REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
汇报.skill · pitchcraft — Structured persuasion for tech leads, PMs, and founders: kickoff, status, wrap-up, pitch, and solution selling on one 5-part framework (Hook→Context→Proposal→Evidence→Ask), with AI material intake and a pre-submit checklist. Works with Claude Code, Cursor, Codex, and more.
Si lo creaste tú, pega este código en tu README. La insignia enlaza a esta página.
[](https://mcp.popnx.com/en/skills/moshuying-pitchcraft)Servidores MCP que conectan la IA a servicios para el mismo trabajo
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
Mismo tipo de trabajo, ordenadas como la lista de Skills
| Este pitchcraft | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| Autor | moshuying | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skills | 1 | 1 | 1 | 1 | 1 |
| Estrellas de GitHub | 202 | 468.733 | 234.332 | 150.287 | 144.566 |
| Último cambio de código | 29 jun 2026 | 19 nov 2026 | 20 abr 2026 | 18 nov 2026 | 18 nov 2026 |
| Licencia | Apache-2.0 | MIT | – | Apache-2.0 | MIT |
1 skills (conjuntos de instrucciones) de moshuying que la IA lee y sigue · no es un MCP server
MCP = las manos
Conecta la IA a un servicio o dato externo, como leer Notion o crear una factura. Necesita un programa o servidor en marcha.
Skill = el manual
Un archivo de texto que enseña a la IA cómo hacer una tarea. No se conecta a nada.
A veces se parecen: algunas Skills ejecutan scripts que llaman herramientas y algunos MCP solo envían conocimiento. Empieza por la tarea que quieres hacer.
Claude CodeCodexCursor
Según el README del autor y las carpetas del repo
GitHub account moshuying (person), 8 years old
★ 202 stars, few users so far · code last changed 29 jun 2026
1 scripts that can run on a computer: scripts/install.js
No internet calls found in the scripts
No hooks or writes to machine settings found
Checked automatically from the repo files at commit e27ca8a (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
Primero: ¿qué IA usas?
Elige tu app y esta página mostrará solo cómo instalarlo en ella
Uploading to claude.ai would fail: the description is over 200 characters (353). Use "Let the AI install it" instead
Copia esta frase y pégala en un chat de Claude Code
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Vuelve a abrir Claude Code y escribe /pitchcraft, o pide una tarea relacionada y Claude lo usará
Checked against official docs 12 nov 2026 · Source: code.claude.com
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
¿Ya está instalado? Compruébalo primero · Abre la Terminal, escribe este comando y pulsa Enter
node -vMac: pulsa ⌘ + Espacio, escribe Terminal y pulsa Enter
Windows: abre Inicio, escribe Windows PowerShell y elige Abrir
Si no está instalado: Abre la página oficial de descargas, elige la versión LTS y el instalador de clics: .pkg en Mac · .msi en Windows. Haz doble clic y sigue hasta el final. No necesitas ningún comando curl
Abrir la página de descarga de Node.js ↗
Al terminar, cierra la Terminal, ábrela de nuevo y ejecuta el mismo comando. Debe aparecer un número de versión: node -v
Se instala una vez y sirve para todo lo que usa Node.js
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Copiado del README del autor; descarga y ejecuta su código
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
La app de escritorio de ChatGPT incluye Codex, y Codex lee las skills de la carpeta ~/.agents/skills
Abre Codex en la app de escritorio de ChatGPT y pega esta frase en el chat
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Coloca la carpeta pitchcraft en ~/.agents/skills/pitchcraft
~ es tu carpeta de inicio ($HOME)
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
Las skills que instalas tú no funcionan aquí; solo las que vienen con un plugin del directorio
Para usar esta skill con ChatGPT, usa la app de escritorio de ChatGPT como se indica arriba
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
Copia esta frase y pégala en un chat de Codex · Sirve en Codex dentro de la app de escritorio de ChatGPT, en Codex CLI y en la extensión del IDE
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex detecta solo las skills recién instaladas; si una no aparece, reinicia Codex · Para usarla: en ChatGPT escribe @ y elige la skill · en Codex CLI o la extensión del IDE ejecuta /skills o escribe $ y el nombre de la skill
Checked against official docs 15 nov 2026 · Source: learn.chatgpt.com
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Copia esta frase y pégala en un chat de Cursor
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
En el chat Agent de Cursor escribe / y elige pitchcraft
Checked against official docs 12 nov 2026 · Source: cursor.com
Un Skill son instrucciones que la IA seguirá. Lee los archivos antes de instalar e instala solo de autores de confianza.
Mac: pulsa Command+Espacio y escribe Terminal · Windows: el comando no funciona en PowerShell; usa «Que la IA lo instale» arriba
Descarga el repo a una carpeta temporal y copia solo las carpetas con SKILL.md
Revisando los comandos · los botones de copiar aparecen cuando pasan la revisión
Para otras apps que leen skills. La frase incluye las rutas de Claude Code, Codex y Cursor para que la IA elija la de tu app · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 12 nov 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com
Otras apps con Agent Skills (como Gemini CLI o GitHub Copilot) usan otras carpetas. Mira la guía de esa app y copia allí la carpeta con el SKILL.md.
Carpetas de skills comprobadas con las guías oficiales de Claude Code, Codex y Cursor el 11 nov 2026
El texto siguiente viene del repo del autor, no de PopNx MCP
Se muestran los primeros 8000 caracteres · Abrir el archivo completo en GitHub
---
name: pitchcraft
description: Structured persuasion for tech leads, PMs, and founders—not activity logs. Five scenarios (kickoff, status update, wrap-up, investor pitch, solution selling) on one 5-part framework (Hook→Context→Proposal→Evidence→Ask). AI prompts for missing materials and audience context; pre-submit checklist. Claude Code plugin; Cursor, Codex, and chat via prompts.
---
**Languages:** English (this file) · 简体中文 → `SKILL.zh-CN.md`
# Persuasive briefings · Workflow
## Essence
This is not report writing—it is **persuasion**. In every scenario you do the same thing:
> In limited time, help a specific audience understand context, trust your judgment, and provide the support you need.
## Users & scenarios
| Role | Scenarios | Audience |
|---|---|---|
| Tech lead / engineering manager | Kickoff, milestone review, wrap-up | Business leaders, CTO, PMO |
| PM / product lead | Quarterly review, annual summary, requirements review | Director, VP |
| Founder / business owner | Investor pitch | Investors, partners |
| Pre-sales / solutions | Solution selling | Customer execs, technical evaluators |
---
## Core: 5-part persuasion framework
All briefing types share one backbone; section emphasis differs.
```
Part 1 · Hook
→ Why should they keep listening?
→ Opportunity / pain / urgency
Part 2 · Context
→ What is the situation?
→ What we have done and what we have
Part 3 · Proposal
→ What we will do / did?
→ Scope, path, pace
Part 4 · Evidence
→ Why we can succeed / succeeded?
→ Data, moat, team, cases
Part 5 · Ask
→ What do we need from them?
→ Decision / resources / partnership / investment
```
---
## Briefing types & templates
Each type is an instance of the 5-part framework.
### Project kickoff
**Goal:** Get leadership to approve start and allocate people and budget.
| Part | Section | Focus |
|---|---|---|
| Hook | Background & opportunity | Market, pain, competition, why now |
| Context | What we already have | Team, tech, data, prior assets |
| Proposal | Goals & scope | In/out of scope, milestones |
| Evidence | Why us | Differentiation, moat |
| Ask | Resources & risks | Support needed, top risks and mitigation |
```
# {Project} · Kickoff
## Background & opportunity
{Why now: market, pain, competition—2–4 sentences.
This is the persuasion entry—create “we should do this.”}
## What we already have
{Team, tech, data, business assets—not bragging, but trust.
Pattern: “We already have X, so this is not from zero.”}
## Goals & scope
**In scope**: {capabilities}
**Out of scope**: {explicit exclusions—prevent scope creep}
{Milestones and timeline}
## Why us
{Core difference vs alternatives. Moat: why others can’t or won’t match.}
## Resources & risks
{People / budget / cross-team needs
Top risk and mitigation}
```
### Status update
**Goal:** Convince leaders and stakeholders the work is on track and worth continued investment.
| Part | Section | Focus |
|---|---|---|
| Hook | One-line summary | 1–2 most important facts this period |
| Context | Period context | Position vs last period |
| Proposal | Key progress | By milestone or module |
| Evidence | Key metrics | Progress, quality, efficiency |
| Ask | Risks & decisions | Decisions and coordination needed |
```
# {Project} · Status update
## One-line summary
{1–2 facts; audience grasps core in 10 seconds}
## Key progress
{Completed items and metrics by milestone or module}
## Risks & response
Formula per item: {symptom} → {root cause} → {mitigation} → {status}
Decisions: options + recommendation—no open homework:
❌ "Dependency X uncertain—please advise"
✅ "Dependency X slipped 2 weeks. Option A (add people) vs B (move milestone). Recommend A; need Team Y support."
## Next phase
| Item | ETA | Dependencies | Risk |
|---|---|---|---|
```
### Wrap-up / annual review
**Goal:** Show delivered value and assets retained.
| Part | Section | Focus |
|---|---|---|
| Hook | Goal attainment overview | Did we succeed overall? |
| Context | Original goals | What we committed to |
| Evidence | Quantified outcomes | Data-led |
| Proposal | Lessons & assets | What remains |
| Ask | Next phase or handoff | What happens next |
```
# {Project} · Wrap-up / {Year} annual review
## Goal attainment
| Goal | Target | Actual | % | Notes |
|---|---|---|---|---|
Underperformance: root cause and improvement—say it before they ask.
## Core deliverables
3–5 items, each: {what} + {metric} + {business impact}
## Lessons
- **What worked**: reusable methods / architecture / process
- **What failed**: root cause + prevention
- **Assets left**: code / data / docs / team capability
## Next
If continuing → direction, goals, key results, resources
If ending → handoff so nothing is left unsupported
```
### Investor pitch
**Goal:** Spark interest for a deeper conversation.
| Part | Section | Focus |
|---|---|---|
| Hook | One-liner | Elevator pitch |
| Context | Market opportunity | Size, pain, why now |
| Proposal | Product | Solution, core features, stage |
| Evidence | Moat & traction | Tech, data, growth, team |
| Ask | Funding / partnership | Amount, use, milestones |
```
# {Project} · Pitch
## One-liner
{What we do, for whom, what value}
## Market opportunity
{Size, persona, pain, why now}
## Product
{How we solve, core features, architecture (brief), stage}
## Moat & traction
**Moat**: {tech / data / network / team—why others can’t}
**Metrics**: {users, growth, retention, revenue}
**Team**: {why this team can execute}
## Funding ask
{Amount, use of funds, milestones, next round goal}
```
### Solution selling
**Goal:** Convince customer executives your solution is the best fit.
| Part | Section | Focus |
|---|---|---|
| Hook | Pain alignment | Their problem in their words |
| Context | Current state | Gaps in status quo |
| Proposal | Solution | How we solve |
| Evidence | Cases & data | Proof |
| Ask | Partnership | How to start |
```
# {Project} · Proposal
## Pain alignment
{Customer language for the problem—accuracy builds trust fast}
## Current state
{Why status quo fails: features, cost, efficiency, risk}
## Our solution
{How we solve; capabilities and differentiation}
## Proof
{Same-industry cases with metrics}
{If no case: POC plan or demo roadmap}
## Partnership
{Engagement model, timeline, what we need from them}
```
---
## Writing rules
### 1. Their concerns first, your story second
❌ Five minutes on how hard the team worked and how clever the architecture is
✅ First sentence answers “why should I care?”
### 2. Risks need judgment
❌ "Servers occasionally timeout—please monitor"
✅ "Connection pool exhaustion; scaling in progress; expected recovery tomorrow"
### 3. Acknowledge peer teams first
❌ "We filled a gap no one else addressed"
✅ "Team X has a mature Y; we extend with Z"
### 4. Metrics need source and definition
❌ "Conversion improved 20%"
✅ "Conversion +20% (June vs May, same account pool)"
### 5. Bad news early when it matters
❌ Wins first, then buried "but we slipped"
✅ Lead with material risks, then progress
### 6. No homework for the audience
❌ "Next: keep pushing forward"
✅ "Integration Wed; risk is dependency Y—owner aligned"
---
## Workflow
```
Step 1 — Load memory
Read leader context, business positioning, format prefs.
Missing → ask user to supply.
Step 2 — Scenario & audience
User picks type (kickoff / status / wrap-up·annual / pitch / solution selling).
Probe audience:
□ Role and level?
□ How much do they already know?
□ Top concerns (tech / business / cost / time)?
Step 3 — Material intake
Check completeness by type; ask for gaps:
Kickoff:
□ Background / market analysis
□ Competitive landscape
□ Team capabilities
□ Goals and KPIs
□ Resources and budget
□ Timeline
Status:
□ Completed work this period
□ Key metrics (progress / quality / efficiency)
□ Risk list with judgment and mitigation
□ Next-phase plan
□ Decisions needed frPregunta, comparte un consejo o avisa de que no funciona. Ordenado por lo que la gente marcó como útil.
Aún no hay publicaciones. Sé la primera persona en preguntar o compartir.
Lo publicado aquí lo escriben usuarios, no el equipo de PopNx.