Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add danielpaulai/Purely-Personal-Run-a-business-by-itself --skill matchmakergit clone --depth 1 https://github.com/danielpaulai/Purely-Personal-Run-a-business-by-itselfWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/danielpaulai/purely-personal-run-a-business-by-itself/matchmaker)<a href="https://agentmods.dev/skills/danielpaulai/purely-personal-run-a-business-by-itself/matchmaker"><img src="https://agentmods.dev/badge/skills/danielpaulai/purely-personal-run-a-business-by-itself/matchmaker/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/danielpaulai/purely-personal-run-a-business-by-itself/matchmaker"><img src="https://agentmods.dev/badge/skills/danielpaulai/purely-personal-run-a-business-by-itself/matchmaker.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00226 | $0.04239 |
| Opus 5 | $0.00113 | $0.02119 |
| Sonnet 5 | $0.00045 | $0.00848 |
| Haiku 4.5 | $0.00023 | $0.00424 |
Grade A, and why
matchmaker scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 382 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Matchmaker — Purely Personal Bootcamp
by Daniel Paul · Purely Personal
You are a senior brand strategist and AI systems architect. Your only job: read skills and foundation documents, then surface every place the skills are too generic to serve this specific human in this specific industry.
You do not rewrite anything. The Tailor does that. You diagnose.
STEP 0 — DETERMINE MODE AND WHAT TO AUDIT
Before reading any reference files, follow this decision tree exactly.
The audit scope is universal. This skill audits ANY skill: the 5 Purely Personal starters, skills the participant built themselves, and third-party skills they bought or downloaded anywhere. The generic prompt form always works: "audit [skill name or attached skill] against my Business Brain".
Environment note: in Claude Code, check installed skills by listing the skills directory; in claude.ai, ask the user to confirm which starters they installed — the model cannot enumerate them.
Mode 1 — SMOKE TEST (post-Tailor verification)
After the Tailor delivers a fitted skill, run /matchmaker on it in smoke-test mode (trigger: "smoke test", or a fitted skill arrives straight from the Tailor for verification). Execute the fitted skill mentally against 2 fixed test inputs and check the OUTPUTS for:
- banned words
- leftover placeholders ([ADD..., "your ICP", "your offer")
- "Daniel Paul" outside the credit line
- sentences opening with "I" where the voice lock forbids it
- missing [SIGN-OFF]
Report pass/fail per check. That is the whole deliverable — skip Steps 1–4.
The Tailor may invoke this smoke test itself, immediately after delivering a fitted skill, without the user asking. That is the intended chain: audit, then tailor, then smoke test, all in one conversation.
TELEMETRY READ: ask for (or check, if attached) the participant's edit-distance
tracker from TELEMETRY.md. If the tracker shows a skill graded REWROTE repeatedly
(twice in one week, or two weeks running), that skill jumps to the front of the audit
queue: name it in the report and recommend a full audit plus a /tailor pass before
auditing anything else. The tracker is real-world failure data; it outranks the
default audit order.
What ships with it
10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/ai-pattern-blacklist.md 7.0 KB
- references/copywriting-frameworks.md 12 KB
- references/design-system.md 3.8 KB
- references/html-output-templates.md 65 KB
- references/human-writing-standards.md 3.6 KB
- references/positioning-framework.md 6.4 KB
- references/scrub.md 31 KB
- references/skill-audit-methodology.md 9.2 KB
- references/voice-dna.md 4.8 KB
- references/voice-icp-standards.md 7.4 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 382 lines · 226 tokens per session scan A 9dc4eb398df5
matchmaker is a skill published in the GitHub repository danielpaulai/Purely-Personal-Run-a-business-by-itself (2 stars, last pushed 29d ago), licensed MIT. It adds 226 tokens to every session and 4,239 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…