ds-plan
REQUIRED Phase 2 of /ds workflow. Profiles data and creates analysis task breakdown.
npx skills add majiayu000/claude-skill-registry --skill ds-plan-edwinhu-workflows-3 --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
Profiles the data and creates an analysis task breakdown, following Phase 2 of the DS workflow. It requires that a SPEC file exists at .planning/SPEC.md from /ds before planning, and it produces an ordered set of analysis tasks based on profiling and data quality checks.
How it works
- Verifies that .planning/SPEC.md exists before planning. If missing, it instructs to stop and run /ds first.
- Performs data profiling for one or more data sources, in parallel when supported, collecting shape, dtypes, sample data, statistics, quality checks, and, for time-series, date ranges.
- Identifies data quality issues (missing values, duplicates, outliers, type issues, cardinality, distribution).
- Evaluates ETL strategy considerations (filters, parallelism, intermediate caching, and scale-up testing) and documents decisions in a PLAN.md-like plan when applicable.
- For each expensive or multi-source task, asks the user to specify scale-up decisions and to document filters, parallelism, and caching in the plan.
- Enforces that profiling is completed and SPEC exists before proceeding to plan creation, per the explicit checks in the workflow section.
When to use it
- When you need to profile data and create an ordered task breakdown for DS Phase 2, given that SPEC.md exists and Phase 2 prerequisites are met.
What it can touch
- Tools indicated for profiling are not directly listed in this excerpt beyond the general workflow, but the skill specifies use of a profiling & planning approach requiring a SPEC file and documenting plan elements.
Caveats
- Requires the SPEC.md file to exist before planning; otherwise, it instructs to stop and run /ds first.
- The workflow emphasizes documenting plans and decisions (PLAN.md) and does not proceed to implementation without explicit steps and approvals.
Announce: "Using ds-plan (Phase 2) to profile data and create task breakdown." ## Contents - [The Iron Law of DS Planning](#the-iron-law-of-ds-planning) - [What Plan Does](#what-plan-does) - [Process](#process) - [Red Flags - STOP If You're About To](#red-flags---stop-if-youre-about-to) - [Output](#output) ## Context Monitoring | Level | Remaining Context | Action | |-------|------------------|--------| | Normal | >35% | Proceed normally | | Warning | 25-35% | Complete current profiling task, then trigger ds-handoff | | Critical | ≤25% | Immediately trigger ds-handoff — do not start new profiling | # Planning (Data Profiling + Task Breakdown) Profile the data and create an analysis plan based on the spec. **Requires `.planning/SPEC.md` from /ds first.** <EXTREMELY-IMPORTANT> ## The Iron Law of DS Planning **SPEC MUST EXIST BEFORE PLANNING. This is not negotiable.** Before exploring data or creating tasks, you MUST have: 1. `.planning/SPEC.md` with objectives and constraints 2. Clear success criteria 3. User-approved spec **If `.planning/SPEC.md` doesn't exist, run /ds first.** </EXTREMELY-IMPORTANT> ### Rationalization Table - STOP If You Think: | Excuse | Reality | Do Instead | |-
- Contents
- Context Monitoring
- The Iron Law of DS Planning
- Rationalization Table - STOP If You Think:
- Drive-Aligned Framing
- Drive-Aligned Framing (Consequences)
- No Pause After Completion
- What Plan Does
- Process
- 1. Verify Spec Exists
- 2. Data Profiling
- 3. Identify Data Quality Issues
- 4. ETL Strategy Assessment (Conditional)
- ETL Rationalization Table - STOP If You Think:
cat .planning/SPEC.md # verify-spec: read SPEC file to confirm it exists
What does the ds-plan skill do?
REQUIRED Phase 2 of /ds workflow. Profiles data and creates analysis task breakdown.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ds-plan-edwinhu-workflows-3 --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.