dev
Full sequential dev pipeline — understand, plan, implement, verify, review
Skill by Hbin77
Chalk Labs
Need help deploying dev?
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/hbin77-dev
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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/dev
What's inside
- Skill name
dev- Description
- Full sequential dev pipeline — understand, plan, implement, verify, review
- License
- MIT
- Instructions
- 40 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
You are executing a full development pipeline. Follow every step in order automatically without asking for confirmation unless genuinely ambiguous. Task: the task/scope the user described when invoking this skill (if none given, ask or infer from context) ## Phase 1: Understand - Scan project structure, tech stack, and architecture patterns. - Find and read the files directly related to the task. - Synthesize findings. ## Phase 2: Design (UI 작업 포함 시에만) Skip entirely for backend-only, bug-fix, or refactor tasks with no UI change. - `design-system/MASTER.md`가 있으면 로드해 재사용 (필요 시 page override 추가). - 없으면 `~/.codex/skills/ui-ux-pro-max/` (reasoning-rules.md → styles.md)로 디자인 토큰을 확정하고 `design-system/MASTER.md`를 생성. - 구현은 MASTER 토큰 100% 준수 (raw hex 금지, 시맨틱 토큰만, 이모지 구조 아이콘 금지, 터치 타겟 ≥44pt). ## Phase 3: Plan Create a brief implementation plan: files to modify, approach, risks. Identify the dependency order of components. ## Phase 4: Implement Implement sequentially, starting with the foundation (types/interfaces → logic → UI). Follow existing project conventions (naming, structure, patterns). ## Phase 5: Verify Run in order and fix failures automatically (up to 3 attempts): build, lint/type-check, tests. For UI changes also run the `/design-audit` checks. ## Phase 6: Review Review your own changes across two lenses: - **Quality**: single responsibility, no duplication, clear naming, proper error handling, no dead code, no N+1 / obvious perf issues, consistent with the codebase. - **Security**: no hardcoded secrets, no injection risks, input validation on external inputs, no sensitive data exposure. Fix any CRITICAL or WARNING findings. ## Phase 7: Finalize Summarize: files changed/created, key decisions, review findings addressed, what to test manually. ## Rules - Do NOT ask for permission between phases — just execute. - If build/test fails, fix it automatically (up to 3 attempts). - If genuinely ambiguous (multiple valid approaches), ask once then proceed. - Commit is NOT included — the user decides when to commit.
From Hbin77/codex-kit, MIT.
More from Hbin77/codex-kit
- 0.518score
qa
Hbin77
Browser QA — automation, accessibility audit, user flow verification
SkillBFreshness: BClaude Code +9 - 0.518score
refactor
Hbin77
Safe, systematic refactoring workflow — same behavior, better structure
SkillBFreshness: BClaude Code +9 - 0.518score
retro
Hbin77
Run a sprint/session retrospective to capture what worked, what didn't, and what to improve.
SkillBFreshness: BClaude Code +9 - 0.518score
design-audit
Hbin77
Audit UI code against ui-ux-pro-max UX guidelines; report by severity
SkillBFreshness: BClaude Code +9 - 0.518score
code-smells
Hbin77
Analyze code for smells, anti-patterns, and refactoring opportunities.
SkillBFreshness: BClaude Code +9 - 0.518score
guard
Hbin77
Activate safety guard mode — restrict edit scope, confirm destructive ops
SkillBFreshness: BClaude Code +9 - 0.518score
design-system
Hbin77
Generate a MASTER design system using the ui-ux-pro-max skill
SkillBFreshness: BClaude Code +9 - 0.518score
explore
Hbin77
Explore and explain the project's architecture and structure
SkillBFreshness: BClaude Code +9 - 0.518score
extract-errors
Hbin77
Parse and analyze error logs, stack traces, and build output to identify and fix issues.
SkillBFreshness: BClaude Code +9 - 0.518score
investigate
Hbin77
Systematically diagnose a bug via structured root cause analysis
SkillBFreshness: BClaude Code +9 - 0.518score
plan
Hbin77
Analyze the project and produce a detailed implementation plan
SkillBFreshness: BClaude Code +9 - 0.515score
browse
Hbin77
Open a URL in a headless browser, screenshot, and report
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 7, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Hbin77/codex-kit
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Hbin77
- 0.518score
extract-errors
Hbin77
Parse and analyze error logs, stack traces, and build output to identify and fix issues.
SkillBFreshness: BClaude Code +9 - 0.518score
investigate
Hbin77
Systematically diagnose a bug via structured root cause analysis
SkillBFreshness: BClaude Code +9 - 0.518score
design-system
Hbin77
Generate a MASTER design system using the ui-ux-pro-max skill
SkillBFreshness: BClaude Code +9 - 0.518score
explore
Hbin77
Explore and explain the project's architecture and structure
SkillBFreshness: BClaude Code +9 - 0.518score
code-smells
Hbin77
Analyze code for smells, anti-patterns, and refactoring opportunities.
SkillBFreshness: BClaude Code +9 - 0.518score
plan
Hbin77
Analyze the project and produce a detailed implementation plan
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 dev 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
dev skill. Agent Mart. https://agentmart.dev/skills/hbin77-dev (last updated 2026-10-24)