agentleFS
automatewithudayautomatewithuday/GTM-Public-Traded-AI-Accounts/.claude/skills/status/SKILL.md

status

Skill0 starsChanged 4 months agoMITView on GitHub

Show the AIPT funnel — company counts per stage, recent qualifications, run history. Use when asked "where are we", "pipeline status", or before deciding which stage to run next.

  • Reads credentials

188 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use off, list and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • StakeholderSenseiSkill

    off

    Disable polygraph for this repo (user-only escape hatch; all hooks no-op)

    Also in 6 projects that use this

  • SuShuhengSkill

    list

    Use when checking obshare-cli upload history, finding document tokens, or reviewing previous upload URLs and permission snapshots.

    Also in 8 projects that use this

  • kennethleungtySkill

    pause

    Pause — stop the music (alias for /stop)

    Also in 7 projects that use this

  • MistralSkill

    import

    Import the user's setup from other coding CLIs (Claude Code, Codex, OpenCode) into Vibe — instructions, skills, subagents, commands, hooks, MCP servers, permissions, and plugins. Load when the user wants to switch to Vibe, import or reuse another CLI's configuration, or asks whether a file from another CLI works in Vibe.

    Also in 6 projects that use this

  • codebycoreySkill

    new

    Start a new change with a proposal. Use when starting a feature, creating a proposal, or beginning planned work.

    Also in 7 projects that use this

  • VercelSkill

    next

    Next.js renderer for json-render that turns JSON specs into full Next.js applications with routes, layouts, SSR, and metadata. Use when working with @json-render/next, building Next.js apps from JSON specs, or creating AI-generated multi-page applications.

    Also in 11 projects that use this

The file

Files
SKILL.md

/status — pipeline funnel report

Run:

uv run python -m pipeline status

This prints counts per status (new / enriched / scored / qualified / disqualified / contacts_found), the most recent qualified companies with total scores, and the last few runs.

Then summarize for the user:

  • Funnel shape and where the bottleneck is (e.g., "42 enriched but only 5 scored → run /score next").
  • Any recently qualified companies worth attention (name, ticker, score, top service fit).
  • Suggest the single next command.
  • The review band (status scored: total between disqualify_below and qualify_threshold) is a human decision queue — when it's non-empty, list its companies with scores and ask whether any should be promoted.
  • Promote review-band companies the user approves with uv run python -m pipeline promote TICK1,TICK2 (this is the human review-band decision — never promote without the user saying so).

Failure modes:

  • Missing SUPABASE_URL → .env not configured; point the user at .env.example.
  • Connection errors → Supabase project paused or wrong key; ask user to check dashboard.

Outcome analytics (v3 phase 4)

uv run python -m pipeline status --analytics adds funnel conversion (rate vs previous stage), avg time-in-stage (labelled approximate for rows predating companies.status_changed_at), and — once outcomes have been recorded — a sent → replied → positive_reply → meeting funnel with a benchmark-band callout on positive reply rate (the north star metric), plus attribution tables by archetype / angle family / service. Every section guards against thin samples by printing "insufficient data" below analytics.min_sends_for_attribution sends, and degrades cleanly (same PGRST205 pattern as the tier breakdown) on a database that hasn't run apply-schema for this feature yet.

Outcomes get recorded with uv run python -m pipeline outcome <message_id> --event replied [--date YYYY-MM-DD] [--note "..."] (events: approved/rejected/exported/sent/bounced/replied/positive_reply/meeting/opt_out; append-only — status only ever advances forward, never backward, and never past a terminal state like bounced/opted_out). Use --csv path for batch imports (columns message_id,event,date,note), or --ticker X --contact "name" as a fuzzy lookup when the message_id isn't on hand — ambiguous matches print candidates and exit nonzero rather than guessing.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.