agentleFS
sd0xdevsd0xdev/sd0x-dev-flow/skills/project-brief/SKILL.md

project-brief

Skill192 starsChanged 37 days agoMITView on GitHub

Convert a technical spec into a PM/CTO-readable executive summary. Simplify technical details, focus on business value.

10 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Document review (use /codex-review-doc)

    line 17
  2. Distinctive:

    Read the specified tech spec file

    line 55
  3. Distinctive:

    Remove internal module names

    line 70
  4. Distinctive:

    Remove technical implementation details

    line 71
  5. Distinctive:

    Keep business logic descriptions

    line 72
  6. Very specific:

    If $ARGUMENTS contains --output <path>, save to the specified location.

    line 119

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

Project Brief

Trigger

  • Keywords: executive summary, project brief, PM summary, CTO summary, project-brief

When NOT to Use

  • First-principles briefing (use /fp-brief)
  • Technical spec writing (use /tech-spec)
  • Document review (use /codex-review-doc)

Agent Dispatch

Agent({
  description: "Convert technical spec into PM/CTO executive summary",
  subagent_type: "brief-writer",
  prompt: `Convert the following tech spec into a PM/CTO-readable executive summary.
Follow the conversion rules and execution flow defined in this skill.`
})

Input

$ARGUMENTS

Conversion Rules

Tech Spec SectionPM/CTO Summary Treatment
Trust boundary diagramSimplify to 3-layer arch
Code analysisRemove
Reusable modulesRemove
System architectureKeep (simplified)
Implementation roadmapKeep
Key design decisionsRemove
Alternative comparisonKeep
Risks & mitigationsKeep
TimelineKeep
Immediate actionsSimplify to decision points

Execution Flow

Step 1: Read Technical Spec

  • Read the specified tech spec file
  • Identify the core value proposition

Step 2: Extract Key Information

  • Project overview: one sentence on what, why, and value
  • Current state vs target comparison
  • Solution evaluation (keep pros/cons comparison)
  • Milestone timeline
  • Risk summary
  • Resource requirements

Step 3: Simplify Technical Details

  • Remove code snippets
  • Remove internal module names
  • Remove technical implementation details
  • Keep business logic descriptions

Step 4: Produce Executive Summary

Output

# [Project Name] Executive Summary

## Project Overview
> One sentence: what, why, and value

## Current State vs Target
| Dimension | Current | Target |
|-----------|---------|--------|

## Solution Evaluation
| Solution | Pros | Cons | Recommendation |
|----------|------|------|----------------|

## Architecture Overview
(Simplified system diagram, 3 layers max)

## Milestones
| Week | Deliverable | Dependencies |
|------|-------------|--------------|

## Risk Summary
| Risk | Impact Level | Mitigation |
|------|-------------|------------|

## Resource Requirements
- **Headcount**:
- **Timeline**:
- **External Dependencies**:

## Decision Points
> Items requiring PM/CTO decision
- [ ] Decision 1:
- [ ] Decision 2:

Save

By default, save to the same directory as the original file with a -brief suffix. Example: docs/features/xxx/architecture.md -> docs/features/xxx/architecture-brief.md

If $ARGUMENTS contains --output <path>, save to the specified location.

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.