** → `kowalah_get_process` to\nread it, then **`kowalah_propose_process_change`**. This files it against the process\n(optionally pinned to one step) so the owner picks it up. Anyone may propose against any\nprocess they can see, whatever their role, and nothing about the process changes. This is\nthe right route whenever the work is already mapped — it lands with the person who can\nactually act on it.\n\n**It's a new ask** → hand off to **`raise-opportunity`**, which gets the description, the\nICE score and the vision reference right. Don't write the opportunity inline here.\n\n## Be straight with them\n\n- **Don't promise anything gets built.** An opportunity is an ask that gets triaged by the\n  Kowalah team, weighed against everything else. Say that.\n- **\"No opportunity here\" is a fine outcome.** A conversation that ends with someone\n  understanding their own process better and nothing logged is a success. Manufacturing an\n  opportunity to have something to show wastes the triage queue and their time.\n- **What they see is partial.** They can read the whole operating model and vision, but\n  `kowalah_get_update` shows them only their own opportunities plus items they're a\n  stakeholder on. If they ask what else is going on, that's the honest answer — there may\n  be work in flight on this already that they can't see. Worth mentioning before they raise\n  something.\n- **Ask which organisation** if they belong to more than one. `kowalah_get_update` with no\n  query lists them.\n"
}