company-context
Skill35 starsChanged 4 months agoMITView on GitHub
Interview the user to build or update a reusable company context file for AI tools — what the company does, its offer, clients, personas, positioning, voice, and the questions clients ask most. Use when the user says "build our company context", "create company context", "set up business context for AI", "update our company context", or wants AI to answer clients and write content in the company's voice without re-explaining the business each time. Produces company-context.md.
We split this skill into the rules it gives an agent
6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Ask in small batches (3–5 at a time), conversational, not a giant form.
- Distinctive: line 19
After the core questions, proactively flag gaps: name 2–4 specific things that are missing and would make the context more useful (e.g.
- Distinctive: line 20
If they have several distinct services or audiences, capture each briefly rather than blending them.
- Distinctive: line 21
When done, write the file (see Output) in their own wording and tone.
- Very specific: line 37
Write company-context.md in the current directory (skip blanks).
- Very specific: line 39
Use the templates' ## headings, in the file's language:
“Common” is measured: kept by at least 6 in 10 of the 5 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
company-context — build a reusable company context file
Interview the user about their company and write a clean company-context.md they can feed into any AI tool so it answers clients, writes content and proposals in the company's voice, and stops guessing the business.
If company-context.md already exists in the current directory, read it first, give the user a two-line summary, and ask what has changed — then update those parts and refresh the Last updated line. Don't re-run the interview from scratch and don't overwrite their file without confirmation.
How to run the interview
- Ask in small batches (3–5 at a time), conversational, not a giant form.
- Interview and write the file in the user's language — if they write in Polish, ask and write in Polish.
- Pre-fill from anything you can see (their site if they share it, the repo, earlier messages) and ask them to confirm rather than re-asking.
- Sections 1–3 (the company, offer, customers) are the core — cover them first, then offer the rest; a file with just the core is already useful, so let the user stop there if they want.
- On "I don't know": give one concrete example answer; if they still don't know, skip the point and move on — don't push.
- After the core questions, proactively flag gaps: name 2–4 specific things that are missing and would make the context more useful (e.g. "you haven't described your ideal customer's main pain — want to add it?").
- If they have several distinct services or audiences, capture each briefly rather than blending them.
- When done, write the file (see Output) in their own wording and tone.
What to cover
- The company — name, a one-line description of what it does, website, stage/size.
- Offer — products/services, who each is for, pricing model (optional), and what genuinely makes it different (the real differentiators, not slogans).
- Customers — the ideal customer (industry, size, role), the problem you solve, the outcome you deliver, and 2–3 real (or anonymised) client examples.
- Personas — the key people involved: who decides to buy, who actually uses it, and each one's main goals and pains.
- Positioning & messaging — the category you compete in, your value proposition in a sentence, proof/credibility, and competitors you're often compared to.
- Voice — tone, words and phrases to use, and ones to avoid; any brand or style rules.
- Team — key people and who does what (optional).
- Client-facing know-how — the questions clients ask most often (with your answers), common objections and how you handle them, and your typical process from first contact to delivery.
- Anything else — an open prompt for what any AI should know to represent the company well.
Output
Write company-context.md in the current directory (skip blanks). Match the templates' top-of-file: a # Company context title (Polish: # Kontekst firmy), a _Last updated: YYYY-MM_ line with the current month, then a one-line > "what we do". Keep it factual and skimmable — it's a reference, not a brochure.
Use the templates' ## headings, in the file's language:
- English: The company · Offer · Customers · Personas · Positioning & messaging · Voice · Team · Client-facing know-how · Anything else
- Polish: Firma · Oferta · Klienci · Persony · Pozycjonowanie i komunikacja · Głos marki · Zespół · Wiedza pod klienta · Cokolwiek jeszcze
- Other languages: translate consistently, keep the same order.
End the file with the templates' footer line, in the file's language:
- English:
_Built with [ai-context-kit](https://github.com/nocodework/ai-context-kit). Put this in a shared ChatGPT/Claude Project, a Gemini Gem, CLAUDE.md, or your editor's AI rules — and keep it updated._ - Polish:
_Zrobione z [ai-context-kit](https://github.com/nocodework/ai-context-kit). Wrzuć do współdzielonego Projektu w ChatGPT/Claude, Gema w Gemini, CLAUDE.md albo reguł AI w Twoim edytorze — i aktualizuj przy zmianach._
Then tell the user:
- the full path of the file you wrote;
- where to put it: a shared ChatGPT/Claude Project (so the whole team's chats use it), a Gemini Gem,
CLAUDE.md, or their editor's AI rules — per-tool steps at https://github.com/nocodework/ai-context-kit#use-your-context-in-any-ai-tool — and to keep it updated. If the file names real clients or internal sales know-how, remind them to share it only in private/team spaces, not publicly.
Offer to append it to an existing CLAUDE.md if present.
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- paradigmxyz/centaur★ 1.4ksame name
- matteotitta/genesys-skills★ 46same name
- Unabyss/unabyss-skills★ 15same name
- 30Elevate/company-context★ 0same name
- matteotitta/claude-marketing-context★ 0same name
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.
Used alongsideProjects with it also use tov-guidelines, icp-research and 1 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
Extracts a company's tone of voice from its own content and turns it into rules a writer or an AI can follow. Phase 1 analyses 15 to 20 pages for sentence, paragraph, word and structure patterns with frequency counts; after the user reviews it, Phase 2 writes the guidelines: tone attributes with before and after examples, a We are / We are not table, tone by context, vocabulary to use and avoid, and open questions. Triggers: "tone of voice", "brand voice", "voice guidelines", "writing style guide", "extract voice from our website", "TOV". Not for visual identity (use /brand-kit) or messaging (use /messaging).
Also in 3 projects that use this
matteotittaSkillicp-research
Builds an ideal customer profile from evidence: case studies, testimonials, customer logos, solutions pages, reviews and any sales notes you have. Produces market sizing layers, firmographic segments, a champion and an economic buyer persona, a negative ICP, intent signals, customer proof points and a voice-of-customer section in the buyers' own words, every claim sourced. Triggers: "ICP research", "ideal customer profile", "who are our customers", "customer segments", "buyer personas", "who should we target". Run after /company-context. Not for competitor analysis (use /competitor-research) or call transcript patterns (use /win-loss).
Also in 3 projects that use this
YepAPISkillcompetitor-research
Competitive analysis between domains using YepAPI.
Also in 3 projects that use this
In this repository2 other files it gives its agents.
- personal-contextSkill
- refresh-contextSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
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.

