prospect-research

prospect-research is a skill for Claude Code from stefanoskarakasis/Product-Marketing-Skills. It costs 170 tokens per session (1,844 once invoked), scanned A, original, MIT.

A research workflow for preparing a dated brief on one company that is not yet a customer. It combines web search, customer records and connected company data, then suggests a possible problem, approach and opening question.

In plain words
What is it for?
Use it to decide whether one named company is worth contacting, check what has changed since an earlier brief, and record the outcome of the conversation.
Why use it?
It avoids contacting a company without a clear reason and keeps facts, assumptions and uncertainty together. It also avoids drafting or sending outreach.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the pmm-sales plugin — 3 skills, 3 commands shipped together

Good fit Use it to decide whether one named company is worth contacting, check what has changed since an earlier brief, and record the outcome of the conversation.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/stefanoskarakasis/product-marketing-skills/prospect-research
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add stefanoskarakasis/Product-Marketing-Skills --skill prospect-research
Clone the repo
git clone --depth 1 https://github.com/stefanoskarakasis/Product-Marketing-Skills

Made for: Claude Code.

Or install pmm-sales, the plugin that ships this one along with the rest of its 3 skills, 3 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for prospect-research

README.md
[![agentmods](https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/prospect-research/github.svg)](https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/prospect-research)
Your own site
<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/prospect-research"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/prospect-research/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for prospect-research

Your own site · 80×15
<a href="https://agentmods.dev/skills/stefanoskarakasis/product-marketing-skills/prospect-research"><img src="https://agentmods.dev/badge/skills/stefanoskarakasis/product-marketing-skills/prospect-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 170 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,844 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00170 $0.01844
Opus 5.5 $0.00068 $0.00738
Sonnet 5.5 $0.00034 $0.00369
Haiku 4.5 $0.00017 $0.00184

Measured today against content hash 5fd8919fc626, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

prospect-research scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

pmm-sales/skills/prospect-research/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prospect Research

A seller needs a reason to write, a first question that tests it, and a verdict on whether to bother. This skill keeps only the signals that map to a pain your brain says you solve and turns them into one hypothesis. It never drafts or sends outreach. What it learns goes back to the PMM as proposals, never silent writes.

Trigger

  • When: Someone is about to reach out to one named non-customer company, or asks in a Slack thread.
  • Not for: A customer → customer-context. A competitor → competitive-profile. A competitor in a live deal → competitive-battlecard. Writing the message → writing-assistant. The deal committee → buyer-personas or stakeholder-maps. A ranked account list → not in this plugin.
  • Examples: "@Claude research Lumio Logistics before I reach out" (Slack) · "Is there a reason to contact Lumio now?" (ask) · "What changed at Lumio since my last brief?" (since)

Inputs

  • Args: company name or domain; optionally the role you will contact; mode brief (default), since or ask (one question, thread-sized). A line starting log: records an outcome.
  • Depth: quick (default) or deep (adds Step 6). The request beats _config.md.
  • Context keys: the brain; /context/prospects/; other skills' ledgers read-only (references/learn-from.md); ~~ connectors (references/connectors.md).
  • Brain contract: Reads Section 1 (claims), Section 2 (pains, triggers, anti_persona, geography, committee_roles, size, industry), Section 3 (alternatives, status_quo), Section 5, Section 6 (proof, forbidden_claims), Section 8 (prohibited, approvals). Never writes the brain; learnings are proposals (references/feed-forward.md).

Connectors (Optional)

Categories: references/connectors.md. Rules on sources, links, untrusted text, people data: references/rules.md. No connectors: web search and pasted notes give the same shape. Pulled facts are drafts, tagged with category, tool and date.

Read the full file on GitHub · 93 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today First seen · 93 lines · 170 tokens per session scan A 5fd8919fc626

Subscribe to this mod's changes

prospect-research is a skill published in the GitHub repository stefanoskarakasis/Product-Marketing-Skills (9 stars, last pushed yesterday), licensed MIT. It adds 170 tokens to every session and 1,844 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-07.

Related

prospect-research compared with skills from other repositories

prospect-research next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
prospect-researchstefanoskarakasis/Product-Marketing-SkillsSkill9yesterdayMITA170Claude Code
reportsmk-labs/claude-pluginsSkill111mo agoMITA57Claude Code
k8s-rightsizesmk-labs/claude-pluginsSkill111mo agoMITA62Claude Code
owasp-securitysmk-labs/claude-pluginsSkill111mo agoMITA72Claude Code
figsmk-labs/claude-pluginsSkill111mo agoMITA45Claude Code
brandsmk-labs/claude-pluginsSkill111mo agoMITA64Claude Code
workspace-rulessmk-labs/claude-pluginsSkill111mo agoMITA83Claude Code