clarifyUse when the user's request is ambiguous — vague asks, polysemous instructions, unclear scope — BEFORE committing to a feature. Two-track loop (one question at a time + parallel codebase exploration) producing a Context Brief that becomes the SSOT for the follow-up work.
debugUse when code behaves differently from expectations — 'why does this happen', 'find the bug', 'follow the callstack', symptom reports even without the word debugging. Blackbox methodology: AS-IS/TO-BE confirmation, callstack tracing recorded in a CWD-relative trace file, red-green fix.
do-workUse when a trace.md with unfinished scenarios exists and the user wants autonomous implementation — 'continue the work', 'implement the traced feature', or after a bundle was selected. Accepts an explicit bundle contract (trace_path + scenario_ids); scans for ready scenarios only when no contract is
excalidraw-diagramCreate Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.
exploreUse when the problem is vague, the domain unfamiliar, multiple approaches are possible, or the user says 'investigate first' / 'before we spec this'. Read-only stance (not a workflow): no code changes, no mandatory artifacts; exits to spec/debug/clarify/direct implementation when insight crystallize
new-taskUse when the user gives a vague or high-level feature request that needs decomposition into implementable work — new ideas, '~만들어줘' with implicit requirements, features with multiple possible approaches. NOT for specific 1-2 file changes, obvious bug fixes, quick questions, or when spec/trace alread
plan-new-taskUse when the trace backlog has ZERO unfinished scenarios (or the user explicitly asks for new feature ideas) and the project needs its next feature proposed. Hands the chosen idea to new-task for spec + trace.
specUse when requirements and architecture need explicit definition before tracing — a new feature interview, or updating an existing spec.md (Update vs New). STV Phase 1: Proposal (WHY) -> Explore First (mandatory unknowns map) -> interview -> docs/{feature}/spec.md.
thinkUse when the user wants real-world experience turned into a methodology, skill, or process — 'turn this into a methodology', 'systematize my approach', 'make this into a skill', or after stv:explore / completed work when raw practice should become reusable structure. Bottom-up inductive distillation
traceUse when a spec.md exists and per-scenario vertical traces + RED contract tests must be derived — or an existing trace.md needs Delta Protocol updates. STV Phase 2: spec.md -> docs/{feature}/trace.md, 7+1-section format with parameter transformation arrows.
using-terminal-chartsThis 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",
verifyUse when a PR must be checked against its issue/spec before merge — 'check the PR', 'is it implemented per the issue', 'compare spec vs implementation', 'verify', 'validate'. Final 3D conformance gate (Completeness/Correctness/Coherence). Inputs: issue (URL or contents) + PR URL.
what-to-workUse when you do not know what to work on next, the user asks 'what should I work on' / '뭐하지', or a session starts over an existing STV backlog. Routes to what-we-have-to-work when ANY unfinished scenario exists, or plan-new-task when the backlog is empty.
what-we-have-to-workUse when unfinished trace scenarios exist and the next execution scope must be chosen. Bundles leftovers of ANY size into 1-3 options and hands the selected bundle contract (trace_path + scenario_ids) to do-work.
workUse when trace scenarios need implementation to GREEN plus trace-conformance verification — invoked with a trace path and OPTIONAL scenario_ids for targeted execution. STV Phase 3.