skills/feasibility-study/SKILL.md
Feasibility analysis from first principles. Use when: evaluating solutions before tech-spec, comparing approaches, risk assessment. Not for: implementation (use feature-dev), architecture advice (use codex-architect). Output: quantitative comparison + recommendation.
npx skillsauth add sd0xdev/sd0x-dev-flow feasibility-studyInstall 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.
For each solution option, dispatch background exploration:
Agent({
description: "Explore feasibility of solution option",
subagent_type: "feasibility-analyst",
prompt: Research the feasibility of: <solution description> Evaluate technical feasibility, effort, risk, extensibility, and maintenance cost.
})
/deep-analyze)/codex-implement)/codex-explain or /codex-architect)Decompose → Constraints → Code research → Solutions → Codex discussion → Decision → Report
Input source priority:
canonical_docs.requirements is non-null → consume as authoritative requirement source, validate via 5-WhyUse "5 Why" to uncover essence:
Inventory constraints by type (Technical, Business, Resource, Compatibility) with flexibility rating.
Research existing codebase:
Brainstorm 2-3+ solutions, each with:
references/analysis-phases.md)⚠️ Core step — not optional (unless --no-codex) ⚠️
See references/codex-discussion-guide.md for full rules and examples.
| Tool | Purpose | When |
|------|---------|------|
| /codex-brainstorm | Enumerate all options | At start |
| /codex-architect | Evaluate design | After proposal forms |
| mcp__codex__codex-reply | Ask details | Anytime |
Side-by-side comparison → recommendation + backup + open questions.
| Dimension | Green | Yellow | Red | | --------------------- | ----- | ------ | --- | | Technical Feasibility | Has existing patterns | Needs adaptation | Major innovation | | Effort | < 3 person-days | 3-10 person-days | > 10 person-days | | Risk | Small scope | Some uncertainty | Many unknowns | | Extensibility | Easy to extend | Needs refactoring | Hard to extend | | Maintenance Cost | Clean, easy | Some complexity | Complex |
## Feasibility Study: <title>
### Quantitative Comparison
| Criterion | Option A | Option B | Option C |
|-----------|----------|----------|----------|
### Recommendation
<selected option with rationale>
--no-codex)references/analysis-phases.mdreferences/codex-discussion-guide.mdreferences/output-template.md/feasibility-study → /tech-spec → /deep-analyze → /codex-implement
Input: /feasibility-study "Add user quota management"
Action: 5 Why → constraints → code research → 3 solutions → Codex discussion → recommendation
Input: /feasibility-study "Optimize cache" --context src/service/cache.ts
Action: Read cache code → constraints → solutions → Codex brainstorm → comparison → report
documentation
Rewrite the previous reply in Traditional Chinese
development
Monitor GitHub Actions CI runs until completion. Use when: watching CI after push, checking build status, monitoring PR checks, waiting for CI completion, user says 'watch CI', 'check CI', 'CI status', 'monitor build', or /watch-ci. Not for: pushing code (use push-ci), creating PRs (use create-pr). Output: per-run verdict (pass/fail/timeout).
development
Verification loop — lint -> typecheck -> unit -> integration -> e2e
development
Research current code state then update corresponding docs, ensuring docs stay in sync with code.