scout
End-to-end feature orchestrator — grills the user on their idea, writes a PRD, breaks it into issues, and executes them with verified PRs.
Skill by iykazrji
Chalk Labs
Need help deploying scout?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/iykazrji-scout
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
- Runs as
- Shell scripts
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/scout
What's inside
- Skill name
scout- Description
- End-to-end feature orchestrator — grills the user on their idea, writes a PRD, breaks it into issues, and executes them with verified PRs. Supports cmux tab mode and autonomous execution. Use when user wants to go from idea to implementation, says "scout this", or wants the full product development pipeline.
- License
- unknown
- Instructions
- 1,568 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Agent Skills spec issues
- body: 1568 lines (spec recommends under 500)
Files (12)
- .gitignore
- CLAUDE.md
- README.md
- SKILL.md
- DESIGN.md · docs/
- 2026-07-20-warden-panel-protocol.md · docs/plans/
- install.sh
- overview.html
- settings.md
- using-react-native-screen-transitions · skills/
- using-math-curve-loaders
- warden
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from iykazrji/scout
- 0.469score
execute-issues
iykazrji
Execute open GitHub issues from a PRD breakdown — implement each issue as a named Builder agent in isolated branches, create verified PRs, with…
SkillCFreshness: CClaude Code +9 - 0.461score
ui-designer
iykazrji
Platform-agnostic UI design orchestrator — produces visual mockups, design systems, and screen specs via a multi-agent pipeline.
SkillCFreshness: CClaude Code +9 - 0.445score
domain-modeling
iykazrji
Build and sharpen a project's domain model.
SkillCFreshness: CClaude Code +9 - 0.445score
codebase-design
iykazrji
Shared vocabulary for designing deep modules.
SkillCFreshness: CClaude Code +9 - 0.406score
animation-performance
iykazrji
Provides React Native Reanimated, React Native Worklets, React Native Gesture Handler performance optimization guidelines for smooth animations.
SkillDFreshness: DClaude Code +9 - 0.405score
using-react-native-skia
iykazrji
Use when writing SKSL shaders, rendering Skia Canvas content, capturing views as SkImage, handling PixelRatio/supersampling, or building shader-based visual…
SkillDFreshness: DClaude Code +9 - 0.405score
expressjs-best-practices
iykazrji
Express.js best practices for building production-grade REST APIs and web servers.
SkillDFreshness: DClaude Code +9 - 0.405score
grill-me
iykazrji
Use when user wants to stress-test a plan, get grilled on their design, says 'grill me', or wants rigorous interrogation of their thinking before implementation
SkillDFreshness: DClaude Code +9 - 0.402score
reconn
iykazrji
Deep research agent — searches codebase, web, and notes (QMD/claude-mem) for technical context.
SkillDFreshness: DClaude Code +9 - 0.402score
fastify-best-practices
iykazrji
Fastify best practices for building high-performance REST APIs and microservices.
SkillDFreshness: DClaude Code +9 - 0.380score
write-a-prd
iykazrji
Use when the user wants to create a Product Requirements Document, write a PRD, define product requirements, or prepare a feature spec for a GitHub issue.
SkillDFreshness: DClaude Code +9 - 0.165score
vercel-react-best-practices
vercel
React and Next.js performance optimization guidelines from Vercel Engineering.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit
- Jul 21, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/iykazrji/scout
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from iykazrji
- 0.469score
execute-issues
iykazrji
Execute open GitHub issues from a PRD breakdown — implement each issue as a named Builder agent in isolated branches, create verified PRs, with…
SkillCFreshness: CClaude Code +9 - 0.461score
ui-designer
iykazrji
Platform-agnostic UI design orchestrator — produces visual mockups, design systems, and screen specs via a multi-agent pipeline.
SkillCFreshness: CClaude Code +9 - 0.445score
codebase-design
iykazrji
Shared vocabulary for designing deep modules.
SkillCFreshness: CClaude Code +9 - 0.445score
domain-modeling
iykazrji
Build and sharpen a project's domain model.
SkillCFreshness: CClaude Code +9 - 0.406score
animation-performance
iykazrji
Provides React Native Reanimated, React Native Worklets, React Native Gesture Handler performance optimization guidelines for smooth animations.
SkillDFreshness: DClaude Code +9 - 0.405score
grill-me
iykazrji
Use when user wants to stress-test a plan, get grilled on their design, says 'grill me', or wants rigorous interrogation of their thinking before implementation
SkillDFreshness: DClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get scout running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
scout skill. Agent Mart. https://agentmart.dev/skills/iykazrji-scout (last updated 2026-10-24)