AGENT SKILL

psp-onboarding

First-run interactive setup for the PSP skill pack. Walks the operator through brand-config.json (ICP precision, exclusion criteria, signal sources) and SOUL.md (buyer vocabulary, stories, the 11am-Tuesday moment) in ~15 minutes. Refuses to let the operator skip — generic PSP output is worse than no PSP. Loaded automatically by the main psp skill when brand-config.json or SOUL.md is missing.

License 许可
MIT
所属仓库
bg-szy/TOP-SKILLS
最近更新
2026-11-15
Stars
★ 6
Forks
0

01 前言 Front Matter

name
psp-onboarding
license
MIT
description
First-run interactive setup for the PSP skill pack. Walks the operator through brand-config.json (ICP precision, exclusion criteria, signal sources) and SOUL.md (buyer vocabulary, stories, the 11am-Tuesday moment) in ~15 minutes. Refuses to let the operator skip — generic PSP output is worse than no PSP. Loaded automatically by the main psp skill when brand-config.json or SOUL.md is missing.
allowed-tools
Read Write - Grep
user-invocable
false

02 资源文件 1

03 SKILL.md 正文

PSP Onboarding — first-run setup

Walks the operator through ~15 minutes of setup that makes every downstream PSP 10x more useful than generic framework prose.

Activation

Loaded automatically by the psp orchestrator when brand-config.json or SOUL.md is missing from the project root.

Also user-invocable: "Set up PSP brand config", "PSP onboarding", "Configure PSP".

Why this exists

A generic PSP that says "Series-B SaaS feels pipeline pressure" is worse than no PSP — it produces outreach that everyone else is also producing. The 5-component PSP framework only generates real differentiation when paired with:

  • Your ICP precision (segment, exclusion, motion)
  • Your buyer's actual vocabulary (sourced from real writing, not invented)
  • Your stories (signal-to-pain mappings you've seen succeed or fail before)
  • Your won't-chase boundaries

Workflow

Step 0 — Detect prior state

Check for existing brand-config.json + SOUL.md. If both exist, ask: "Refresh, or skip?" If one exists, fill the gap.

Step 1 — ICP precision

First, ICP. Be specific — "B2B SaaS" is too broad.

Tell me in one batch:
1. The 1-sentence segment (stage / size / motion / region)
2. The size range ($M ARR)
3. The motion (PLG / sales-led / hybrid)
4. The 3-5 exclusion criteria (who you don't sell to)

If your ICP is fuzzy, that's a finding — outreach against a fuzzy ICP
will be fuzzy. We can use placeholders for now and flag them for refresh
after 100 sends.

Save to brand-config.icp.

Step 2 — Primary PSP draft

Now your primary PSP. Five components:

1. SIGNAL — what's a public, recent, verifiable thing your buyer does
   that implies the pain? (job post, funding round, leadership change,
   product launch, pricing change)
2. PAIN — what's the felt operational reality at 11am Tuesday when
   that signal is present? In their language, not yours.
3. TIMING TRIGGER — which 90-day window makes the pain acute now:
   new-exec / budget-cycle / obvious-failure?
4. FELT-PAIN ROLE — who at the buyer feels it most? (Often a layer
   below the buying authority.)
5. VOCABULARY — 4-8 phrases the buyer uses in private about this. If
   you don't know yet, that's step 3.

Save to brand-config.psp_drafts.primary.

Step 3 — Vocabulary mining

If you don't have 4-8 buyer phrases yet, let's mine them.

Point me at any of these sources for the buyer segment:
- 3-5 of their public LinkedIn posts
- 1-2 podcast appearances
- 2-3 of their hiring job posts (job posts reveal pain language verbatim)
- 1-2 conference talks / panel appearances
- Their public AMA responses

I'll extract candidate phrases — you confirm which ones land.

If WebFetch is available, the skill can pull + extract directly. If not, instruct the operator to paste content and run extraction.

Step 4 — Signal sources (operations)

Where will you hunt these signals? (Mark all that apply.)

1. LinkedIn job search (daily — manual or via Phantombuster)
2. Crunchbase / news APIs (weekly)
3. RSS feeds for specific publications
4. Podcast feeds for relevant shows
5. Manual research only

How often refresh:
- PSP refresh cadence (default: 90 days)
- Vocabulary refresh (default: 30 days)
- Signal freshness window (default: 14 days — older signals drop)

Save to brand-config.signal_sources + brand-config.research_cadence.

Step 5 — Stories (SOUL.md)

Tell me 3-5 stories that anchor your PSP — times you saw a signal-to-pain
mapping work or fail.

Each story: 1-2 sentences, anonymized but specific. These become
calibration points for the construct skill.

Also:
- Your won't-chase boundaries (topics / segments you refuse)
- The 11am-Tuesday operational moment of your buyer (paint it specific)

Save to SOUL.md.

Step 6 — Write the files

Write brand-config.json + SOUL.md at the project root. Show preview:

✓ brand-config.json — ICP + 1 PSP draft + signal sources + cadence
✓ SOUL.md — 3 stories + vocabulary + 11am-Tuesday moment

Try a quick test:
> Construct a PSP for <segment>

The output will now use:
- Your ICP precision (not generic "B2B SaaS")
- Your vocabulary (not category jargon)
- Your stories as calibration

Next step: install `cmj-hub/claude-evp` to lock the EVP that speaks
to this PSP. Then `cmj-hub/claude-cold-email` to ship outreach.

Step 7 — Refresh cadence

PSPs decay. Re-run onboarding when:
- ICP shifts (new segment / segment cull)
- Buyer vocabulary evolves
- Quarterly minimum (90 days)

Re-run: `/psp onboarding refresh`

References

  • ../../brand-config.example.json — full template
  • ../../SOUL.md — voice template
  • ../../AGENTS.md — behavior rules
  • Sister skills:
    • psp-kickoff — adaptive router that uses these files
    • psp-construct — uses brand + SOUL for actual PSP build
    • psp-signal-hunt — runs against your signal sources

04 同仓库更多 Skills

bg-szy
bg-szy/TOP-SKILLS

serpmaven

Scrape Google search results (SERP) to JSON with SERP Maven (serpmaven) - a real Chrome browser on a residential proxy with sticky sessions. Run it as a CLI, a Python library, a local HTTP search API (`serve`), an MCP server or a Docker image; set the proxy login, workers, pages and cost tracking. Use when the user wants Google results, rank tracking, a self-hosted SERP API, or live Google search for an AI agent.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-landing-page-audit

Find out why a landing page isn't turning visitors into signups, demos or sales. Audits one page against what the ad, post or search that sends people there promised, then checks the first screen, proof, call to action, friction and mobile. Returns at most 7 prioritized fixes, plus what is fine and what could not be checked; rewrites specific lines and fixes the page in the repo when asked. Never promises a conversion lift. Works without a Revnu account. Use when the user says or asks: "audit my landing page", "why isn't this page converting", "review my homepage", "my ads get clicks but no signups", "people bounce from the pricing page", "CRO review", "improve conversion rate", "is my hero section clear", "roast my landing page", "rewrite my headline", "what's wrong with this page", "landing page feedback", "make the signup page convert better". Not for SEO or AI-search audits, page speed engineering on its own, or building a new page from scratch.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-growth-context

Write down once who buys, what they're stuck on, what it costs, what proof you have and what you've already tried, so every growth task starts from facts instead of a questionnaire. Creates or updates .agents/revnu-growth.md from the repo, the live site and the user, and imports an existing product-marketing.md. Use when the user says "set up our marketing context", "who is our ideal customer", "write our ICP", "describe the product for marketing", "positioning doc", "what's our brand voice", "remember this about our customers", "log what we tried", "what have we learned from marketing", "we changed pricing, update the context", "update our growth notes", "summarize the business for the agent", "import my product-marketing.md", "start a growth doc", or before a first marketing, SEO, outreach or launch task when no context file exists. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-get-listed

Get onto the third-party pages AI answers and search cite when buyers ask for the best tool in your category: "best X" roundups, directories, review sites, GitHub awesome lists, community threads and comparison pages. Finds which ones are cited, ranks them by fit and effort, and drafts each submission, PR or pitch by the target's own rules. Use when the user says "get us listed", "which directories should we submit to", "how do we get into best-of lists", "why does ChatGPT recommend competitors and not us", "get mentioned in AI answers", "submit to awesome lists", "get on G2", "where are our competitors listed", "pitch listicle authors", "find backlink opportunities", "launch directories", "get into roundups", "Product Hunt alternatives", "where should we be listed", "get cited by Perplexity". Never submits, pays or posts without a yes. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

revnu-ai-readiness-audit

Audit whether your website gives ChatGPT, Perplexity, Claude, Gemini and Google's AI Overviews something worth quoting, and fix the pages that don't. Use when the user says or asks "is my site ready for AI search", "audit my site for AI answers", "AEO audit", "GEO audit", "why doesn't ChatGPT quote our pricing", "make our pages citable by AI", "do I need llms.txt", "does schema help with ChatGPT", "check our structured data", "is our content visible without JavaScript", "AI SEO audit", "optimize our homepage for AI answers", "LLM SEO check", "why does AI get our product wrong", "fix our site for AI Overviews". Checks fetchability and indexability, answers in the raw HTML, entity facts, schema (including JS-injected markup), headings, dates and llms.txt, then gives at most 10 prioritised fixes and edits the repo when asked. Works without a Revnu account.

★ 6
bg-szy
bg-szy/TOP-SKILLS

proxy-troubleshooting

Diagnose residential proxy failures, with NodeMaven's gateway as the reference - 407 with correct credentials, 406, 410, 500, a connection that hangs, ERR_TUNNEL_CONNECTION_FAILED in a browser, Playwright or Puppeteer ignoring proxy credentials, a sticky session that changes IP, geo-targeting that is silently ignored, passwords with special characters, and unexpected traffic from headless Chrome. Use when a proxy connection fails, returns the wrong location, or costs more traffic than expected.

★ 6