본문으로 건너뛰기
cccskills
무료GitHub에 공개

learning-retrospective

Use when asked to review learning progress after a milestone. Not for engineering retrospectives, use engineering-retrospective. For agent-environment ones, use agent-environment-retrospective.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(2)

  • SKILL.md3.8 KB
  • agents/openai.yaml137 B

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Learning retrospective

Contract

FieldBound contract
TriggerReview learning progress after a milestone.
AuthorityRead-only. No file, VCS, credential, paid, published, deployed, or remote mutation.
Side effectConversation artifact only.
DoneA learning retrospective, adjusted plan, and measurable next milestone.

Inputs

  • Milestone or learning plan (required): the goal, topic, or checkpoint under review.
  • Evidence of progress (required): completed exercises, notes, project artifacts, or session records that demonstrate what was attempted and what was produced.
  • Current plan or curriculum (optional): the existing learning plan, if one exists, to be adjusted.

Procedure

  1. Confirm read-only authority. Done when: read-only authority is confirmed and no mutation has been performed.
  2. Collect the milestone definition and all supplied evidence of progress. If evidence is absent or insufficient, stop and report the gap; do not invent evidence. Done when: the milestone definition and all supplied evidence are collected, or the gap is reported and the run stops.
  3. Review the evidence against the milestone criteria. Classify each criterion as met, partially met, or unmet, citing the specific artifact or record that supports the classification. Done when: every milestone criterion is classified with a cited supporting artifact or record.
  4. Identify gaps between the milestone definition and the observed evidence. For each gap, state what was expected and what was actually produced. Done when: every gap is stated with its expected and observed values.
  5. Analyze which learning strategies, resources, or approaches were effective and which were not, grounded only in the supplied evidence. Done when: each strategy is assessed as effective or not with its evidentiary basis.
  6. Propose adjustments to the learning plan: what to continue, what to change, what to drop, and what to add. Each adjustment must cite the evidence that motivates it. Done when: every adjustment is stated with its motivating evidence cited.
  7. Define the next milestone. It must be specific, measurable, and achievable based on the current trajectory. State the success criteria explicitly. Done when: the next milestone is stated with explicit, measurable success criteria.
  8. Assemble the learning-retrospective report per the Output section. Done when: the report is assembled with all five Output sections present.

Failure and recovery

  • Insufficient evidence: report which criteria cannot be evaluated and why. Do not fill gaps with assumptions. Ask the learner to supply missing artifacts before proceeding.
  • No existing plan: proceed with the learning retrospective using the milestone and evidence alone. Propose an initial plan as part of the adjusted plan output.
  • Conflicting evidence: surface the conflict, state both interpretations, and ask the learner to clarify before finalizing the learning retrospective.
  • Scope creep detected: if the review expands beyond the stated milestone, stop and report that the scope has widened. Recommend a separate learning-retrospective for the additional scope.

Output

A learning-retrospective report containing:

  1. Evidence review: classification of each milestone criterion (met / partially met / unmet) with cited evidence.
  2. Gap analysis: what was expected versus what was observed.
  3. Strategy assessment: which approaches worked, which did not, and why, grounded in evidence.
  4. Adjusted plan: concrete changes to the learning plan, each motivated by evidence.
  5. Next milestone: a specific, measurable goal with explicit success criteria.

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