agentsclimarketplace

Playbook writer

Skill tuliosousapro/SaaS-blueprint/skills/playbook-writer

Meta-skill that generates compliant PLAYBOOK.md files following the BRAINIAC template. Use when creating or editing modules in the command center. For general readme creation, see create-readme.From its SKILL.md

Install
npx -y skills add tuliosousapro/SaaS-blueprint --skill playbook-writer

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.4 KB, 752 tokens by cl100k_base, as published. Nobody here has run it

Playbook Writer Skill

When to Use

  • When a directory has no PLAYBOOK.md or has generic boilerplate
  • When rewriting existing playbooks to match PLAYBOOK_TEMPLATE.md
  • When adding new modules to the command center

Tools Required

ToolPurpose
view_fileRead PLAYBOOK_TEMPLATE.md for format compliance
write_to_fileCreate or overwrite the PLAYBOOK.md
view_fileRead adjacent playbooks for cross-references

Instructions

1. Read the Template

Always start by reading BRAINIAC/PLAYBOOK_TEMPLATE.md to ensure format compliance.

2. Gather Context

Before writing, determine:

  • Phase: Which lifecycle phase (Idea, Validation, Planning, etc.)
  • Module: The specific subdirectory (Problem Discovery, Market Research, etc.)
  • Phase Index: The numbered prefix (0. Idea, 1. Validation, etc.)
  • Module Position: Where this module sits in the phase sequence
  • APP_NAME: The user's SaaS product name (from GEMINI.md or user input)

3. Determine Prerequisites

Scan the phase directory:

  • List all sibling modules
  • Check which modules logically precede this one
  • Check cross-phase dependencies (e.g., Development depends on Planning)
  • Read adjacent PLAYBOOK.md files for cross-reference links

4. Write Module-Specific Content

CRITICAL RULES:

  • NO BOILERPLATE. Every section must contain content specific to THIS module.
  • Action steps must name the specific tool, MCP, or agent to use.
  • Vibe Coding Prompts must include {PLACEHOLDERS} for user-specific context.
  • Success Criteria must be binary pass/fail — never subjective vibes.
  • Deliverables must be concrete files, documents, or decisions.

Anti-patterns to AVOID:

BAD:  "Define the MVP for Frontend."
GOOD: "Create a component inventory listing every UI screen, with wireframe references from Design/Wireframes/."

BAD:  "Track the metrics."
GOOD: "Set up Posthog/Mixpanel tracking for: signup rate, activation rate, D7 retention. Export dashboard link to this directory as METRICS.md."

BAD:  "Generate a robust, production-ready implementation plan."
GOOD: "Using Next.js 15 App Router, scaffold the authenticated dashboard layout with sidebar navigation. Include: /dashboard, /settings, /billing routes. Use Supabase Auth for session management."

5. Validate Before Saving

Checklist before writing the file:

  • Every section from PLAYBOOK_TEMPLATE.md is present
  • Objective is exactly one sentence
  • Deliverables are checkboxes with concrete outputs
  • Prerequisites table references real modules with correct paths
  • Action Steps each specify Tool/Agent, Input, Output
  • Agent Context table lists actual MCPs, skills, and workflows
  • Vibe Coding Prompts use {PLACEHOLDERS}
  • Success Criteria are binary pass/fail
  • Cross-References link to real adjacent playbook paths

6. Save

Write the file to BRAINIAC/{Phase}/{Module}/PLAYBOOK.md, overwriting any existing boilerplate.

Quality Gates

  • Zero generic sentences (grep for "ship fast", "no fluff", "pour gasoline" — these are boilerplate markers)
  • Every action step maps to a tool or agent
  • Cross-references resolve to existing files

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most docs writing skills give in 752 tokens

Counted across 1,951 of the 3,904 authors here whose files we hold, read 2026-09-06

  • Use third-person for skill descriptionsin 54 of 1951, across 35 files
  • Start descriptions with Use whenin 43 of 1951, across 29 files
  • Run baseline scenarios before writing any skillin 40 of 1951, across 26 files
  • Use active voicein 40 of 1951, across 36 files
  • Map file responsibilities before defining tasksin 36 of 1951, across 29 files
  • Use checkbox syntax for tracking stepsin 35 of 1951, across 27 files
  • Ask one question at a timein 35 of 1951
  • Offer execution options after saving the planin 33 of 1951, across 24 files
  • Include complete code in every stepin 33 of 1951, across 27 files
  • Design units with clear boundaries and interfacesin 31 of 1951, across 23 files
  • Announce the skill usage at the startin 30 of 1951
  • Verify agent compliance after adding the skillin 29 of 1951, across 17 files

Said here and by no other author read

  • Identify phase and module context
  • List all sibling modules
  • Check cross-phase dependencies
  • Include specific tool or agent for action steps
  • List concrete files or documents as deliverables
  • Validate all sections against the template

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 611,884. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.