sector-rotation
Skill2 starsChanged 5 months agoMITView on GitHub
Run a Renaissance-style sector rotation and pattern analysis. Use when the user asks about sector trends, "what sectors should I overweight?", money flows, sector leadership, or institutional positioning.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- Weaxs/stock-analysis-plugintheir own version, first seen Nov 15, 2026
- Shubhamkumartrichy/claude-trading-skills-indiatheir own version, first seen Nov 1, 2026
- awslabs/agentcore-samplestheir own version, first seen Oct 13, 2026
- awslabs/amazon-bedrock-agentcore-samplestheir own version, first seen Oct 8, 2026
- IngAs8/ClaudeSkilltheir own version, first seen Sep 28, 2026
- SKE-Labs/agent-trading-skillstheir own version, first seen Jul 18, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- awslabs/amazon-bedrock-agentcore-samples★ 3.5ksame name
- awslabs/agentcore-samples★ 3.5ksame name
- Weaxs/stock-analysis-plugin★ 95same name
- Shubhamkumartrichy/claude-trading-skills-india★ 64same name
- SKE-Labs/agent-trading-skills★ 17same name
- IngAs8/ClaudeSkill★ 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 repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- adversarial-researchSkill
- auto-rebalanceSkill
- cash-deploymentSkill
- daily-briefingSkill
- dividend-strategySkill
- earnings-analyzerSkill
- earnings-postmortemSkill
- employer-stockSkill
- health-checkSkill
- macro-impactSkill
- momentum-scannerSkill
- optimize-allocationSkill
- pead-trackerSkill
- perf-optimizerSkill
- portfolio-healthSkill
- portfolio-reviewSkill
- position-reviewSkill
- pre-trade-checkSkill
- profile-setupSkill
- risk-assessmentSkill
- stock-analysisSkill
- stock-compareSkill
- tax-loss-reviewSkill
- top-trades-todaySkill
- trade-journalSkill
- trading-deskSkill
- weekly-mirrorSkill
The file
We split this skill into the rules it gives an agent
8 rules. 0 are common, 2 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 18
Call mcp__aifolimizer__get_profile - account types and capital.
- Very specific: line 19
Call mcp__aifolimizer__get_portfolio - current sector exposure
- Very specific: line 20
Call mcp__aifolimizer__get_xray - true sector + geographic exposure after ETF expansion
- Very specific: line 21
Call mcp__aifolimizer__get_market_breadth - VIX, SPY regime (bull/bear vs SMA200).
- Very specific: line 22
Call mcp__aifolimizer__get_factor_snapshot - Fama-French factor leadership.
- Very specific: line 44
Crowding gate on add candidates: - before naming anything to add, call mcp__aifolimizer__get_positioning_signals (symbols=[add candidates]).
- Distinctive: line 51
Use live data via WebSearch - sector rotation is time-sensitive
- Distinctive: line 60
Don't confuse sector ETF performance with underlying sector - track index, not just ETF, when comparing.
“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
Sector Rotation Detector (Renaissance + quantitative style)
Decision Memory Protocol (load first, log after)
Before forming any view, load prior decisions so verdicts stay consistent across sessions:
mcp__aifolimizer__get_cross_ticker_lessons(max_lessons=3) - portfolio-level win/loss patterns- For any name you issue a per-ticker BUY/SELL/TRIM/HOLD/ADD on, also load
mcp__aifolimizer__get_ticker_decision_history(ticker=…, max_decisions=5) andmcp__aifolimizer__get_ticker_reflection(symbol=…, n=3). If a prior decision exists and this run flips it, state explicitly WHY (new data / catalyst / price); never silently contradict a logged decision.
After output, log every actionable verdict: for each BUY/SELL/TRIM/ADD/HOLD issued, call mcp__aifolimizer__log_recommendation (skill="sector-rotation", ticker, action, conviction, rationale, target_pct, stop_pct). Skipping breaks the cross-session feedback loop and causes drift.
How to run
- Call
mcp__aifolimizer__get_profile- account types and capital. Rotation trades in TFSA tax-free; non-reg triggers capital gains - Call
mcp__aifolimizer__get_portfolio- current sector exposure - Call
mcp__aifolimizer__get_xray- true sector + geographic exposure after ETF expansion - Call
mcp__aifolimizer__get_market_breadth- VIX, SPY regime (bull/bear vs SMA200). Usemarket_regimeto calibrate rotation conviction: bull_low_fear = high conviction; bear_high_fear = defensive only - Call
mcp__aifolimizer__get_factor_snapshot- Fama-French factor leadership. Factor rotation drives sector rotation: value leading → financials/energy/industrials; growth/momentum leading → tech/discretionary; quality (RMW) leading → defensives/staples - WebSearch for: 30-day S&P 500 and TSX sector performance, relative strength rotations, ETF money flows, recent 13F filings (Berkshire, Renaissance, Bridgewater)
- Identify rotations and translate to actions for user's portfolio
Investor profile
- Canadian retail investor
- Account types and capital: always read from
get_profile- never hardcode - Equities, ETFs, crypto exposure
- Wants to spot institutional moves before they're obvious
Output structure
- Current economic cycle phase (expansion / peak / contraction / trough) and implied sector leadership
- Last 30 days: sectors flipping from negative to positive relative strength
- Sectors losing vs gaining momentum - cite specific data signals
- Highest-conviction rotation trade right now: overweight X, reduce Y
- 3 ETFs (Canadian or US listed) to express rotation - with tickers
- Seasonal patterns - which months favour rotating-into sectors
- Unusual money flows - signals of institutional accumulation in quiet sectors
- Institutional footprint - sectors with rising 13F ownership
- Impact on user's portfolio - which existing holdings benefit/at risk
- Crowding gate on add candidates - before naming anything to add, call
mcp__aifolimizer__get_positioning_signals(symbols=[add candidates]). Defer adds wherecrowding_score >= 70(consensus-crowded → negative expected alpha); favor names<= 30(contrarian edge) - Recommended adjustment - specific tickers to add/trim
Rules
- Quantitative research memo format with sector scorecard table
- Under 500 words
- Use live data via WebSearch - sector rotation is time-sensitive
Gotchas
get_xrayETF expansion is static sector mapping - not live ETF holdings. Use for "true sector tilt" approximation, NOT precise weight claims.get_market_breadthcached - verify with WebSearch on volatile days before sizing rotation trade.- 13F filings lag 45 days - never present 13F-derived positioning as "current".
- Rotation trades in non-reg trigger capital gains; in TFSA tax-free - always pair recommendation with right account.
- Seasonal patterns are statistical priors, NOT predictions - present as base rate, not directive.
- Don't confuse sector ETF performance with underlying sector - track index, not just ETF, when comparing.
get_factor_snapshottrailing-252d shows the established regime; latest-daily is noise. Cite the trailing window for rotation direction, not one day.
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.

