market-scan
Skill1 starsChanged 3 months agoMITView on GitHub
Analyze the US market regime, breadth, sector or industry strength, leadership, stock discovery, screening results, and watchlist candidates. Use whenever the user asks how the market is, which areas are strong, what tickers look promising, or to build or refresh a watchlist, even if Minervini is not named. Do not use for a buy, sell, hold, entry condition, or diagnosis judgment about one or a few named tickers; use ticker-analysis. Crypto, non-US listings, completed-trade grading, account-level position sizing, and capital allocation advice are outside scope.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- TrueScrape/truescrapetheir own version, first seen Nov 8, 2026
- Latifox/find-me-saastheir own version, first seen Sep 6, 2026
- AIDevGTM/gtm-cofoundertheir own version, first seen Aug 17, 2026
- Lengros/bennutheir own version, first seen Jul 8, 2026
- InfiniteRoomLabs/agent-opstheir own version, first seen Jun 23, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- AIDevGTM/gtm-cofounder★ 340same name
- Latifox/find-me-saas★ 10same name
- Lengros/bennu★ 2same name
- InfiniteRoomLabs/agent-ops★ 1same name
- TrueScrape/truescrape★ 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 repository3 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ticker-analysisSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 9 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
9
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
- Very specific: line 11
Use doctrine list --context <ctx> to discover the claims an analysis context rests on, then doctrine show <id> to read one.
- Distinctive: line 17
Start with the market snapshot appropriate to the user's as-of request.
- Distinctive: line 20
Read persistent overbought action with shallow pullbacks as possible lockout demand, not an automatic sell signal.
- Distinctive: line 21
If the environment is hostile or evidence is materially incomplete, reduce the discovery depth and return watch-only conditions.
- Distinctive: line 25
Use provider-ranked sectors, industries, and leading stocks as observations, not as a weighted master score.
- Distinctive: line 27
Use same-industry peer comparison on promising leaders to establish current classification, stable identity, and relative leadership.
- Distinctive: line 28
Treat the candidate-universe capability as scope and pagination, not an automatic recommendation engine.
- Distinctive: line 29
Keep the set small enough to investigate well.
- Distinctive: line 33
Run technical qualification before setup, fundamentals, narrative research, or recommendation language.
- Distinctive: line 43
When no candidate earns recommendation, say so plainly.
“Common” is measured: kept by at least 6 in 10 of the 5 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.
Files
Market scan
Orient through the interface
- Use
doctrine list --context <ctx>to discover the claims an analysis context rests on, thendoctrine show <id>to read one. - Work from the repository root; the root constitution holds the bootstrap and capability-catalog commands. Before invoking a capability for the first time, read only its
describeoutput or that leaf command's--help. - Compose calls around unresolved evidence. Do not execute every capability, preload all help, or force a fixed screening rail.
Establish the environment
- Start with the market snapshot appropriate to the user's as-of request. Treat each source and breadth section independently; a composite response can be usable while one section is unavailable.
- Actual trade traction is a separate bottom-up gate. Without the user's own recent pilot, breakout, or stop-out feedback, preserve
needs_inputrather than promoting QQQ or breadth alone to a favorable regime. - QQQ versus 21 EMA is environmental context only. Leaders and real trade behavior decide whether apparent strength has earned confidence.
- Read persistent overbought action with shallow pullbacks as possible lockout demand, not an automatic sell signal. Also surface leader/index divergence and the evidence that would refute the regime read.
- If the environment is hostile or evidence is materially incomplete, reduce the discovery depth and return watch-only conditions. Sparse qualified leadership is itself evidence; never loosen hard gates to fill a list.
Find leaders without manufacturing a score
- Use provider-ranked sectors, industries, and leading stocks as observations, not as a weighted master score.
- Preserve each candidate's discovery origin. Repeated appearance across independent evidence is useful context but cannot erase a failed gate.
- Use same-industry peer comparison on promising leaders to establish current classification, stable identity, and relative leadership.
- Treat the candidate-universe capability as scope and pagination, not an automatic recommendation engine.
- Keep the set small enough to investigate well. When independent qualification calls can run concurrently, parallelize them adaptively; do not depend on a fixed agent, workflow, batch size, or quota.
Make every candidate earn depth
- Run technical qualification before setup, fundamentals, narrative research, or recommendation language.
- For finalists that pass qualification, collect only the setup, filed fundamentals, peer, chart, and risk evidence needed by the user's question.
- Discovery language stops at ranked leader, watch candidate, and setup-ready. The final verdict comes from the risk reducer, never from a strong screen.
Synthesize
Lead with the completed US session, evidence quality, and the regime state. Then report leading sectors and industries with the supporting vector rather than a naked rank.
For each candidate, show ticker, current industry identity, discovery origin, eligibility state, exact failed or missing gates, why it merits attention, and the observable condition for promotion or removal.
When no candidate earns recommendation, say so plainly. Cash and an empty high-quality list are valid outcomes.
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.

