journey
Skill258 starsChanged 29 days agoMITView on GitHub
Use this skill when a solo founder does not know where to start or what to do next: 'where do I start,' 'what should I do first,' 'what order do I do things in,' 'what should I work on now,' 'I have an idea, now what,' or 'I don't have an idea yet.' Finds the founder's stage from paying customers, not from code, and names the one next skill to use. Not for judging whether a specific activity or purchase is worth it (use focus).
9 other projects use a version of this.
Adopted by
Most recently taken up by
- whawkinsiv/solo-founder-skillsword for word, first seen Oct 25, 2026
- kv0906/pm-kittheir own version, first seen Oct 13, 2026
- butterbase-ai/butterbase-plugintheir own version, first seen Oct 8, 2026
- me2resh/apexyardtheir own version, first seen Oct 8, 2026
- Thalisu/SKILLStheir own version, first seen Oct 1, 2026
- tonydzi/second-brain-starter-kittheir own version, first seen Sep 8, 2026
Used with
Projects with it also use inbox and discover.
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.
kv0906Skillinbox
Quick capture mode (with content) or batch processing mode (no content). GTD-style routing of inbox items to proper folders. Use "/inbox thought to capture" or "/inbox" to process.
Also in 3 projects that use this
anombyte93Skilldiscover
Phase 1 of the prd-taskmaster pipeline: brainstorm-driven discovery. Delegates to superpowers:brainstorming in Interactive Mode (one adaptive question at a time), or self-brainstorms in Autonomous Mode when no user is present. Intercepts before the brainstorming chain hands off to writing-plans — this skill owns the exit. Extracts constraints, calibrates scale (Solo / Team / Enterprise), and advances the pipeline to GENERATE.
Also in 3 projects that use this
Other versions9 projects use a version of this.
Word for word · 1
- whawkinsiv/solo-founder-skills★ 260100% same
Edited · 0
None found.
Wrote their own version · 8
- me2resh/apexyard★ 542same name
- butterbase-ai/butterbase-plugin★ 535same name
- butterbase-ai/butterbase-skills★ 535same name
- kv0906/pm-kit★ 138same name
- tonydzi/second-brain-starter-kit★ 6same name
- MeshJS/evolving-claude-skills★ 4same name
- Thalisu/SKILLS★ 1same name
- weg-9000/Orange-pm★ 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.
In this repository20 other files it gives its agents.
- about-meSkill
- beautifySkill
- buildSkill
- contentSkill
- domain-nameSkill
- emailSkill
- financesSkill
- first-customersSkill
- focusSkill
- go-liveSkill
- humanizeSkill
- is-this-an-appSkill
- landing-pageSkill
- legalSkill
- paymentsSkill
- pricingSkill
- retentionSkill
- secureSkill
- seoSkill
- validateSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 8 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
Use these at any stage: focus (is this worth my time or money), finances (runway and the quit number), domain-name (when the founder needs …
- Distinctive: line 29
Read the project's CLAUDE.md and README if they exist.
- Distinctive: line 30
If you cannot tell, ask two questions in one message:
“Common” is measured: kept by at least 6 in 10 of the 8 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
Journey
Find the founder's stage and name the one next step. The stage depends on paying customers, not on how much code exists.
The order
Sell before you build. Get the first 10 paying customers by hand, then grow to 100.
| Stage | The founder says | Use | Gate to pass before the next stage |
| 0. No idea | "I don't have an idea yet" | validate (find the problem) | One problem that people they can name have now |
| 1. Idea | "I have an idea" | validate, then is-this-an-app | Evidence that strangers have the problem and spend money or time on it |
| 2. Sell by hand | "How do I get my first customers?" | pricing, landing-page, email, first-customers, then the manual delivery test in validate | 10 paying customers who are not friends or family, and the delivery steps written down |
| 3. Build | "Now I build it" | build, beautify, secure | The step that takes the most time is automated, and customers use it |
| 4. Go live | "Is it ready?" | go-live, payments, legal | go-live passes |
| 5. 10 to 100 | "How do I grow?" | first-customers (launch), content, seo, retention | 100 paying customers |
Use these at any stage: focus (is this worth my time or money), finances (runway and the quit number), domain-name (when the founder needs a name), about-me and humanize (writing in the founder's voice).
Steps
- Read the project's CLAUDE.md and README if they exist. Look for how many people pay today and what is built.
- If you cannot tell, ask two questions in one message:
- How many people pay you today?
- What have you built so far?
- Place the founder at the earliest stage whose gate they have not passed. A founder with a finished app and no paying customers is at stage 2, not stage 4. The code exists, but nobody has paid yet. Say this plainly. It is the most useful thing this skill can tell them.
- Name one next skill and one next action for this week.
Rules
- One recommendation. A list of five skills is a menu, and a founder who is lost cannot choose from a menu.
- Do not skip a gate. Building before stage 2 is the most common way founders lose months. A launch before 10 customers sends strangers to a product nobody has paid for.
- A product that cannot be delivered by hand (real-time collaboration, network effects) replaces the manual test with a pre-sale in validate. The gate stays at 10 paying customers.
- Friends and family can buy, but they do not count toward a gate. They pay to support the founder, not to solve a problem.
Output
Stage: <number and name>
Why: <one sentence, from what the founder said or what the project shows>
Next: <one action for this week>
Skill: <one skill name>
Gate: <what must be true before the next stage>Example
User says: "My app is finished. Where do I launch it?"
The founder has no paying customers. Result:
Stage: 2. Sell by hand
Why: The app works, but nobody has paid for it yet.
Next: Sell it, one person at a time, to 10 people who have the problem.
Skill: first-customers
Gate: 10 paying customers who are not friends or family. Then launch.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.