gtm-strategist-skills: Skill for Claude Code

.claude/skills/collecting-intelligence/SKILL.md

collecting-intelligence is a skill for Claude Code from GTM-Strategist/gtm-strategist-skills. It costs 75 tokens per session (4,376 once invoked), scanned A, original, MIT.

A guided research workflow for learning about customers, markets, and competitors. Customer discovery means gathering evidence from potential users instead of relying only on assumptions.

In plain words
What is it for?
Use it to identify an initial target customer group, map market problems, plan interviews and surveys, and analyze competitors.
Why use it?
It gives structure to market research and shows which beliefs about customers or competitors still need to be tested.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is GTM-Strategist/gtm-strategist-skills's own configuration. It tells Claude Code how to work on gtm-strategist-skills itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gtm-strategist-skills configures →

Part of the .claude plugin — 12 skills shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to GTM-Strategist/gtm-strategist-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/GTM-Strategist/gtm-strategist-skills/master/.claude/skills/collecting-intelligence/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/GTM-Strategist/gtm-strategist-skills

Made for: Claude Code.

Or install .claude, the plugin that ships this one along with the rest of its 12 skills.

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 collecting-intelligence

README.md
[![agentmods](https://agentmods.dev/badge/skills/gtm-strategist/gtm-strategist-skills/collecting-intelligence/github.svg)](https://agentmods.dev/skills/gtm-strategist/gtm-strategist-skills/collecting-intelligence)
Your own site
<a href="https://agentmods.dev/skills/gtm-strategist/gtm-strategist-skills/collecting-intelligence"><img src="https://agentmods.dev/badge/skills/gtm-strategist/gtm-strategist-skills/collecting-intelligence/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 collecting-intelligence

Your own site · 80×15
<a href="https://agentmods.dev/skills/gtm-strategist/gtm-strategist-skills/collecting-intelligence"><img src="https://agentmods.dev/badge/skills/gtm-strategist/gtm-strategist-skills/collecting-intelligence.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,376 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00075 $0.04376
Opus 5 $0.00037 $0.02188
Sonnet 5 $0.00015 $0.00875
Haiku 4.5 $0.00007 $0.00438

Measured 12d ago against content hash e6eeaa55705c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

collecting-intelligence 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 12d ago.

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.

.claude/skills/collecting-intelligence/SKILL.md · 366 lines

How it starts

The opening of the file, as written. The whole thing — 366 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phase 2: Collecting Intelligence — Customer Discovery & Competitive Research

You are executing Phase 2 of the GTM Strategist methodology. This phase transforms the user's assumptions from Phase 1 into evidence-backed market intelligence through structured customer discovery and competitive research.

Before You Start

  1. Read my-gtm-context.md at the project root. If critical fields (Product/Service, Target Market, Problem & Value) are empty, ask the user to fill them in before proceeding.

  2. Check outputs/ for Phase 1 deliverables. This phase builds directly on:

    • outputs/01-ope-canvas.md (Opportunity, Product, Execution canvas)
    • outputs/01-swot-analysis.md
    • outputs/01-value-proposition.md
    • outputs/01-90-day-plan.md

    If Phase 1 outputs exist, reference them throughout. If they don't exist, note that the user is working from assumptions — which is fine, but flag it. Phase 2 is specifically designed to test assumptions.

  3. Work one task at a time. Present the deliverable, get feedback, then move to the next task. Don't dump all nine tasks at once.


Task 1: Identify Beachhead Segment Candidates

Duration: 1-3 hours | Output: outputs/02-beachhead-candidates.md

"SaaS founders from the US" is NOT a segment. As a new player entering a market, you need critical mass of traction with relatable references. You cannot effectively market to 17,000 SaaS founders — nobody will feel like your product was built for them. A beachhead segment is narrow enough that customers within it reference each other, share context, and create word-of-mouth density.

What to do:

  1. Read my-gtm-context.md sections 2 (Target Market) and 3 (ICP). Pull any existing market assumptions.

  2. If Phase 1 outputs exist, extract the initial market/customer assumptions from the OPE canvas and SWOT.

  3. Guide the user to brainstorm 5-8 candidate beachhead segments. For each segment, capture:

    • Segment label — specific enough that the user could name 10 people in it
    • Size estimate — rough order of magnitude (hundreds, low thousands)
    • Pain intensity — how urgent is the problem for this group (1-5 scale)
    • Reachability — can you actually get in front of them? Through what channels?
    • Reference density — do people in this segment talk to each other, follow each other, attend the same events?
    • Willingness to pay — is this a budget line item or a nice-to-have?

Read the full file on GitHub · 366 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. 12d ago First seen · 366 lines · 75 tokens per session scan A e6eeaa55705c

Subscribe to this mod's changes

collecting-intelligence is a skill published in the GitHub repository GTM-Strategist/gtm-strategist-skills (254 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 4,376 once invoked, about $0.0004 per session on Opus 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 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens