agentleFS
sumeetkbhardwajsumeetkbhardwaj/small-trading-indian-stock-market-survival-kit/skills/opportunity-screen/SKILL.md

opportunity-screen

Skill0 starsChanged 4 months agoMITView on GitHub

Screen a universe of NSE/BSE stocks through the survival-first gates and return only the few that pass, each with a ready signal (entry/stop/size/target/break-even) and — where the surface supports it — a beautiful report Artifact. Use for pre-market idea generation, watchlist review, or "find me something worth looking at". Broker-agnostic, read-only, advisory only.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. frankxai/geninvestor-skills★ 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

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    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. Distinctive:

    Default output is no candidate.

    line 8
  2. Very specific:

    Never invent a price, a fill, or a fundamental figure.

    line 26
  3. Distinctive:

    Never place or suggest placing an order.

    line 27

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “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

Opportunity Screen (survival-first)

Default output is no candidate. A stock earns a place on the shortlist only by passing every gate below, in order. Reject ~95% — that emerges from the stacked setup gates, not a quota.

Run the deterministic gate — capability resolver (never compute the numbers in prose)

  1. A Gate MCP tool connected → call it.
  2. Else code execution available → python3 "${CLAUDE_PLUGIN_ROOT}/scripts/kit.py" evaluate (candidate JSON on stdin).
  3. Else plain chat → route each candidate's math through the JS-paise gate Artifact.
  4. Else REFUSE to fabricate — state the gate could not run and return no shortlist.

Procedure

  1. Universe & data. Use india-data (broker-agnostic: free-web delayed [screener + Yahoo] + manual-paste baseline; broker MCP optional read-only enrichment) for OHLCV + last close over the universe (default: user's watchlist, else Nifty 500). Stamp every reading {value, source, as_of, delay_class}. If required data is missing/stale for a name → drop it (STAND DOWN on that name); never guess.
  2. Regime gate. Index trend (Nifty vs 50/200 DMA), breadth, India VIX. Risk-off (index < 200 DMA) → say so and return an empty shortlist unless the user overrides; surface an explicit raise-cash / stand-down read.
  3. Exclusion kill-filter FIRST. Drop any name in GSM/ASM/ESM/T2T, tight circuit band, or an F&O-ban underlying (crowding caution). Drop names below the liquidity floor.
  4. Fundamental red-flags. Promoter pledge, OCF/PAT, auditor/rating flags (from india-data/screener). Exclude on a hard red flag.
  5. Technical setup. Rank by 6m+12m relative strength; keep only Trend-Template survivors near a valid pivot (within ~5% — never chase an extended breakout).
  6. Cost/size/exit/2R gate. For each survivor build the evaluate JSON (incl. targets) and run the gate via the resolver. Keep only decision == long, shares > 0, with a ≥2R target.
  7. Output. For each survivor: symbol · entry · stop · shares · target(≥2R) · statutory break-even · the dominant reason it passed, plus its exit contract (stop/R-target/trailing rule). If the surface supports Artifacts, render a beautiful report Artifact (shortlist table + per-name reasons); otherwise a concise text digest. If none pass: "No trade — here is the gate that eliminated the most names." Append the disclaimer.

Never

  • Never invent a price, a fill, or a fundamental figure; cite {source, as_of, delay_class} for every number and never compute the gate numbers yourself.
  • Never place or suggest placing an order. Read-only.

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.