community-alpha
Skill6 starsChanged 2 months agoMITView on GitHub
Run one full mining pass over an imported community-chat corpus: deterministic detector, LLM judge, harvest, review screen. Works on any imported corpus through a per-source config and is safe to re-run, being idempotent by message id. Triggers: "/community-alpha <source> [month]", "mine alpha from <community>".
In this repository100 other files it gives its agents.
- AGENTS.mdAGENTS.md
- 03Skill
- 1Skill
- agendaSkill
- alfa-search-recall-deepresearchSkill
- alpha-judgeSkill
- alpha-reviewSkill
- archSkill
- askSkill
- bibleSkill
- brainSkill
- busSkill
- canon-revisionSkill
- ccSkill
- chatgpt-syncSkill
- chat-searchSkill
- chatSkill
- claudeai-syncSkill
- coachSkill
- codex-mirrorSkill
- codex-reviewSkill
- cofounderSkill
- cofounder-watchSkill
- commentsSkill
- content-mineSkill
- crm-syncSkill
- declinedSkill
- dedupSkill
- defuddleSkill
- dr-fanoutSkill
- episodeSkill
- faaa-syncSkill
- faSkill
- fb-postSkill
- fb-replySkill
- fb-watchSkill
- findSkill
- fireflies-syncSkill
- five-hardSkill
- fleetSkill
- follower-onboardSkill
- geminiSkill
- gitbook-importSkill
- gmailSkill
- granola-syncSkill
- handoffSkill
- health-syncSkill
- inboxSkill
- intakeSkill
- intentionSkill
- introSkill
- issue-matchSkill
- journeySkill
- last30daysSkill
- local-chatgpt-token-healSkill
- mcpSkill
- migrateSkill
- mine-channelSkill
- n8nSkill
- notebooklmSkill
- The first 60 shown.
The file
Files
/community-alpha <source> [month] — one community-alpha run
Example: /community-alpha sostav 2026-06. No month given → the previous full month.
Steps
- Is there a detector?
$IMPORTS_ROOT/<source>\<source>_alpha.py(today:lobster,sostav).- No → this is a NEW corpus: offer the operator a one-off adapter built to the existing pattern (schema from their SQLite + language keys + intro/banter penalty + topic weights; template =
sostav_alpha.py). Do not build it without an explicit "+".
- No → this is a NEW corpus: offer the operator a one-off adapter built to the existing pattern (schema from their SQLite + language keys + intro/banter penalty + topic weights; template =
- Run the detector (0 tokens):
→cd /e/Obsidian/_imports/<source> && PYTHONIOENCODING=utf-8 python <source>_alpha.py \ --since <YYYY-MM-01> --until <the 1st of the next month> --top 35 --tag <YYYY-MM>$IMPORTS_ROOT/alpha/candidates/<source>-<tag>-report.md. Show the scanned→shortlisted counter. - Judge (me, with the session model): I read ONLY the report (~35 candidates, never the corpus — token economy) and give a verdict ✅ ALPHA / 🟡 WATCH / 🗑 NOISE with a reason for each → write
$IMPORTS_ROOT/alpha/candidates/<source>-judged-latest.md(format:## ✅ ALPHA/## 🟡 WATCH/## 🗑 NOISE (DROP), inside it### #N — title+ Verdict + Reason — the harvest parser already understands this). - Is the miner registered?
MINERSin$IMPORTS_ROOT/alpha/alpha_harvest.py. No → add the row("<source>", "<source>-judged-latest.md", "<home-note>"). ⚠️ A parallel fleet edits this file too — re-read it immediately before editing (verify-existing), and keep the edit strictly additive. Optional: a label in the server'sMINER_LABEL/ORDER(it does not crash without one — there is a fallback). - Harvest + screen:
python $IMPORTS_ROOT/alpha/alpha_harvest.py(counters!) →/alpha-review. The new batch is visible by the 🆕 badge.
Boundaries
- 🔒 Private communities (sostav and the like) are HIGH sensitivity: the layer stays strictly local, nothing goes outside; people surfaced by a find are approached value-first / warm intro only (zero cold DMs). Risk signals are DATA, not "opportunities".
- Judge honestly: reference cards, intro blurbs and restatements are 🗑 — never stretch a ✅ to pad the counter.
- This skill writes nothing into the vault; moving gold into home notes is a separate step behind the Tier-2 gate (the "→ to home" queue on the screen).
<!--kit-footer-->Like this skill? It is one of 100 in second-brain-starter-kit: the second brain we built for ourselves and run every day at Palo Alto AI Research Lab. Install the whole set with npx skills add tonydzi/second-brain-starter-kit. Everything is open source and free, so take what you need.
Flagships worth a look on their own: secondop-panel (a second opinion from a panel of external models), claude-memory-tidy (stop your agent's memory from rotting), telegram-mcp-kit (your own Telegram over MCP in about 15 minutes).
Author: Anton Dziatkovskii, Palo Alto AI Research Lab. Telegram @tonydzi - WhatsApp +1 341 222 9178 - X @Tony_Stef_
Engineers: want to test-drive this setup? Message me. I hand out free starter seeds to engineers who test and report back, and custom skill requests are welcome.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

