skills/requirements/SKILL.md
Use when you need to discover hidden requirements, risks, or edge cases.
npx skillsauth add seokan-jeong/team-shinchan team-shinchan:requirementsInstall 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.
Look for brainstorm output in the current session:
If .shinchan-docs/*/brainstorm-output.md exists:
Read the brainstorm output.
Note to user: "Prior brainstorm found — using it to seed the requirements interview."
Include in Misae's prompt: "A brainstorm was completed. Summary: [brainstorm-output content]. Use this as context for the requirements interview."
Else:
Note to user: "No prior brainstorm found. For deeper requirements coverage, consider running /team-shinchan:brainstorm first. Continuing with requirements interview."
(Continue to Step 1 regardless — brainstorm is optional)
If args is empty or only whitespace:
Ask user: "What feature or task would you like me to analyze for hidden requirements?"
STOP and wait for user response
If args length > 2000 characters:
Truncate to 2000 characters
Warn user: "Request was truncated to 2000 characters"
Do not read further. Execute this Task NOW:
Task(
subagent_type="team-shinchan:misae",
model="sonnet",
prompt=`/team-shinchan:requirements has been invoked.
## Hidden Requirements Analysis Request
Analyze the request to discover:
| Category | Analysis Focus |
|----------|----------------|
| Hidden Requirements | Unstated needs, implicit expectations |
| Edge Cases | Boundary conditions, unusual inputs |
| Risks | Potential problems, failure scenarios |
| Dependencies | Prerequisites, blocking items |
| Scope | Clarifications needed, ambiguities |
## Analysis Areas
- Error handling scenarios
- Performance implications
- Security considerations
- User experience impacts
- Maintenance burden
- Integration points
## Output Requirements
- Show analysis process in real-time
- List all hidden requirements found
- Prioritize risks by impact
- Provide specific recommendations
- Note any clarifications needed from user
User request: ${args || '(Please describe what to analyze)'}
`
)
STOP HERE. The above Task handles everything.
development
Deterministic adversarial code review for high-stakes scope — independent per-dimension review, a non-skippable per-finding refutation, a completeness critic, and a schema-validated rubric judge. Opt-in main-loop Workflow tier.
data-ai
Deterministic loop-until-done for high-stakes long-running tasks — a worker/verifier loop the script bounds by iteration cap, token budget, and stagnation, closed by an Action-Kamen gate. Opt-in main-loop Workflow tier.
testing
Deterministic adversarial debate for high-stakes or irreversible decisions — mandatory refutation plus a scored judge panel. Opt-in main-loop Workflow tier.
development
Deterministic competitive code tournament — N builders independently solve one task and return patches, an Action-Kamen judge scores them head-to-head, the winner is picked by score and applied. Opt-in main-loop Workflow tier.