ワンクリックで
wtf-wid
WTF was I doing? — a tight, fits-on-screen recap of the current session so you can re-enter in under 10 seconds
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
WTF was I doing? — a tight, fits-on-screen recap of the current session so you can re-enter in under 10 seconds
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Load saved review feedback from /bpe:review and apply changes to the reviewed artifact
Iterative Q&A to develop a thorough project specification (spec.md)
Generate a commit message explaining what was changed and write it to commit-msg.md
Implement the next unchecked step from plan.md by executing its sub-steps as written (RED-GREEN-REFACTOR for Feature steps; Scope/Tooling/Do/Verify/Document for Task steps)
Fetch a GitHub issue and route to brainstorm or plan based on detail level
Autonomous-mode BPE run via /goal. Modes — full (default) | section <name> | step. Pre-flights branch safety (refuses on main), resolves the project verification command (test-runner autodetect, spec.md fallback, or ask), builds a verifiable completion condition, and writes the assembled /goal block (condition + validator-aware orchestrator playbook + per-commit verification) to goal.md at the repo root for you to paste. Requires Claude Code v2.1.139+; put your session in auto mode before pasting for unattended execution.
| name | wtf-wid |
| description | WTF was I doing? — a tight, fits-on-screen recap of the current session so you can re-enter in under 10 seconds |
| model | sonnet |
| disable-model-invocation | true |
Print a tight context-recovery block so the user can re-enter the session without scrolling. The user has stepped away (overnight, days) and needs the current state surfaced fast. No preamble. No closing offer. Just the block.
Why, Open, Refs) first, then trim the Status file list.….The user explicitly cares about the current session, not history. Read sources in this order and privilege the earlier ones:
Problem, Next, Why, and Open.git rev-parse --abbrev-ref HEAD (branch)git status --short (modified/staged/untracked counts + paths)git log -1 --format="%h %s" (last commit, subject only)basename "$PWD" (repo dir name).ai-sessions/handoffs/*.md (most recent) — if present, its focus is a strong signal for Nexttodo.md — first unchecked - [ ] item, only if it matches what's actually in flightplan.md / spec.md — pull Why if the conversation doesn't already supply itDo not synthesize a "current session" from .ai-sessions/session-*.md. Those are past sessions. If you must reference one (cold-start fallback only), label it prev: so the user knows it's historical.
If the current conversation has no substantive content yet (this command is the first or second turn of a fresh session), fall back in this order for Problem / Next:
.ai-sessions/handoffs/.ai-sessions/session-*.md (label prev:)When falling back, make the first line of the block: Source: no live context — recovered from <handoff|prev session|git>.
Render this shape. Omit any optional row when empty — do not print blank values. Align the colons for readability.
Problem: <one-line statement of the active problem, ≤120 chars>
Repo: <repo-dir-name> (<branch>)
Status: <N modified, N staged, N untracked> · <up to 3 most-relevant paths, truncated>
Last: <short-sha> <commit subject ≤80 chars>
Next: <the immediate next action, ≤120 chars>
Why: <optional — motivation behind the work, ≤120 chars>
Open: <optional — unresolved decision or blocker, ≤120 chars>
Refs: <optional — paths to handoff/plan/todo if user should open them>
Field rules:
clean. If dirty, counts + up to 3 paths that best characterize the change. Skip the file list if it would push the line past 144 chars.todo.md item.Problem alone. Often skippable.ls on .ai-sessions/handoffs/ and a Read of todo.md only if they exist.