agentleFS
hailneedhailneed/painradar/skills/fit/SKILL.md

fit

Skill0 starsChanged 3 months agoMITView on GitHub

Rank what is worth building from a radar report — cross each complaint theme with verified-revenue proof (TrustMRR) and, when available, the developer's own persona card from devpersona (stack, strengths, risk patterns) to produce a founder–opportunity fit ranking with MVP scope and first-10-users source. Use when the user asks which idea to build, what would pay, "ne inşa etmeliyim", "hangisi para eder", "bana uygun fırsat", "rank these opportunities", or runs /painradar:fit. Requires a radar report from painradar:scan and runs it first if missing. Not for the complaint report itself — that is painradar:scan. Not for marketing — that is painradar:launch.

  • Reads credentials

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. ontology-of-everything/handy-skills★ 2same name
    2. pueding/houserules★ 1same 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 repository2 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    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
  1. Very specific:

    If present, read stack, strengths, risk patterns.

    line 18
  2. Very specific:

    Money proof: if TRUSTMRR_API_KEY is set, run node "${CLAUDE_PLUGIN_ROOT}/scripts/radar.mjs" --topic "<topic>" --trustmrr …

    line 20

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Founder–opportunity fit

Answer one question per theme: is there pain, is anyone paying, and is this person the right one to build it? Every score must point at evidence. No evidence, no ranking.

Language rule: write every user-facing output in the language the user is speaking with you.

Step 0 — Load inputs

  1. Latest ~/.claude/radar/<slug>-<date>.md (+ <slug>-raw.json). If none or older than 14 days, run the scan skill of this plugin first.
  2. Persona (optional, local): ~/.claude/persona/persona.md written by devpersona. If present, read stack, strengths, risk patterns. If absent, say fit is estimated without a persona and suggest /devpersona:analyze — do not guess the user's skills.
  3. Money proof: if TRUSTMRR_API_KEY is set, run node "${CLAUDE_PLUGIN_ROOT}/scripts/radar.mjs" --topic "<topic>" --trustmrr "<Category>,<Category>" --out "<home>/.claude/radar/<slug>-money.json" and use trustmrr median MRR / growth per category. Without a key, fall back to the public stats page (https://trustmrr.com/stats) and mark figures "(doğrulanmadı)" — never invent numbers. Map each theme to the closest TrustMRR category (Marketing, Developer Tools, Analytics, Security, Sales, Content Creation, …).

Step 1 — Score (0–5 each, one line of evidence per score)

DimensionWhat counts
Painthe theme's Signal from the radar report
Money proofverified startups earning in the adjacent category; median MRR; 30-day growth
Competition gaphow many tools already serve it; is there a free/OSS incumbent or big vendor
Founder fitpersona stack & strengths match the MVP; risk patterns that would hurt here
Effort5 = MVP in ≤ 2 weeks solo, 1 = months or a team
Platform risk5 = owns its data/channel, 1 = depends on one API/licence that may change

Fit = weighted: Pain 25 % · Money 20 % · Gap 20 % · Founder 15 % · Effort 10 % · Risk 10 %. State the weights in the report so the user can override them.

Step 2 — Write ~/.claude/radar/<slug>-fit-<date>.md

  1. Ranking table (theme, Fit 0–100, the six scores).
  2. For the top 3: one-paragraph thesis · MVP scope (the one job it does, 3–5 bullets) · what to leave out · pricing hypothesis with comparable verified products (linked) · where the first 10 users are (specific communities/threads from the evidence) · the riskiest assumption and a ≤ 1-week test for it · evidence links.
  3. "Do not build" notes: themes that are real pain but saturated (name the incumbents).
  4. Persona notes: which persona traits helped or hurt each score (or "persona yok").

Step 3 — Reply

Chat: the top 3 with Fit score and a one-line why; the single riskiest assumption of #1; then /painradar:launch for the go-to-market plan of the chosen one.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.