spec-kitty-research（规格小猫研究）

🔗 Workflow Provenance

Source: This skill augments the baseline workflow located at ./workflows/spec-kitty.research.md. It acts as an intelligent wrapper that is continuously improved with each execution.

Path reference rule: When you mention directories or files, provide either the absolute path or a path relative to the project root (for example, kitty-specs/<feature>/tasks/). Never refer to a folder by name alone.

In repos with multiple features, always pass --feature <slug> to every spec-kitty command.

Location Pre-flight Check

BEFORE PROCEEDING: Verify you are working in the project root checkout.

pwd
git branch --show-current

Expected output:

• pwd: Should end with your project root directory path
• Branch: Should show your feature branch name like 001-feature-name (NOT main)

If you see the main branch or the wrong directory path:

⛔ STOP - You are in the wrong location!

This command creates research artifacts in your feature directory. You must be in the project root checkout.

Correct the issue:

1. Navigate to your project root checkout: cd /path/to/project/root
2. Verify you're on the correct feature branch: git branch --show-current
3. Then run this research command again

What This Command Creates

When you run spec-kitty research, the following files are generated in your feature directory:

Generated files:

• research.md – Decisions, rationale, and supporting evidence
• data-model.md – Entities, attributes, and relationships
• research/evidence-log.csv – Sources and findings audit trail
• research/source-register.csv – Reference tracking for all sources

Location: All files go in kitty-specs/<feature-slug>/

Workflow Context

Before this: /spec-kitty.plan calls this as "Phase 0" research phase

This command:

• Scaffolds research artifacts
• Creates templates for capturing decisions and evidence
• Establishes audit trail for traceability

After this:

• Fill in research.md, data-model.md, and CSV logs with actual findings
• Continue with /spec-kitty.plan which uses your research to drive technical design

Goal

Create research.md, data-model.md, and supporting CSV stubs based on the active mission so implementation planning can reference concrete decisions and evidence.

What to do

1. You should already be in the correct project root checkout (verified above with pre-flight check).
2. Run spec-kitty research to generate the mission-specific research artifacts. (Add --force only when it is acceptable to overwrite existing drafts.)
3. Open the generated files and fill in the required content:

- research.md – capture decisions, rationale, and supporting evidence. - data-model.md – document entities, attributes, and relationships discovered during research. - research/evidence-log.csv & research/source-register.csv – log all sources and findings so downstream reviewers can audit the trail.

1. If your research generates additional templates (spreadsheets, notebooks, etc.), store them under research/ and reference them inside research.md.
2. Summarize open questions or risks at the bottom of research.md. These should feed directly into /spec-kitty.tasks and future implementation prompts.

Success Criteria

• kitty-specs/<feature>/research.md explains every major decision with references to evidence.
• kitty-specs/<feature>/data-model.md lists the entities and relationships needed for implementation.
• CSV logs exist (even if partially filled) so evidence gathering is traceable.
• Outstanding questions from the research phase are tracked and ready for follow-up during planning or execution.