plugins/stv/skills/what-to-work/SKILL.md
Decide what to work on next by scanning docs/*/trace.md for unfinished scenarios, then routing to what-we-have-to-work or plan-new-task.
npx skillsauth add 2lab-ai/oh-my-claude what-to-workInstall 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.
Provide clear, user-confirmable next work options. Scan docs/*/trace.md for unfinished scenarios. If enough work exists, route to stv:what-we-have-to-work. If not, route to stv:plan-new-task.
| Tier | Lines | Example | |--------|--------|--------------------------------------------| | tiny | ~5 | Config values, constants, string literals | | small | ~20 | One function, one file, local refactor | | medium | ~50 | Multiple files, interface changes | | large | ~100 | Cross-cutting concerns, schema migrations | | xlarge | ~500 | Architecture shift, framework replacement |
Scan trace files
docs/*/trace.md in the projectDecide if work exists
Route
Skill(skill="stv:what-we-have-to-work") to propose 1-3 bundlesSkill(skill="stv:plan-new-task") to propose new featuresPresent next action
Trace scan complete: {N} features found, {M} unfinished scenarios
Total estimated work: {tier}
Route: what-we-have-to-work
Next step: I'll bundle scenarios into up to three options for you to pick.
Trace scan complete: {summary}
No meaningful unfinished work found.
Route: plan-new-task
Next step: I'll propose new features based on completed work and project context.
stv:what-we-have-to-work when unfinished scenarios can form a large/xlarge bundlestv:plan-new-task when all scenarios are complete or remaining work is too smallstv:do-work for executiondevelopment
Problem space exploration mode. Stance, not workflow. Read-only codebase investigation before committing to spec. Triggers on 'explore this', 'investigate', 'understand the problem', 'what are we dealing with', 'before we spec this'.
tools
유저의 요구가 불명확할때 트리거. 애매한 요청, 다의적 지시, 범위 불분명한 작업에서 Context Brief를 생성하여 명확화한다.
development
STV Phase 3: Implementation (GREEN) + Trace Verify loop. Implements code to pass contract tests, then verifies implementation matches trace document. Supports non-linear flow — returning to spec/trace when implementation reveals errors in earlier artifacts.
testing
Triggers on "check the PR", "is it implemented per the issue", "compare spec vs implementation", "compare JIRA and PR", "verify", "validate". Final checkpoint before PR merge using 3-dimensional verification (Completeness, Correctness, Coherence).