본문으로 건너뛰기
cccskills
무료GitHub에 공개

necessary-work

Use when work is about to grow past the ask, the task may already be done, or the user requests only the minimum. Not for executing the work: use tdd to build or strike-the-root to fix.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(2)

  • SKILL.md3.9 KB
  • agents/openai.yaml181 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Necessary work

Contract

FieldBound contract
TriggerWork is about to grow past the ask, the task may already be done, or the user requests the minimum, only what is needed, or a stop once it works.
AuthorityRead-only. No file, VCS, credential, paid, published, deployed, or remote mutation. Reads and assesses request, environment, policy, and evidence only.
Side effectNarrow the scope of work by classification only; produce no operational side effect.
DoneThe contract is written before work, every admitted action fails the delete test, and classification stops once the minimum proof is identified.

Inputs

Supply the request and the available evidence of its current state. Include any binding environmental limits or authoritative policies that constrain the outcome. Existing measurements are optional; do not create measurements unless the delete test establishes that they are necessary. If the request is ambiguous and the available inputs cannot resolve it, use the smallest interpretation consistent with the stated intent and record that interpretation.

Procedure

  1. Write the contract before admitting work: state the requested outcome and the minimum evidence that would prove it. Done when: the outcome and its proof requirement are stated in writing.
  2. Enumerate only candidate actions that could close a stated outcome or proof gap. Treat no action as automatically necessary because it is useful, conventional, safer, cleaner, or more thorough. Done when: every plausible candidate is listed and none is admitted by default.
  3. For each candidate c, apply the delete test: if deleting c would leave the contract unmet or unproven, admit only the smallest reliable form of c; otherwise reject it. Done when: every candidate has an admit-or-reject decision with its delete-test result.
  4. Admit a limit, threshold, retry, budget, abstraction, artifact, check, process, or follow-up only when its necessity comes from the request, the environment, authoritative policy, or measured evidence. Done when: every admitted action has a named necessity source.
  5. Classify the admitted and rejected candidates without executing them or changing any state. Do not widen scope or invent evidence when an input is missing. Done when: the classification is complete and no state has changed.
  6. Stop as soon as the admitted actions and minimum proof are sufficient for the contract. Do not add speculative follow-up work. Done when: the minimum sufficient set is identified and no further candidate is considered.

Failure and recovery

  • Unresolved ambiguity: bind the smallest interpretation consistent with stated intent, identify the ambiguity in the output, and do not widen the contract.
  • Missing necessity source: reject the candidate and name the absent request, environmental limit, authoritative policy, or measured evidence; do not invent support for it.
  • Insufficient available evidence: return blocked with the exact unproven part of the contract and the missing evidence; do not claim completion or perform a new check under this read-only authority.
  • Accidental scope admission: remove any candidate that does not fail the delete test and recompute the minimum set. Because this procedure makes no mutations, rollback is not required.

A partial classification may be returned only with unresolved items named; it is not a successful result unless the done predicate holds.

Output

A scope decision: outcome, minimum proof, admitted actions (each with its contract gap), rejected candidates (each with its delete-test result), and status (sufficient, already done, or blocked), ordered by the procedure steps that produced them.

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