to-task

Distil the chat discussion so far (or a roadmap item) into .task/task/<slug>.md — ## Description only, no ## Plan. Lightest of the three capture skills (to-task / to-plan / to-roadmap): use it to record the "what and why" before implementing directly, or before to-plan later. The written file is the handle — no active-task pointer, no separate execution skill; a fresh session implements it by reading ## Execution.

Input: $ARGUMENTS — optional. Recognized forms:

• (empty) — draft from the chat discussion so far.
• <roadmap-slug> or <roadmap-slug>#<N> — open from that roadmap item instead of the chat.
• anything else — free-form context to fold into the draft alongside the chat discussion.

Step 0: Setup gate

Resolve the pipeline root, then check whether its CLAUDE.md exists:

source "${CLAUDE_PLUGIN_ROOT}/skills/_lib/resolve-ws.sh"   # sourcing runs find_ai_dir → sets AI_DIR
echo "$AI_DIR"                                             # the resolved root — use this value verbatim in every artifact path below
[[ -f "$AI_DIR/CLAUDE.md" ]] || echo "CLAUDE.md not found"

The helper walks task.root git config when that path already holds a .task/CLAUDE.md → ancestor .task/CLAUDE.md (the walk stops at the top of this project, so it never claims a neighbouring one's .task/) → dirname(git-common-dir)/.task → $CLAUDE_PROJECT_DIR/.task when that path already holds a CLAUDE.md → ./.task. Use ${CLAUDE_PLUGIN_ROOT} — a bare skills/… path resolves against the user's project cwd, where it does not exist.

The echoed value is normally absolute. In a project that is not a git repository and has no .task/ yet it can be the bare relative .task — the historical default; treat that as "unconfigured" and let the inline setup below establish <ROOT>/.task, rather than writing a cwd-relative artifact from a subdirectory.

Once .task/CLAUDE.md exists, every artifact path in this skill is under that resolved $AI_DIR, never the cwd — .task/task/<slug>.md below is shorthand for $AI_DIR/task/<slug>.md. A cwd-relative write from a subdirectory or a linked worktree would create a second .task/ that validate.sh (which resolves $AI_DIR itself) never sees. The inline setup below is the one exception: it runs before a root exists, writes to <ROOT>/.task, and records git config task.root "$ROOT" — which is exactly what $AI_DIR resolves to on every later run.

• Absent → inline setup. Read ${CLAUDE_PLUGIN_ROOT}/skills/_lib/setup.md and follow it: detect the stack → write $AI_DIR/CLAUDE.md from its template → record git config --local task.root → exclude .task → report what was written. No confirmation chip: the file is written first and edited afterwards if a detected value came out wrong. setup.md is the single source of truth for the sub-steps and for the .task/CLAUDE.md template — do not restate either here. Then continue with the original $ARGUMENTS unchanged.
• Present → leave it alone. The file is user-owned: never rewrite it, never re-detect its values, never "repair" a section you find missing. Only the two markers are restored silently when absent: git config --local task.root and the .task line in .git/info/exclude. To regenerate the file from scratch, the user deletes it and re-runs any capture.

There is no full-scan validate call here — the file this run writes is validated after the write (Step 2.5 / Step 1a.6), and pre-existing artifacts are checked on demand with validate.sh all, never as an entry gate.