ds-implement
REQUIRED Phase 3 of /ds workflow. Enforces output-first verification at each step.
npx skills add majiayu000/claude-skill-registry --skill ds-implement-edwinhu-workflows-2 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Apply output-first verification at every step of analysis implementation. This is Phase 3 of the /ds workflow.
How it works
- Enforces that EVERY code step MUST produce visible output by requiring run, output, verification, and documentation before moving on.
- Uses delegation: for every task in PLAN.md, the lead dispatches a subagent per ds-delegate patterns; main chat does not contain analysis code.
- Requires printing state before and after each operation, verifying, and recording LEARNINGS.md entries.
- Provides a strict protocol for how to spawn analysts, verify outputs, and log results, including a mandatory task-by-task log format and self-verification checklist.
- Guides the flow through a detailed implementation process: read PLAN and delegation skill, execute tasks via delegation, and log findings, with a no-pause rule between tasks.
When to use it
Use when implementing Phase 3 of /ds workflow to ensure verifiable, output-first progress across all analysis steps, and when coordination across multiple analysts is needed.
What can touch
- Tools declared in the skill: claude-code is listed as a declared tool.
- Interaction patterns: Read calls to the PLAN and delegation SKILL, per the implementation steps.
Caveats
- Requires strict adherence to output-first protocol; failure to produce visible outputs halts progress.
- Enforcement of delegation means analysis code should not be written in the main chat; must be dispatched to task agents.
- No speculation about outcomes; only documented observations and verifications per step are allowed.
## Overview Apply output-first verification at every step of analysis implementation. This is Phase 3 of the `/ds` workflow. ## Contents - [The Iron Law of DS Implementation](#the-iron-law-of-ds-implementation) - EVERY step MUST produce visible output - [Delegation](#delegation) - Main chat orchestrates, subagents analyze - [What Output-First Means](#what-output-first-means) - [Red Flags](#red-flags---stop-immediately) - [Implementation Process](#implementation-process) - [Verification Patterns](#verification-patterns) - See `references/verification-patterns.md` - [Common Failures](#common-failures-to-avoid) - [Gate: Exit Implementation](#gate-exit-implementation) # Implementation (Output-First Verification) Implement analysis with mandatory visible output at every step. **NO TDD** - instead, every code step MUST produce and verify output. <EXTREMELY-IMPORTANT> ## The Iron Law of DS Implementation **EVERY CODE STEP MUST PRODUCE VISIBLE OUTPUT. This is not negotiable.** Before moving to the next step, you MUST: 1. Run the code 2. See the output (print, display, plot) 3. Verify output is correct/reasonable 4. Document in LEARNINGS.md 5. Only THEN proceed to next step This applies eve
- Overview
- Contents
- The Iron Law of DS Implementation
- Delegation
- What Output-First Means
- Red Flags - STOP Immediately
- Implementation Strategy Choice
- Implementation Process
- Step 1: Read Plan and Delegation Skill
- Step 2: Execute Each Task via Delegation
- Step 3: Log to LEARNINGS.md
- Verification Patterns
- Common Failures to Avoid
- If Output Looks Wrong
What does the ds-implement skill do?
REQUIRED Phase 3 of /ds workflow. Enforces output-first verification at each step.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ds-implement-edwinhu-workflows-2 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.