decide-before-doing
Use when the user says 先别动手, 先讨论, 先给方案, wait for confirmation, clarify before editing, or when an implementation is ambiguous, risky, broad, multi-step, or…
Skill by Orchardxyz
Chalk Labs
Need help deploying decide-before-doing?
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/orchardxyz-decide-before-doing
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: writing, 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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/decide-before-doing
What's inside
- Skill name
decide-before-doing- Description
- Use when the user says 先别动手, 先讨论, 先给方案, wait for confirmation, clarify before editing, or when an implementation is ambiguous, risky, broad, multi-step, or likely to need user judgment before file edits.
- License
- MIT
- Instructions
- 25 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Decide Before Doing ## Purpose Pause before action when the request is ambiguous, risky, broad, or likely to benefit from user judgment. ## Process 1. Restate the user's goal in one short paragraph. 2. Read the repo or local context needed to separate facts from assumptions. 3. List discovered facts and unresolved assumptions separately. 4. Convert unresolved assumptions into decisions for the user. 5. Recommend one path, with concise alternatives only when the tradeoff matters. 6. Ask for confirmation before editing files, running broad commands, or committing to an implementation path. 7. After confirmation, continue with the appropriate next skill or normal implementation flow. ## Guardrail Do not turn this into endless questioning. Ask only for decisions that materially change the work. Facts should be investigated locally whenever possible. ## Completion Finish when the user explicitly approves a direction, or when the work is blocked on a clear unresolved decision.
From Orchardxyz/agent-skills, MIT.
More from Orchardxyz/agent-skills
- 0.529score
oh-my-posh-setup
Orchardxyz
Set up or troubleshoot a modern Windows terminal environment based on Windows Terminal, PowerShell 7, and oh-my-posh.
SkillBFreshness: BClaude Code +9 - 0.529score
scheduling-codex-window-starts
Orchardxyz
Use when a Codex user wants recurring start points optimized around predictable daily working periods and a rolling usage window.
SkillBFreshness: BClaude Code +9 - 0.529score
skill-comparison
Orchardxyz
Compare multiple similar skills to help users choose the best one for their needs.
SkillBFreshness: BClaude Code +9 - 0.529score
visualizing-leetcode-solutions
Orchardxyz
Use when turning a LeetCode problem and one chosen solution into a step-by-step HTML walkthrough, especially when code alone is hard to follow and the user…
SkillBFreshness: BClaude Code +9 - 0.526score
windows-fe-dev-setup
Orchardxyz
Set up or repair a Windows frontend development environment with NVM for Windows, Node.js 24 LTS, npm, pnpm, Claude Code, Git, VS Code CLI, PowerShell…
SkillBFreshness: BClaude Code +9 - 0.524score
review-to-docs
Orchardxyz
Use when code from another model or engineer needs a durable review artifact, especially when the user asks for docs/reviews, executor review, handoff review…
SkillBFreshness: BClaude Code +9 - 0.524score
executor-plans
Orchardxyz
Use when implementation work will be handed off to another model or engineer, and a decision-complete execution plan needs to be written into docs/plans for…
SkillBFreshness: BClaude Code +9 - 0.524score
executor-reviews
Orchardxyz
Use when code written by another model or engineer needs to be validated and reviewed, and the results must be written into docs/reviews with findings…
SkillBFreshness: BClaude Code +9 - 0.524score
git-conditional-identities
Orchardxyz
Use when Git needs to switch user.name and user.email automatically based on repository location (per-folder identities via includeIf gitdir).
SkillBFreshness: BClaude Code +9 - 0.524score
git-conventions
Orchardxyz
Use when asked for branch names, commit messages, or PR descriptions for code changes.
SkillBFreshness: BClaude Code +9 - 0.524score
codex-proxy
Orchardxyz
Configure Codex to use the machine's proxy by detecting the active proxy on Windows or macOS, validating it, and writing the required variables to…
SkillBFreshness: BClaude Code +9 - 0.515score
ask-orchard
Orchardxyz
Ask which Orchard skill or flow fits the current situation.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 10, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/Orchardxyz/agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from Orchardxyz
- 0.529score
visualizing-leetcode-solutions
Orchardxyz
Use when turning a LeetCode problem and one chosen solution into a step-by-step HTML walkthrough, especially when code alone is hard to follow and the user…
SkillBFreshness: BClaude Code +9 - 0.529score
oh-my-posh-setup
Orchardxyz
Set up or troubleshoot a modern Windows terminal environment based on Windows Terminal, PowerShell 7, and oh-my-posh.
SkillBFreshness: BClaude Code +9 - 0.529score
scheduling-codex-window-starts
Orchardxyz
Use when a Codex user wants recurring start points optimized around predictable daily working periods and a rolling usage window.
SkillBFreshness: BClaude Code +9 - 0.529score
skill-comparison
Orchardxyz
Compare multiple similar skills to help users choose the best one for their needs.
SkillBFreshness: BClaude Code +9 - 0.526score
windows-fe-dev-setup
Orchardxyz
Set up or repair a Windows frontend development environment with NVM for Windows, Node.js 24 LTS, npm, pnpm, Claude Code, Git, VS Code CLI, PowerShell…
SkillBFreshness: BClaude Code +9 - 0.524score
executor-reviews
Orchardxyz
Use when code written by another model or engineer needs to be validated and reviewed, and the results must be written into docs/reviews with findings…
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 decide-before-doing 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
decide-before-doing skill. Agent Mart. https://agentmart.dev/skills/orchardxyz-decide-before-doing (last updated 2026-10-24)