
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'.
Autonomous work execution on STV-traced scenarios. Selects unfinished scenarios from trace.md, implements via stv:work, loops until done or user input needed.
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.
유저의 요구가 불명확할때 트리거. 애매한 요청, 다의적 지시, 범위 불분명한 작업에서 Context Brief를 생성하여 명확화한다.
STV Phase 2: spec.md -> vertical trace + RED contract tests. Traces every API scenario through all layers with 7-section format and parameter transformation arrows. Supports Delta Specs change tracking for trace evolution over time.
Trigger this skill in any situation where code behaves differently from expectations like "why does this happen", "find the bug", "form a hypothesis", "follow the callstack", "trace back from the result". Even without the explicit word "debugging", trigger on symptom reports.
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).
STV Phase 1: Proposal (WHY) -> Feature interview -> spec.md. PRD + Architecture decisions in one pass. Uses decision-gate to minimize questions. Supports non-linear flow (Actions not Phases) and Update vs New decision tree.
This skill should be used when the user asks to "visualize data", "render a chart", "plot numbers", "show a graph in terminal", "create a bar chart", "make a sparkline", "draw a heatmap", or needs to display numeric data as terminal charts using chartli. Also triggers on "chartli", "terminal chart", "ASCII chart", "braille chart".
Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
Meta-skill for designing methodologies, skills, and processes from experience. Triggers on "I want to turn this into a methodology", "organize this pattern", "systematize my approach", "make this into a skill", "structure this as a process". Use when the user mentions real-world experience and wants to structure/systematize/formalize it. Not top-down design from theory, but bottom-up distillation that strips away the unnecessary from what actually worked.
Propose new features when all trace scenarios are complete or backlog is too small. Reviews completed work and project context, then applies stv:new-task to create spec + trace for chosen feature.
Bundle unfinished trace scenarios into up to three candidate work chunks, present options with rationale, and get user confirmation before starting do-work execution.
Trigger when 유저가 뭔가 일을 시키거나, 하이 레벨 컨셉을 이야기 할 경우, 유저의 지시에 여러 가지 암묵지가 느껴질 경우.
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.