Chalk Labs
Need help deploying doit?
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/1jaypeng-doit-713b88
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: testing, productivity
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
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/doit
What's inside
- Skill name
doit- Description
- Spec-driven TDD workflow. Auto-classifies simple/feature/bug. Triggers: 我想做, 帮我加, 我需要, add feature, implement, I want to, build.
- License
- unknown
- Instructions
- 97 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions call the network
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Agent Skills spec issues
- name: "doit" does not match folder "doit-skill"
Files (98)
- settings.json · .claude/
- .gitignore
- doit.md · .omp/commands/
- doit-workflow.md · .omp/rules/
- CLAUDE.md
- LEAN-CTX.md
- README.md
- README_ZH.md
- SKILL.md
- README.md · adapters/
- claude-code.md · adapters/
- codex.md · adapters/
- default.md · adapters/
- jcode.md · adapters/
- mimo-code.md · adapters/
- oh-my-pi.md · adapters/
- opencode.md · adapters/
- background-process.md
- classifier.md
- codegraph.md
- doit.md · commands/
- commit.md
- e2e.md · core/
- env-check.md · core/
- execute.md · core/
- iron-rules.md · core/
- phase-0.md · core/
- phase-1.md · core/
- phase-10.md · core/
- phase-9.5.md · core/
- plan.md · core/
- review.md · core/
- commit.md · core/shared/
- e2e-verify.md · core/shared/
- phase-gate.md · core/shared/
- review-simplify.md · core/shared/
- subagent.md · core/
- team-roles.md · core/
- workflow.md · core/
- dangerous-ops.md
- debug.md
- README.md · dist/
- build.sh · dist/
- doc-capture.md
- MULTI-MODEL.md · docs/
- OMP-DEEP-ADAPTATION.md · docs/
- doit-config.md
- e2e.md
- errors.md
- headroom.md
- mempalace.md
- package.json
- plan.md
- principles.md
- review-simplify.md
- review.md
- add-dependency.sh · scripts/
- caveman-addon.toml · scripts/addons/caveman/
- code-review-addon.toml · scripts/addons/code-review/
- codegraph-addon.toml · scripts/addons/codegraph/
- …and 38 more
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from 1JayPeng/doit-skill
- 0.492score
deep-grill
1JayPeng
Deep-grill a plan, belief, or design through a 4-phase interrogation loop: Deconstruct (first principles) → Cross-examine (Socratic) → Rebuild → Meta.
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
deep-grill-cn
1JayPeng
四阶段追问引擎:解构(第一性原理)→ 交叉审问(苏格拉底)→ 重建 → 元审视。 用于压力测试想法、发现盲点、挑战假设、逼近基本面真相。 触发词:"deep-grill-cn"、"拷问我"、"深度追问"、"拆解一下"、"压力测试"、"追问到底"。
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
knowledge-distillation
1JayPeng
Extract and reuse knowledge from doit sessions.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
tdd
1JayPeng
Test-driven development with red-green-refactor loop.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
improve-codebase-architecture
1JayPeng
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill-me
1JayPeng
Interview the user relentlessly about a plan or design.
SkillCFreshness: C★ 1Claude Code +9 - 0.456score
handoff
1JayPeng
Compact the current conversation into a handoff document for another agent to pick up.
SkillCFreshness: C★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit
- Jul 30, 2026 (3 months ago)
- Last release
- Jul 26, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/1JayPeng/doit-skill
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
More from 1JayPeng
- 0.492score
deep-grill
1JayPeng
Deep-grill a plan, belief, or design through a 4-phase interrogation loop: Deconstruct (first principles) → Cross-examine (Socratic) → Rebuild → Meta.
SkillCFreshness: C★ 1Claude Code +9 - 0.489score
deep-grill-cn
1JayPeng
四阶段追问引擎:解构(第一性原理)→ 交叉审问(苏格拉底)→ 重建 → 元审视。 用于压力测试想法、发现盲点、挑战假设、逼近基本面真相。 触发词:"deep-grill-cn"、"拷问我"、"深度追问"、"拆解一下"、"压力测试"、"追问到底"。
SkillCFreshness: C★ 1Claude Code +9 - 0.488score
knowledge-distillation
1JayPeng
Extract and reuse knowledge from doit sessions.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
tdd
1JayPeng
Test-driven development with red-green-refactor loop.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
improve-codebase-architecture
1JayPeng
Find deepening opportunities in a codebase, informed by the domain language in CONTEXT.md and the decisions in docs/adr/.
SkillCFreshness: C★ 1Claude Code +9 - 0.467score
grill-me
1JayPeng
Interview the user relentlessly about a plan or design.
SkillCFreshness: C★ 1Claude 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 doit 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
doit skill. Agent Mart. https://agentmart.dev/skills/1jaypeng-doit-713b88 (last updated 2026-10-24)