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

enrich

Skill0 starsChanged 4 months agoMITView on GitHub

Run signal collectors (SEC EDGAR filings analysis + Parallel.ai web research) for companies in the pipeline. Use after ingest/discover, or when asked to "run signals" for companies.

6 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup.

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.
  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. garrytan/gbrain★ 33ksame name
    2. baojie/shiji-kb★ 3.4ksame name
    3. ZimoLiao/scholaraio★ 589same name
    4. iliasedelkin/jobissimo★ 8same name
    5. omesiri/claude-skills★ 0same name
    6. opendatadiscovery/odd-team★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    After running: show a compact table (ticker → signals found, strongest signal, evidence snippet), note failures, suggest /score when a …

    line 35
  2. Distinctive:

    Run after scoring for companies at/near the qualify bar — before outreach.

    line 39

“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

/enrich — collect signals

EDGAR signals (free, run first):

uv run python -m pipeline enrich --source edgar --limit 10

Parallel web signals (paid per task — capped by config enrich.parallel.max_tasks_per_run):

uv run python -m pipeline enrich --source parallel --limit 10

Both: --source all. Single company (works even before it's in the DB): --ticker XYZ. Preview with --dry-run — for Parallel this lists which companies WOULD get a task and never spends. Re-enrich already-enriched companies: --force.

What gets collected (details in docs/SIGNALS.md):

  • EDGAR E1–E9: AI-mention analysis in 10-K/10-Q (strategy vs risk-factor placement, YoY delta), 8-K exec changes and restructuring, S&M-spend efficiency from XBRL, tech-leadership gap from proxy, recent-IPO flag, cash capacity.
  • Parallel P1–P6: AI job postings, SDR/marketing hiring, AI announcements, product AI gap, martech stack, exec AI commentary — one structured research task per company.

Ground rules:

  • EDGAR before Parallel (free before paid); don't run Parallel on companies the user hasn't asked to prioritize unless batch is small.
  • Respect the config caps; never loop Parallel calls around them.
  • One company failing must not stop the batch — failures are logged per company; report them at the end. A failed/timed-out Parallel task keeps the company's previous parallel signals; retry it alone with --ticker X --source parallel --force.
  • Run multi-company batches in the background (Bash run_in_background) and report from the final Done: {...} stats line plus DB counts — don't stream dozens of per-company tables into the conversation.
  • Timing: Parallel tasks are created up front and polled together, so a full 25-company batch ≈ its slowest single task (~3–5 min). EDGAR batches run at SEC-polite rates — 8-Ks are filtered by index metadata, so expect seconds per company plus 10-K parsing.

After running: show a compact table (ticker → signals found, strongest signal, evidence snippet), note failures, suggest /score when a decent batch is enriched.

Deep tier

Run after scoring for companies at/near the qualify bar — before outreach.

uv run python -m pipeline enrich --source deep --dry-run   # see which companies qualify
uv run python -m pipeline enrich --source deep --limit 15  # capped, paid batch

Deep tier creates one richer Parallel task per company (e.g., executive moves, AI investment patterns) plus a free EDGAR scan for funding events, refreshing the company's P1–P6 parallel signals and additionally producing structured outreach-angle rows (funding raises, leadership hires, AI moves).

Ground rules:

  • Always --dry-run first to preview which companies will be selected (filtered by status + score + freshness).
  • Cap is strict: enrich.deep.max_tasks_per_run (default 15). Never loop around it.
  • Results feed the /score rescoring step: score --prepare --statuses scored (review band) before re-running the subagent.

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.