# Feasibility

> Decide whether a task should be fixed and whether the proposed approach is acceptable. Use when the user asks for steward feasibility or wants a first maintainer decision.

- Skill: `samzong/feasibility` (Agent Skill)
- Install (CLI): `npx skillmds@latest add samzong/feasibility`
- Raw SKILL.md: https://api.skillmd.com/api/skills/samzong/feasibility/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Productivity
- Author: samzong (https://skillmd.com/u/samzong)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/samzong/feasibility

---


# Feasibility

Use this skill for the Steward feasibility decision.

## First Step

Read `../../shared/protocol.md` before acting. Treat it as the source of truth for case file discovery, state transitions, update rules, and output.

## Gate

Run only the `feasibility` gate.

## Behavior

- Decide whether the task should be fixed.
- Decide whether the proposed approach is acceptable.
- Identify the smallest acceptable fix.
- Call out wrong premises directly.
- Apply the Requirement Deletion Lens from the shared protocol before accepting
  a proposed solution.
- If re-running and a feasibility entry already exists, show the previous verdict for comparison.
- If positive, set status to `execute`.
- If negative, record the final negative verdict and make the next action `stop` unless specific evidence remains missing.
- If no valid case file exists, auto-create a minimal case file first, write it to the current pointer, then run feasibility.
- Do not drift into implementation.

## Output

Use the protocol output contract:

```md
Verdict: <short sentence>
Why: <short paragraph>
Missing evidence: <short list or "None">
Next action: <one concrete next step>
Case file: <absolute path>
```