본문으로 건너뛰기
cccskills
무료GitHub에 공개

wait-what

Use when the user says "wait, what", "the explanation is unclear", "say that again", or asks to restate the last response in plain language. Not for tasks that require source or remote-system changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(2)

  • SKILL.md3.7 KB
  • agents/openai.yaml209 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Wait, what

Contract

FieldBound contract
TriggerUser says "wait, what", "I don't follow", "say that again", "the explanation is unclear", or "restate in plain language".
AuthorityRead-only. No file, VCS, credential, paid, published, deployed, or remote mutation.
Side effectRestates the same claim without softening; nothing touches disk.
DoneThe claim is re-pitched with the missing frame supplied, in plain English and the project''s ubiquitous language.

Inputs

The trigger identifies which explanation failed. Read CONTEXT.md if it exists; no external file is required when it is absent. Read the per-context CONTEXT.md beside the relevant source when the project keeps a CONTEXT-MAP.md. If no CONTEXT.md or CONTEXT-MAP.md exists, use the names already in the code.

Entry phrasings

One skill, three entry phrasings, one mechanism: re-pitch the same claim with the missing frame supplied in plain language:

  • "wait, what" or "say that again": the explanation did not land. Re-pitch the same claim, preserving its substance and conclusions, and lead with the context the explanation assumed.
  • "the explanation is unclear" or "context was omitted": the prior explanation skipped background, definitions, assumptions, causal links, or prerequisite steps. Re-pitch from scratch in plain language, embedding the missing context at the point where the original jumped ahead.
  • "restate in plain language" or "bro": restate the last response concisely without jargon. Preserve the original meaning and add no new claims, opinions, or information beyond the source response.

All three produce one plain-language re-pitch in chat. None touches disk.

Procedure

  1. Identify the explanation that did not land: the last assistant message immediately before the trigger. Done when: the failed explanation is identified.
  2. Restate the same claim, preserving its substance and conclusions. Do not soften, hedge, or replace it with an easier version. Done when: the claim is restated with substance and conclusions intact.
  3. Re-pitch it: lead with the context the explanation assumed (one or two sentences on where the conversation is and what the message was answering: the gap is a missing frame, not a missing word); write in ISO 24495-1 English (short sentences, active voice, direct address, common words replacing jargon); use the project''s ubiquitous language. Done when: the claim is re-pitched with the missing frame supplied in plain English and ubiquitous language.

Failure and recovery

  • Non-converged: the user signals they do not understand after one re-pitch. Stop. Do not elaborate, restate a third time, or widen scope. The user is the authority on whether the explanation landed. Report non-converged.
  • No prior explanation or response: if no prior assistant message exists to re-pitch or restate, stop and report that there is nothing to restate. Do not invent a prior explanation.
  • Ambiguous confusion signal: if the user's indication is unclear about which part was hard to follow, ask which part of the prior explanation was unclear before re-pitching.
  • Scope creep: if the re-pitch would require teaching an entire prerequisite topic, state the prerequisite boundary and offer to cover it separately. Do not widen into a tutorial.
  • Clean re-pitch: keep the re-pitch free of caveats, meta-commentary, or references to the original explanation's failure.

Output

A single re-pitched message in the conversation, in plain English with the missing context supplied.

리뷰

아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.

댓글

로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.

아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.

보내면 바로 공개됩니다. 이메일 주소나 전화번호 같은 개인 정보는 쓰지 마세요. URL은 2개까지입니다.

0 / 1,000자

이 양식은 reCAPTCHA로 보호되며 Google 개인정보처리방침 및 서비스 약관이 적용됩니다.

같은 저장소의 스킬

Use when explaining System V AMD64, ARM AAPCS, RISC-V psABI, stack frames, variadic calls, or FFI register rules. Not for the Rust FFI binding layer: use rust-ffi.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when configuring ADC sampling time, DMA-driven ADC, calibration, or DAC channel setup on bare-metal MCUs. Not for the DMA stream itself: use dma-baremetal.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

af-xdp

무료

Use when creating AF_XDP sockets, configuring UMEM and XSK rings, writing an XDP redirect program, or choosing copy versus zero-copy mode. Not for full kernel bypass: use dpdk.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when a completed session needs an agent-environment retrospective. Not for an engineering retrospective from telemetry: use engineering-retrospective.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

Use when a redacted, trimmed agent transcript must be appended to a GitHub PR or issue body, with human approval and preview. Not for automated or model-initiated insertion.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

agents-md

무료

Use when a repo needs agent setup, AGENTS.md added or made lean, CLAUDE.md audited, or agent instructions scored or pruned. Not for remote, credential, publish, deploy, or irreversible changes.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

OutlineDriven/odin-claude-plugin372026년 9월 29일 업데이트

OutlineDriven의 스킬 모두 보기

이 스킬의 문제 신고