positioning
Skill2 starsChanged 19 days agoMITView on GitHub
Write the one-liner, ICP with disqualifiers, job to be done, three named alternatives and proof points once, into .claude/context/positioning.md, so the deck, site, docs and launch post say the same thing. Use for "positioning", "ICP", "who is this for", "value prop", "how do we describe this".
19 other projects use a version of this.
Adopted by
Most recently taken up by
- matteotitta/repo-structure-agencytheir own version, first seen Nov 8, 2026
- kasperjunge/skillstheir own version, first seen Nov 8, 2026
- vijaysuperpositionist/skillstheir own version, first seen Nov 1, 2026
- runbooklabhq/indie-launch-skills-litetheir own version, first seen Oct 25, 2026
- vercel-labs/marketing-team-eve-templatetheir own version, first seen Oct 23, 2026
- matteotitta/claude-code-marketing-quickstarttheir own version, first seen Oct 21, 2026
Used with
Projects with it also use tov-guidelines, icp-research and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
matteotittaSkilltov-guidelines
Analyzes existing client content (website, blog, social, docs) to extract voice patterns, vocabulary preferences,
Also in 4 projects that use this
growthack88Skillicp-research
Scrapes case studies, testimonials, and solutions pages from a target website to build structured ICP documentation. Produces TAM analysis, firmographic segments, champion and economic buyer personas, use case mapping, customer proof points, and voice-of-customer synthesis with normalized attributes. Requires website URL as primary input. Upstream: recommended company-context. Downstream: feeds positioning, product-messaging, landing-page-copy, content-strategy, and outreach-emails.
Also in 4 projects that use this
dachi-jp3Skilllevel
表示レベル(auto / low / medium / high)を切り替える。
Also in 3 projects that use this
YepAPISkillcompetitor-research
Competitive analysis between domains using YepAPI.
Also in 4 projects that use this
Other versions19 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 19
- RefoundAI/lenny-skills★ 1.3ksame name
- vercel-labs/marketing-team-eve-template★ 459same name
- matteotitta/claude-code-marketing-quickstart★ 70same name
- matteotitta/repo-structure-in-house★ 70same name
- nahid-sparktales/agent-dispatcher★ 59same name
- Infinite-Labs-AI/infinite-skills★ 43same name
- kasperjunge/skills★ 7same name
- Dragoon0x/product-skills★ 4same name
- matteotitta/claude-marketing-context★ 3same name
- protocol/perun★ 2same name
9 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- build-statusSkill
- ecosystem-bdSkill
- fundraisingSkill
- hackathonSkill
- idea-sprintSkill
- incident-commsSkill
- launchSkill
- market-sizingSkill
- pitch-deckSkill
- pitch-reviewSkill
- pricingSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 16 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 72
Write positioning.md, then read the one-liner against the ICP and the disqualifiers: would a disqualified reader think it is for them?
“Common” is measured: kept by at least 6 in 10 of the 16 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Positioning
Pin down who it is for → what it replaces → why you win → write .claude/context/positioning.md.
The artifact matters more than the interview: every other skill reads it instead of re-deriving
the audience, and that is what stops the deck and the launch post from drifting apart.
Format and section rules: positioning-md-format.md.
Context handoff
- At start: read
.claude/context/positioning.md,.claude/context/idea.mdand.claude/context/build.mdif present. Take the wedge and the bear case fromidea.md, and the proof points frombuild.md's Traction table and What works today. Ask only for what is missing. - On completion: write
.claude/context/positioning.md. Readers: pitch-deck, hackathon, idea-sprint (on a re-run).
Workflow
1. ICP, with who it is not for
Name the buyer and the user separately; on Solana they are often different. The ICP is often another team (a protocol integrating you, a wallet, another founder), and the one who decides may be a DAO or a foundation, not a person with a budget. Write disqualifiers, the people who will show up and are not the target. Crypto-specific patterns: crypto-icp.md.
2. Job to be done
One sentence: when <situation>, they want to <progress>, so they can <outcome>. Use the
situation they are in today, not the category you are in.
3. Three named alternatives
The real alternatives: a named protocol, the manual workaround, and doing nothing (or the spreadsheet, the Discord bot, the CEX). For each, the one dimension you beat it on, and where it beats you. Use real names; "existing solutions" is not an alternative. Mapping method and moat types: alternatives.md.
4. One-liner
Says what it does for whom, not what it is. Draft three:
- a plain one a non-crypto friend understands (hackathon's tagline test)
- an "X for Y" anchor on something the ICP already respects
- the builder version, with the jargon the ICP uses
Pick one as primary. A one-liner that still works with a competitor's name swapped in is too generic.
5. Proof points with sources
Each one is a fact with a link: a tx, a build.md Traction row, an audit, a verified build,
a named integrator. If a trust property is the differentiator (non-custodial, verified
build, no admin key, immutable program), state it as the risk it removes for the ICP and
prove it with the on-chain fact. Never claim a property that build.md's upgrade authority
contradicts.
6. Words to avoid
List the words this team must not use, with the replacement. Start from the defaults in the format file and add the ones this category overuses.
7. Write and check
Write positioning.md, then read the one-liner against the ICP and the disqualifiers: would
a disqualified reader think it is for them? If so, tighten it.
Not here
- Visual and verbal brand identity: get-shit-pretty's gsp-brand-strategy can start from this file.
- Anything about how a token, fee share or yield claim is classified, or what you may say about it where: crypto-legal-skill. This skill does not improvise there.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

