portfolio-health
Skill2 starsChanged 5 months agoMITView on GitHub
Run a BlackRock-style portfolio health analysis. Use when the user asks about portfolio health, allocation review, rebalancing, or asks "how is my portfolio doing?". Produces a point-in-time health snapshot (scores + flags), NOT a per-name decision table (use portfolio-review for that).
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-reviewSkill
- position-reviewSkill
- pre-trade-checkSkill
- profile-setupSkill
- risk-assessmentSkill
- sector-rotationSkill
- 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. About 0 are common, 3 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
5
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 - learn user's account types (TFSA, RRSP, etc.)
- Very specific: line 19
Call mcp__aifolimizer__get_personal_context - this report's age-based allocation targets and tax tips need province, marginal_tax_rate_pct, …
- Very specific: line 20
Call mcp__aifolimizer__get_portfolio - fetch enriched holdings
- Very specific: line 21
Call mcp__aifolimizer__get_xray - true geographic/asset-class exposure (expands ETF holdings)
- Very specific: line 22
Call mcp__aifolimizer__get_concentration_warnings - flag over-allocations
- Distinctive: line 23
Run analysis below using returned data
- Distinctive: line 48
Use actual ticker symbols and weights from returned data
- Distinctive: line 49
Never reference account IDs, names, or PII (MCP returns filtered data only)
≈ “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.
Files
Portfolio Health Analysis (BlackRock 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="portfolio-health", 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- learn user's account types (TFSA, RRSP, etc.) - Call
mcp__aifolimizer__get_personal_context- this report's age-based allocation targets and tax tips need province, marginal_tax_rate_pct, age, and goals, whichget_profiledoes not carry. Ifpresent=false, fall back to generic targets and suggest the user run theprofile-setupskill. - Call
mcp__aifolimizer__get_portfolio- fetch enriched holdings - Call
mcp__aifolimizer__get_xray- true geographic/asset-class exposure (expands ETF holdings) - Call
mcp__aifolimizer__get_concentration_warnings- flag over-allocations - Run analysis below using returned data
Investor profile
- Canadian retail investor
- Philosophy: growth stocks, index ETFs, dividends, crypto exposure
- Risk profiles: conservative, moderate, aggressive (across different accounts)
- Time horizons: day trading, short-term <3yr, long-term 10yr+
- Account types and capital: always read from
get_profile- never hardcode - Tax: TFSA gains tax-free; RRSP tax-deferred; non-reg has 50% capital gains inclusion
Output structure
BlackRock Portfolio Builder report with these sections:
- Portfolio Health Score (0-100) with one-paragraph rationale
- Asset allocation breakdown vs targets for this investor's age and goals
- Top 3 concentration or risk concerns - name specific tickers/sectors
- 3-5 actionable rebalancing recommendations with tickers and reasoning. Before issuing any ADD, call
mcp__aifolimizer__get_positioning_signalson those names and gate on crowding: defer the ADD ifcrowding_score >= 70(consensus-crowded, negative expected alpha), favor it wherecrowding_score <= 30(contrarian edge) and fundamentals support. - Canadian tax-efficiency tip based on actual account types from
get_profile - Expected return range (annualized) and maximum drawdown estimate for current allocation
Rules
- Under 500 words
- Use actual ticker symbols and weights from returned data
- Never reference account IDs, names, or PII (MCP returns filtered data only)
- Direct and specific - no hedging
- Keep-what-works: before recommending a trim/sell, check whether the position is best LEFT ALONE (large embedded gain in a Non-Reg account, safe growing dividend, core index ETF doing its job). Overtrading erodes long-term returns - the bar to touch a working position is high. For the full leave-alone discipline + whole-book decision table, defer to the
portfolio-reviewskill.
Gotchas
get_xrayETF expansion is mapping-based, not live holdings - exotic/new ETFs may fall back to single-asset weight. Flag when unknown.get_concentration_warningsonly fires on threshold breaches; do NOT skip narrative concentration analysis because tool returned no warnings.- Health score is heuristic, not backtest - never present as return forecast.
- Allocation targets must reference user's actual age + risk tier from
get_profile; do not paste generic 60/40 template.
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.

