skills/create-spec/SKILL.md
Create a task specification (SPEC.md) through interactive requirements elicitation. Use when helping users define what they want to build before autonomous execution begins.
npx skillsauth add srobinson/nancy create-specInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Before asking questions, understand the codebase:
ls -la
git log --format=full -3
find . -type f -name "*.ts" -o -name "*.py" -o -name "*.sh" | head -30
# Task: <name>
## Goal
<clear statement of objective>
## Success Criteria
- [ ] <verifiable outcome 1>
- [ ] <verifiable outcome 2>
## Constraints
- <limitation 1>
## Notes
<implementation guidance if needed>
✅ "All existing tests pass" ✅ "New endpoint returns 200 for valid input" ❌ "Code is clean" (subjective) ❌ "Performance is good" (unmeasurable)
testing
Mark success criteria as complete in SPEC.md. Use when a criterion has been verified and should be checked off.
data-ai
Access session history to continue work, see what happened, or search past sessions. Use this instead of relying on memory - the raw data is always more accurate.
tools
Send a message to the orchestrator. Use for blockers, progress updates, requesting review, or communicating status during autonomous execution.
testing
Check for orchestrator messages.