본문으로 건너뛰기
cccskills
무료GitHub에 공개

codexkit-report-summarizer

Condense long reports, documents, or data exports into structured summaries with key findings, implications, and recommended actions. Use when the work is distilling dense content for busy readers. Do not use for original analysis, strategy formulation, or when the source material needs expert interpretation beyond summarization.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

설치 방법 보기

포함된 파일(5)

  • SKILL.md3.9 KB
  • agents/openai.yaml174 B
  • examples/common-mistakes.md894 B
  • examples/good-output.md1.5 KB
  • verification/checklist.md1.4 KB

SKILL.md(원문)

설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.

Report Summarizer

Purpose

Transform lengthy documents into actionable summaries that respect the reader's time and attention.

When to use

  • condensing a long report for executive review
  • extracting key points from research, audits, or analysis documents
  • creating pre-read summaries for meetings
  • summarizing vendor proposals, competitive analyses, or market reports

When not to use

  • the document needs original analysis, not summarization
  • technical accuracy requires domain expertise the agent lacks
  • the summary replaces reading the source for compliance or legal reasons

Inputs

  • source document or report (paste text or describe contents)
  • target audience (executive, peer, team, external)
  • desired summary length (one-pager, 3-bullet, paragraph)
  • focus areas if specific (e.g. "focus on financials" or "skip methodology")
  • format preference (bullets, narrative, table)

Procedure

  1. Identify the document's purpose and core thesis.
  2. Extract key findings, data points, and conclusions.
  3. Note any recommendations, action items, or decisions embedded in the source.
  4. Structure the summary: what (findings) → so what (implications) → now what (actions).
  5. Calibrate detail level to the target audience.
  6. Flag anything notable that was omitted from the summary.

Output

  • structured summary (format per user preference)
  • key findings list
  • recommended actions or decisions (if present in source)
  • "what was left out" note (for transparency)

Definition of done

  • summary can be read in under 2 minutes
  • no critical points from the source are missing
  • the reader can decide whether to read the full document based on the summary
  • action items are preserved with owners and timelines if mentioned

Examples

  • "Summarize this 40-page market research report into a one-page executive brief."
  • "Extract the top 5 findings from the quarterly budget review and list recommended actions."
  • "Create a 3-bullet pre-read summary of the vendor evaluation document for tomorrow's meeting."
  • "Condense this audit report into key risks and remediation priorities."

Quality Criteria

  • The summary preserves the source's core thesis, key findings, numbers, and conclusions.
  • The output separates source-backed facts from interpretation or recommended action.
  • The length and detail match the requested audience and format.
  • Important caveats, omitted sections, and uncertainty are visible.
  • No unsupported assertions or generic filler language are introduced.

Verification (4C)

CheckQuestion
CorrectnessAre all findings, numbers, names, and recommendations faithful to the source?
CompletenessAre the main argument, evidence, implications, actions, and caveats covered?
Context-fitIs the summary calibrated to the reader's role, time, and decision need?
ConsequenceWhat could be misinterpreted if the reader skips the source and acts only on this summary?

Edge Cases

  • Source is too long for one pass — Summarize by section and list any skipped portions explicitly.
  • Report mixes facts and opinion — Label each recommendation as source-stated or inferred.
  • Audience has mixed expertise levels — Use a top summary first, then optional detail.
  • Legal, financial, or compliance report — Preserve caveats and recommend expert review before action.

Changelog

  • v1.1.0 — Added source-faithful summarization quality gates and edge cases.
  • v1.0.0 — Initial release

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

Design rigorous A/B test plans with hypothesis, sample size calculation, Minimum Detectable Effect (MDE), randomization strategy, and decision rules. Includes guardrail metrics and rollout playbook. Use when planning product experiments, conversion optimization, or data-driven feature decisions.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hoavdc/CodexKit252026년 10월 11일 업데이트

Review REST and GraphQL API designs for consistency, usability, and best practices. Covers naming conventions, versioning strategy, error format, pagination, authentication patterns, and breaking change detection. Use when reviewing API specs, designing new APIs, or auditing existing endpoints.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hoavdc/CodexKit252026년 10월 11일 업데이트

Write Architecture Decision Records (ADRs) following the Michael Nygard format. Captures context, options considered, decision rationale, and consequences. Use when making technology choices, framework selections, or any architectural decision that future developers need to understand.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hoavdc/CodexKit252026년 10월 11일 업데이트

Assess organizational readiness for financial audits (internal or external). Map assertions to account balances, check evidence completeness, score readiness using a Red/Amber/Green framework, and generate a remediation timeline. Aligned with SOX, IFRS, and GAAP audit standards. Use before scheduled audits or when preparing for first-time compliance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hoavdc/CodexKit252026년 10월 11일 업데이트

Design safe recurring Codex automations with clear prompts, outputs, schedules, and gating rules.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hoavdc/CodexKit252026년 10월 11일 업데이트

Refine Product Backlog Items to meet INVEST criteria. Write User Stories with Acceptance Criteria in Given/When/Then format, estimate with Story Points, and flag dependencies. Use before sprint planning when backlog items need grooming. Do not use to prioritize the backlog — that is the Product Owner's decision.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

hoavdc/CodexKit252026년 10월 11일 업데이트

hoavdc의 스킬 모두 보기

이 스킬의 문제 신고