Update to august

{
  "name": "august-weekly-digest",
  "description": "Build a Slack-ready weekly digest of all August research — interviews and focus groups — run against a given org (or across all orgs) in the past 7 days. Surfaces top themes with supporting quotes, standout twin verbatims, and unresolved questions to follow up on, so the team stays caught up on customer signal without skimming raw transcripts. This workflow can be scheduled to run every Monday morning. Triggers on: \"weekly august digest\", \"august weekly recap\", \"summarize this week's research\", \"what did we learn from twins this week\", \"/august-weekly-digest\".",
  "included_files": [],
  "skill_md_contents": "---\nname: august-weekly-digest\ndescription: >\n  Build a Slack-ready weekly digest of all August research — interviews and\n  focus groups — run against a given org (or across all orgs) in the past 7\n  days. Surfaces top themes with supporting quotes, standout twin verbatims,\n  and unresolved questions to follow up on, so the team stays caught up on\n  customer signal without skimming raw transcripts. This workflow can be\n  scheduled to run every Monday morning. Triggers on: \"weekly august digest\", \"august\n  weekly recap\", \"summarize this week's research\", \"what did we learn from\n  twins this week\", \"/august-weekly-digest\".\n---\n\n# August Weekly Digest\n\nRoll up every August interview transcript and focus-group result from the\npast 7 days into a Slack-ready markdown digest, one section per org. All\ntools live under the August MCP.\n\nThe output is **copy-paste-ready markdown**, not an auto-post. The user\npastes it into #research, #product, or their own channel.\n\n---\n\n## When to use\n\n- User asks for a weekly recap of research / twin conversations.\n- User is prepping for a Monday standup and wants the customer signal from\n  the prior week.\n- A scheduled run fires every Monday morning.\n\n## When NOT to use\n\n- User wants deep synthesis of a *single* interview → use `/august-interview`.\n- User wants live feedback on a new artifact → use `/august-feedback`.\n- User wants a single focus-group readout → use `/august-focus-group-report`.\n- Time window is not \"past 7 days\" — for arbitrary windows, ask the user\n  and pass the date range through instead of hardcoding.\n\n---\n\n## STEP 1 — Resolve the org(s)\n\nThe digest is org-scoped. Figure out which org(s) to summarize.\n\n- If the user names a specific org (\"weekly digest for GNC\") → resolve via\n  `list_organizations` and use that one.\n- If the user says \"all my orgs\" / \"across everything\" → call\n  `list_organizations` and iterate over every org they have access to.\n- If ambiguous, default to **all orgs** rather than blocking — the digest is\n  cheap to skim and easy to trim. Note at the top which orgs were included.\n\n---\n\n## STEP 2 — Pull the past 7 days of activity per org\n\nFor each org, in parallel where possible:\n\n1. `list_conversations` with `org_id` and filter to conversations whose\n   `created_at` (or equivalent timestamp) falls within the last 7 days.\n2. `list_focus_groups` with `org_id` and filter to focus groups completed in\n   the last 7 days.\n\nIf both lists are empty for an org, produce the **empty-week fallback**\n(see STEP 5) — do NOT skip the org silently.\n\n---\n\n## STEP 3 — Fetch content for each item\n\nFor each conversation ID from step 2: call `get_interview_transcript`.\nFor each focus group ID from step 2: call `get_focus_group_results`.\n\nBatch these calls in parallel where the tool signatures allow. If any\nindividual fetch fails, note the item as \"unavailable\" in the digest\nrather than failing the whole run.\n\nKeep track of:\n- twin name / persona (for quote attribution)\n- artifact or topic evaluated\n- the raw response body\n\n---\n\n## STEP 4 — Synthesize the per-org digest\n\nFor each org, cluster across all items pulled and produce:\n\n- **3–5 top themes** — recurring reactions, objections, or observations that\n  showed up in more than one conversation. For each theme:\n  - one-sentence description of the theme\n  - one supporting verbatim quote (≤25 words), attributed to twin + org\n- **3–5 standout quotes** — the punchiest single lines from the week that\n  don't necessarily belong to a theme but are worth circulating. Attribute\n  each.\n- **Unresolved questions** — 2–4 things the research raised but didn't\n  answer, worth following up on next week.\n\n**Hard budget: ≤400 words per org.** If it runs long, cut themes down to 3\nand standout quotes down to 3. Slack readers scan; density beats completeness.\n\n---\n\n## STEP 5 — Format output\n\nReturn one markdown block per org, in this shape:\n\n```\n*August weekly digest — {Org name} — {date range}*\n_{N interviews, M focus groups} from the past 7 days_\n\n*Top themes*\n1. *{Theme name}* — {one-line description}\n   > \"{quote}\" — {twin name}\n2. …\n\n*Standout quotes*\n- > \"{quote}\" — {twin name}, on {topic}\n- …\n\n*Unresolved questions*\n- {question 1}\n- {question 2}\n\n_Source: {N} interviews, {M} focus groups. Full transcripts in August._\n```\n\nIf a run turned up nothing for an org, use the **empty-week fallback**:\n\n```\n*August weekly digest — {Org name} — {date range}*\nNo new interviews or focus groups this week. Consider spinning up a round\non {suggested topic based on prior weeks or open questions}.\n```\n\nAt the top of the whole response, add a one-line summary: \"Digest across N\norgs — copy-paste each block into Slack.\"\n\n---\n\n## Output rules\n\n- **Do NOT auto-post to Slack.** This skill produces markdown; the user\n  posts it.\n- **Do NOT include the raw transcript.** Only synthesized themes + quotes.\n- **Every quote must be attributable** to a real twin from the actual\n  transcripts — never invent verbatims.\n- **Keep it human.** Punchy quotes > paraphrases. If a twin said something\n  striking, use their words, not yours.\n- If the user later asks \"expand theme 2\" or \"what did Sarah say in full,\"\n  re-fetch that specific transcript rather than reconstructing from memory.\n"
}