srinandansrinandan/portfolio-copilot/skills/suitability/SKILL.md

suitability

Skill0 starsChanged 4 months agoApache-2.0View on GitHub

Combines a standalone equity assessment with the user's Investment Policy Statement, holdings, and allocation drift to produce an advisory buy / add / hold / trim / avoid recommendation for a specific stock. Advisory only — it never drafts or executes a trade, and is not investment advice.

In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- action-draftingSkill
- equity-researchSkill
- goals-onboardingSkill
- portfolio-analysisSkill
- researchSkill
- reviewerSkill
- spending-analysisSkill

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
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

Very specific:
After equity-research, when the user asked whether a specific ticker is worth buying or selling.
line 30

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

suitability

Purpose

Answers the personalization half of "should I buy/sell this stock?": given the security-only EquityAssessment from equity-research, is this name right for this user? It produces an advisory EquityRecommendation — a buy / add / hold / trim / avoid lean with conviction, transparent suitability factors, risks, and disclaimers.

Advisory only. This skill does not draft a ProposedAction and does not execute anything; the user decides, and any actual order still goes through action-drafting → reviewer → the human approval gate.

When this skill runs

After equity-research, when the user asked whether a specific ticker is worth buying or selling. The planner orders equity-research → suitability.

Deterministic core + advisory narrative

Per the reviewer pattern (ADR-0014), the direction and conviction are decided by deterministic rules in primitives/suitability.py; the LLM layer only explains them. Decision order (first applicable wins):

Excluded by IPS → avoid
Overvalued → trim if held, else avoid
Undervalued + room (under the concentration limit and the asset-class band has room) → add if held, else buy
Undervalued + no room (at the concentration limit or the sleeve is full) → hold
Fairly valued → hold
Unknown (valuation could not be computed) → hold, low conviction

Conviction is capped for conservative risk tolerance on a buy/add, and raised only for aggressive tolerance with strong upside into an under-allocated sleeve.

Inputs

Field	Source	Required
`EquityAssessment`	`equity-research` (transient, this cycle)	Yes
Active `InvestmentPolicyStatement`	Firestore, read-only (risk tolerance, concentration limit, excluded tickers, target bands)	Yes
`HoldingsSnapshot`	Firestore, read-only (current position + weight)	Yes
`DriftReport`	`portfolio-analysis` (allocation room), optional	Recommended
`UserProfile`	Firestore, read-only (goals/risk notes for narrative), optional	No

Data access scope: read:ips, read:holdings.

Output: EquityRecommendation

Transient (not persisted). Key fields: direction, conviction, rationale, valuation_verdict + upside_pct (carried from the assessment), already_held, current_weight_pct / concentration_limit_pct / headroom_pct, suitability_factors[], key_risks[], and disclaimers[] (always present).

Failure modes

No active IPS → cannot judge suitability; decline rather than assuming a policy (consistent with portfolio-analysis).
unknown valuation verdict → returns hold at low conviction and says so; it never manufactures a lean from missing data.

Registry metadata

Registered as: projects/{project}/locations/{location}/skills/private-suitability
Skill revision: 0.1.0 (draft — not yet registered)
Approval scope: read:ips,read:holdings

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.

Check your setup, free