{"skill":{"slug":"random-coffee-best-fit-outreach","displayName":"Random Coffee Best Fit Outreach","summary":"Offline random coffee skill for ranking opt-in people and preparing consent-first intro packets. It creates local reports only; any external communication st...","description":"---\nname: random-coffee-best-fit-outreach\ndescription: Offline random coffee skill for ranking opt-in people and preparing consent-first intro packets. It creates local reports only; any external communication stays outside the public skill.\nversion: 0.1.4\nhomepage: https://github.com/zack-dev-cm/random-coffee-best-fit-outreach\nlicense: MIT\nuser-invocable: true\nmetadata: {\"openclaw\":{\"homepage\":\"https://github.com/zack-dev-cm/random-coffee-best-fit-outreach\",\"skillKey\":\"random-coffee-best-fit-outreach\",\"requires\":{\"anyBins\":[\"python3\",\"python\"]}}}\n---\n\n# Random Coffee Best Fit Outreach\n\n## Goal\n\nRun a consent-first random coffee workflow from local participant data:\n\n- normalize opt-in people into a small participant CSV\n- rank best-fit 1:1 intro candidates by mutual utility\n- draft first-touch and double opt-in intro text\n- render an offline review packet for the operator\n- keep external communication outside this public skill\n\n## Use This Skill When\n\n- the user asks for random coffee, best-fit introductions, warm networking, or founder/operator matching\n- the source data is already opt-in, consented, or intentionally provided by the operator\n- an older chat-first matching project exists and should be adapted into a public-safe intro workflow\n- Codex should produce a repeatable intro packet, not ad hoc social copy\n\n## Inputs\n\nUse a CSV with these canonical columns:\n\n```csv\nperson_id,display_name,role,organization,location,timezone,languages,domains,skills,offers,needs,preferred_channel,availability,consent_notes,do_not_match,notes\n```\n\nRead `references/intake-schema.md` when the user gives messy notes, a contact map, or community notes.\n\n## Workflow\n\n1. Restate the cohort goal, target audience, consent boundary, and verification command.\n2. Normalize participant data into the CSV schema. Use placeholder or consented data only.\n3. Rank matches:\n   - In a cloned repo: `python3 -m random_coffee_matcher rank <people.csv> --format markdown --out <report.md>`.\n   - From this skill wrapper in the repo: `python3 {baseDir}/scripts/random_coffee_matcher.py rank <people.csv> --format markdown --out <report.md>`.\n4. Review the top matches. Prefer pairs with clear mutual utility, language overlap, manageable timezone gaps, and complete consent notes.\n5. Generate a reviewed packet for any selected pair:\n   - `python3 -m random_coffee_matcher packet <people.csv> <person-a-id> <person-b-id> --out <packet.md>`.\n6. Hand the packet to the operator. Any external communication happens outside this public skill.\n7. Log the operator-recorded outcome: skipped, blocked, opted in, declined, scheduled, or closed.\n\n## External Communication Boundary\n\nRead `references/outreach-surface-runbook.md` before using the packet outside the repo.\n\nRules:\n\n- Use only operator-provided or consented participant data.\n- Keep the generated packet local until the operator approves it.\n- Do not include private notes, long copied profile text, or private conversations in public artifacts.\n- Do not reveal names, handles, links, or detailed context until both sides opt in.\n- If any platform, privacy, or account-control issue appears, stop this workflow and ask for human handling outside the skill.\n\n## Outreach Rules\n\n- First touch asks whether the person wants to be considered. It should not reveal another person's identity.\n- Double opt-in asks each side before sharing names, handles, links, or detailed context.\n- Keep drafts short, concrete, and easy to decline.\n- Avoid fake urgency, pressure, claims of personal familiarity, or unverifiable praise.\n- If either person declines or does not reply after the agreed follow-up limit, close the case.\n\n## Verification\n\nFor the open-source repo, run:\n\n```bash\npython3 -m pytest -q\npython3 -m random_coffee_matcher rank examples/participants.csv --format text\npython3 scripts/check_clawhub_skill_surface.py\n```\n\nBefore publishing, run the local public-surface audit available in the surrounding Codex workspace when present.\n","tags":{"consent":"0.1.4","discord":"0.1.4","introductions":"0.1.4","latest":"0.1.4","linkedin":"0.1.4","matching":"0.1.4","networking":"0.1.4","outreach":"0.1.4","random-coffee":"0.1.4"},"stats":{"comments":0,"downloads":442,"installsAllTime":1,"installsCurrent":1,"stars":0,"versions":5},"createdAt":1777036122053,"updatedAt":1778492741073},"latestVersion":{"version":"0.1.4","createdAt":1777516525190,"changelog":"Reviewed source and refreshed public ClawHub skill surface.","license":"MIT-0"},"metadata":{"setup":[],"os":null,"systems":null},"owner":{"handle":"zack-dev-cm","userId":"s170hyv1nagjajq3y5c6kpzx3s84jp29","displayName":"Zakhar Pashkin","image":"https://avatars.githubusercontent.com/u/112114097?v=4"},"moderation":null}