AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Prospect Scoring

skill-xuxchloris-hermes-export-skills-prospect-scoring · by Xuxchloris

Use when a trade agent needs to rank, qualify, prioritize, segment, score, or reject overseas prospects based on product fit, channel value, decision-maker access, market relevance, and risk

↗ Repository
— No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-xuxchloris-hermes-export-skills-prospect-scoring

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Prospect Scoring? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Prospect Scoring

Overview

Score prospects with transparent evidence so the user knows who to contact first. The score is a decision aid, not a claim that the prospect is ready to buy.

When to Use

Use this skill after company-research has produced facts and evidence for a prospect, or when the user uploads a prospect list and asks which companies deserve outreach.

Do not use it when there is no product context.

Inputs

  • Product context from product-loader
  • Company research output
  • Target market rules from MARKET.yaml
  • Optional contact availability data

Outputs

{
  "score": 0,
  "priority": "A|B|C|D",
  "score_breakdown": {},
  "recommended_action": "",
  "evidence_status": "verified|no_evidence|fetch_failed",
  "reason": "",
  "evidence": [],
  "risk_notes": []
}

Procedure

  1. Score product and category fit from 0 to 40.
  2. Score channel value from 0 to 20.
  3. Score decision-maker access from 0 to 15.
  4. Score target-market value from 0 to 10.
  5. Score website quality and business activity from 0 to 10.
  6. Apply risk adjustment from 0 to -10 for weak evidence, unrelated business, suspicious contact data, or compliance concerns.
  7. If evidence status is fetch_failed or no_evidence, cap priority at D and set recommended_action to manual_review.
  8. If no product or channel evidence was fetched, do not assign A or B even when the market is relevant.
  9. Assign priority:
  • A: 80-100, contact first
  • B: 60-79, contact after manual review
  • C: 40-59, keep for monitoring or enrichment
  • D: 0-39, do not contact
  1. Provide a recommended next action.

Verification

  • Score breakdown totals equal final score.
  • Priority matches the score range.
  • A or B priority requires fetched evidence for product or channel fit.
  • A-level prospects include at least two evidence points.
  • D-level prospects are not recommended for outreach.
  • Risk notes explain every deduction.

Common Mistakes

| Mistake | Fix | | --- | --- | | Giving high score because the company is large | Product fit must carry the most weight | | Ignoring missing decision-maker data | Reflect it in the access score | | Hiding risk deductions | List each risk note | | Treating score as purchase intent | Explain that score means development priority |

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Communication