How do I install the Suitability skill?

Run npx skillmds@latest add srinandan/suitability in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Suitability safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Suitability?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Suitability free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Suitability?

srinandan (@srinandan) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Suitability by srinandan — Agent Skill

Name: Suitability
Author: srinandan

Suitability

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.

srinandan 0296a8c 3 files · 8.6 KB Updated Sep 17, 2026

File contents

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

---name: suitabilitydescription: 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.---# suitability## PurposeAnswers the *personalization* half of "should I buy/sell this stock?": given thesecurity-only [`EquityAssessment`](../../orchestrator/src/orchestrator/contracts/equity_assessment.py)from `equity-research`, is this name right **for this user**? It produces anadvisory [`EquityRecommendation`](../../orchestrator/src/orchestrator/contracts/equity_recommendation.py)— a `buy` / `add` / `hold` / `trim` / `avoid` lean with conviction, transparentsuitability factors, risks, and disclaimers.**Advisory only.** This skill does not draft a `ProposedAction` and does notexecute 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 narrativePer the reviewer pattern (ADR-0014), the direction and conviction are decided bydeterministic rules in `primitives/suitability.py`; the LLM layer only explainsthem. Decision order (first applicable wins):1. **Excluded by IPS** → `avoid`2. **Overvalued** → `trim` if held, else `avoid`3. **Undervalued + room** (under the concentration limit and the asset-class band has room) → `add` if held, else `buy`4. **Undervalued + no room** (at the concentration limit or the sleeve is full) → `hold`5. **Fairly valued** → `hold`6. **Unknown** (valuation could not be computed) → `hold`, low convictionConviction is capped for `conservative` risk tolerance on a buy/add, and raisedonly 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: EquityRecommendationTransient (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`

Frequently asked questions