Agent skill
context-intake
Personalize PMM Kit and/or start a new product's context hub — this is the load-bearing, run-first skill that turns the generic PMM Kit framework into something specific to a real organization and product.
Filed under Positioning and messaging.
From kili-d/pmm-kit · 14 skills · 2 · pushed 2026-07-15
What it does when it runs
Personalize PMM Kit and/or start a new product's context hub — this is the load-bearing, run-first skill that turns the generic PMM Kit framework into something specific to a real organization and product. Use whenever the context/ folder is empty or missing key files, when starting work on a product that has no hub yet, when the user says things like "set up PMM Kit for my product," "personalize this," "let's start a new product," "onboard this product," or drops docs into an inputs/ folder wanting them turned into usable context, or whenever CLAUDE.md's own instruction to run context-intake first applies. Always run this before product-immersion, evidence-synthesizer, or any other PMM Kit skill on a product that hasn't been through intake yet.
Read from the skill and the 19 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.
- Keys and connectors you must supply
- None found.
- Hosts it reaches
- No third-party host appears in the skill or its bundled files.
- Tool permissions it declares
- No
allowed-toolsin the frontmatter. It only issues instructions, so there is nothing to bound. - Actions present in the files
- None. Instructions only.
Install it
View source on GitHub ↗git clone --depth 1 --filter=blob:none --sparse https://github.com/kili-d/pmm-kit.git /tmp/pmm-kit git -C /tmp/pmm-kit sparse-checkout set ".claude/skills/context-intake" mkdir -p ~/.claude/skills/context-intake cp -R "/tmp/pmm-kit/.claude/skills/context-intake/." ~/.claude/skills/context-intake/
Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗
The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.
The skill
Source on GitHub ↗The source carries no licence at all, so no permission to redistribute it exists. Everything else on this page is our own reading of the file and is published here; the text of the skill is not, and stays where its author put it.
Files bundled with it
These load only when the skill asks for them, so they cost nothing until it runs.
- 00-index.md
- 01-product-truth.md
- 02-evidence-log.md
- 03-customer-and-jobs.md
- 04-competitor-map.md
- 05-journey-teardowns.md
- 06-pricing-packaging.md
- 07-positioning.md
- 08-messaging-house.md
- 09-value-prop-matrix.md
- 10-distribution.md
- 11-stakeholders.md
- 12-campaign-brief.md
- 13-copy-library.md
- 14-strategic-narrative.md
- .gitkeep
- .gitkeep
- .gitkeep
- .gitkeep
Other skills for the same job
Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.
- startup-context by shawnpang · 308
- multi-turn-context-retention by louisblythe · 136
- product-context by taizen-ai · 8
- firm-context by b2bforce · 2
Need help setting it up?
This page tells you what context-intake does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.
Book a call →The directory stays free. There is nothing gated behind this.