opportunity-screen
Skill0 starsChanged 12 days agoApache-2.0View on GitHub
Turn the owner's own written mandate into a short list of candidates worth researching, each with the case against it. Use when asked to find ideas, run a screen, or see what looks interesting.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- sumeetkbhardwaj/small-trading-indian-stock-market-survival-kittheir own version, first seen Jul 16, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
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 repository3 other files it gives its agents.
- calibration-logSkill
- source-checkSkill
- thesis-trackerSkill
The file
We split this skill into the rules it gives an agent
5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 19
Use the data and tools available.
- Distinctive: line 60
Never say buy, sell, trim, exit or hold, and never present a price target as a fact.
- Distinctive: line 62
Do not use hype words: no "top pick", "undervalued gem", "can't miss".
- Distinctive: line 63
Every number has a source and an as-of date.
- Distinctive: line 64
Check crowding where the data exists: analyst coverage, ownership concentration, short interest.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Opportunity screen
A screen surfaces candidates for research. It does not reach conclusions. This skill searches against the owner's own rules, cuts hard, and hands back a few candidates with the strongest argument against each.
Workflow
1. Read the mandate
A written mandate is required: markets, horizon, risk tolerance, exclusions, concentration limits, and the styles wanted (value, quality, growth, special situation, insider activity). If none exists, ask for one or stop. Do not invent a mandate.
2. Choose screens and write down their parameters
State each criterion and threshold. Record the date, the universe and the data sources so the screen can be run again and give the same answer.
3. Run the screens
Use the data and tools available. Note the source and as-of date of everything the screen relies on, and flag anything delayed or missing.
4. Cut hard
Drop anything that breaks an exclusion, is too illiquid for the mandate, rests on stale data, or duplicates something already seen. Keep at most five.
5. Write a card for each candidate
- Name and identifier.
- Three lines on why it passed the screen.
- The evidence, each figure with its source and as-of date.
- What would prove it wrong: measurable kill criteria.
- The case against: the strongest skeptical argument, with evidence.
- Risks, including liquidity and data gaps.
- How it fits or conflicts with the mandate, including concentration.
- What to check next.
6. Say what the screen cannot see
Accounting quality, management, legal exposure, anything the data does not capture.
Output
## Screen record
Mandate version: <id/date> · Universe: <...> · Run: <date> · Sources: <...>
Criteria: <list with thresholds>
## Candidates (for research, not recommendations)
### <Name> (<identifier>)
**Why it passed:** ...
**Evidence:** | claim | value | source | as of |
**Would prove it wrong:** ...
**Case against:** ...
**Risks:** ...
**Fit with mandate:** ...
**Check next:** ...
## Not visible to this screen
...Rules
- Never say buy, sell, trim, exit or hold, and never present a price target as a fact. Cards are candidates for research.
- Rank by fit with the mandate and strength of evidence, never by expected return.
- Do not use hype words: no "top pick", "undervalued gem", "can't miss".
- Every number has a source and an as-of date. Delayed data is labelled as delayed.
- Check crowding where the data exists: analyst coverage, ownership concentration, short interest.
- Five candidates is a ceiling, not a target. Fewer is fine. Zero is a valid result.
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.

