agent-workflow
Run Frontier's inspect, route, implement, and verify workflow.
Skill by yousofdavamkar
Chalk Labs
Need help deploying agent-workflow?
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/yousofdavamkar-agent-workflow
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: frontend, productivity, agent-building
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-workflow
What's inside
- Skill name
agent-workflow- Description
- Run Frontier's inspect, route, implement, and verify workflow. Use when an agent is planning or executing a frontend repository change with the Frontier CLI.
- License
- MIT
- Instructions
- 11 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- openai.yaml · agents/
- frontier.skill.yaml
SKILL.md (first lines)
# Agent Workflow 1. Run `frontier context --task "<task>"` and inspect the returned profile, skills, and sources. 2. Inspect affected code, nearby tests, components, tokens, and public contracts. 3. For meaningful journeys, define problem, target user, desired outcome, states, constraints, and verification. 4. Implement the minimum complete solution using routed skills. 5. Web-search returned source URLs and official documentation only when guidance may have changed or local evidence is insufficient. 6. Record consulted sources and unresolved uncertainty; never claim a search occurred when it did not. 7. Run `frontier check --changed`, `frontier test --affected`, then `frontier verify --changed` before completion.
From yousofdavamkar/frontier, MIT.
More from yousofdavamkar/frontier
- 0.519score
user-flow
yousofdavamkar
Design and review multi-step user flows, navigation changes, forms, onboarding, checkout, and recovery paths.
SkillBFreshness: BClaude Code +9 - 0.519score
react
yousofdavamkar
Apply React-native component, state, effect, rendering, and composition conventions.
SkillBFreshness: BClaude Code +9 - 0.519score
tdd
yousofdavamkar
Select behavior-first verification for frontend bug fixes, new behavior, API integrations, refactors, styling, animation, SEO, and performance work.
SkillBFreshness: BClaude Code +9 - 0.519score
semantic-html
yousofdavamkar
Choose semantic HTML and native browser controls for pages, forms, navigation, content structure, and interactive components.
SkillBFreshness: BClaude Code +9 - 0.519score
animation-review
yousofdavamkar
Design and review frontend motion, transitions, gestures, and reduced-motion behavior.
SkillBFreshness: BClaude Code +9 - 0.519score
typescript
yousofdavamkar
Model frontend data, state, component APIs, and integration boundaries with TypeScript.
SkillBFreshness: BClaude Code +9 - 0.516score
visual-quality
yousofdavamkar
Review hierarchy, spacing, typography, color, depth, responsive composition, and interaction feedback in frontend UI.
SkillBFreshness: BClaude Code +9 - 0.516score
product-brief
yousofdavamkar
Create a lightweight implementation-ready product brief for new journeys, pages, navigation, data collection, monetization, or ambiguous frontend features.
SkillBFreshness: BClaude Code +9 - 0.516score
browser-testing
yousofdavamkar
Verify critical frontend journeys in a real browser, including navigation, responsive behavior, focus, rendering, and integrations.
SkillBFreshness: BClaude Code +9 - 0.516score
accessibility
yousofdavamkar
Implement and verify accessible frontend interactions, forms, navigation, overlays, and visual redesigns.
SkillBFreshness: BClaude Code +9 - 0.516score
css-engineering
yousofdavamkar
Engineer maintainable, responsive CSS using existing tokens and repository styling conventions.
SkillBFreshness: BClaude Code +9 - 0.516score
performance
yousofdavamkar
Measure and improve frontend loading, rendering, interaction, asset, and bundle performance.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 1, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/yousofdavamkar/frontier
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from yousofdavamkar
- 0.519score
user-flow
yousofdavamkar
Design and review multi-step user flows, navigation changes, forms, onboarding, checkout, and recovery paths.
SkillBFreshness: BClaude Code +9 - 0.519score
semantic-html
yousofdavamkar
Choose semantic HTML and native browser controls for pages, forms, navigation, content structure, and interactive components.
SkillBFreshness: BClaude Code +9 - 0.519score
react
yousofdavamkar
Apply React-native component, state, effect, rendering, and composition conventions.
SkillBFreshness: BClaude Code +9 - 0.519score
tdd
yousofdavamkar
Select behavior-first verification for frontend bug fixes, new behavior, API integrations, refactors, styling, animation, SEO, and performance work.
SkillBFreshness: BClaude Code +9 - 0.519score
animation-review
yousofdavamkar
Design and review frontend motion, transitions, gestures, and reduced-motion behavior.
SkillBFreshness: BClaude Code +9 - 0.519score
typescript
yousofdavamkar
Model frontend data, state, component APIs, and integration boundaries with TypeScript.
SkillBFreshness: BClaude 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 agent-workflow 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
agent-workflow skill. Agent Mart. https://agentmart.dev/skills/yousofdavamkar-agent-workflow (last updated 2026-10-24)