本文へ移動
cccskills
無料GitHub で公開

apa-formatting

Format, repair, and audit APA Style seventh-edition papers, author-date citations, and reference lists. Use for APA student or professional manuscripts, quotations, missing reference metadata, DOI handling, and APA generative-AI attribution. NOT for MLA or Chicago formatting, general prose editing, finding evidence for unsupported claims, or certifying rendered layout from plain text.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/windags-skillsスター 17(GitHub 17 + cccskills 0)

実行スコア 未検証

インストール方法を見る

含まれるファイル(10)

  • SKILL.md7.6 KB
  • CHANGELOG.md406 B
  • examples/activation-evals.md1.7 KB
  • examples/worked-examples.md3.8 KB
  • README.md494 B
  • references/citations.md4.4 KB
  • references/layout.md4.9 KB
  • references/reference-patterns.md5.5 KB
  • references/sources.md7.2 KB
  • templates/student-paper.md1.6 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

APA Formatting

Turn supplied writing and verified source metadata into APA seventh-edition output. Guidance checked 2026-10-25. The seventh edition remains current; online APA updates supplement the manual. Consult references/sources.md when a rule is disputed, time-sensitive, or outside the examples.

When to use

Activate for explicit APA formatting, APA citation repair, an APA reference list, or a comparison that needs the APA side. For MLA output use the MLA skill; for an unspecified citation style, establish the required style before converting anything. Do not silently rewrite claims, invent research, or treat a formatting request as permission to submit an assignment or publish a document.

Core process

flowchart TD
  A[Read assignment and requested output] --> B{APA required?}
  B -->|No| C[Route to requested style or clarify]
  B -->|Yes| D[Identify student or professional and local rules]
  D --> E[Inventory source metadata and quotations]
  E --> F{Enough verified information?}
  F -->|No| G[Mark gaps and request only necessary details]
  G --> H[Format supported portions]
  F -->|Yes| H
  H --> I[Reconcile citations and reference entries]
  I --> J{Rendered document available?}
  J -->|Yes| K[Inspect layout and report observed checks]
  J -->|No| L[Provide content and layout instructions with limits]
  1. Set the contract. Read the rubric, journal instructions, edition, paper type, and target format. Local requirements may override APA defaults; label each departure. For coursework use student setup unless professional setup is required. When only a citation is requested, deliver the citation directly.
  2. Separate evidence from presentation. Record author order, date, title, source type, container, volume/issue/pages or article number, publisher, and DOI/URL as applicable. Verify against the source or publisher record when available. Record whether each detail was supplied, independently verified, or unresolved. Never manufacture a locator, author, DOI, date, or quotation.
  3. Choose the needed reference. Read references/layout.md for paper structure and appearance; references/citations.md for attribution and quotations; references/reference-patterns.md for source types, missing metadata, DOI/URL decisions, and current AI guidance.
  4. Apply and reconcile. Preserve meaning and verified quotations. Cross-check every recoverable cited work against the references, and every reference against an actual citation. Account explicitly for personal communications and secondary-source exceptions. Check author spellings, years/suffixes, author order, quotation locators, title capitalization, italics, and link destinations.
  5. Verify the deliverable at its actual level. A text review can check citation consistency; only the final document can show margins, headers, page breaks, fonts, spacing, and table overflow. When tools permit, render and inspect the DOCX/PDF in its target application. State exactly what was inspected. A regex, Markdown preview, or citation-manager export does not establish compliance.

Output contract

Scale the response to the task. A single reference needs the entry, its in-text form, and any consequential uncertainty. A paper audit or conversion returns:

  • Corrected content or a clearly named artifact; distinguish a scaffold from a formatted document.
  • Assumptions: edition, student/professional, local overrides, and output format.
  • A short correction log for material changes, with rule/source links when useful.
  • Missing or unverifiable details, named precisely; use conspicuous placeholders in drafts and keep unresolved entries out of a claimed submission-ready artifact.
  • Verification scope: content checks performed; rendered checks observed; remaining layout checks. Never say “APA compliant” when only plain text was available.

Use examples/worked-examples.md for finished small examples and an audit handoff. Use templates/student-paper.md only to start a student paper's content; its comments require actual word-processor settings.

Anti-patterns

Put a running head on every student paper

Novice: Apply a professional title page and an abstract to all assignments. Expert: Establish the paper type and rubric first; student defaults differ. Timeline: Seventh-edition guidance introduced a separate student setup in 2019; current online instructions retain that distinction. See the layout reference.

Use the in-text author limit in the reference list

Novice: Change every three-author reference to “et al.” Expert: In-text abbreviation and reference-list author transcription have separate rules; preserve source order and resolve ambiguous shortened citations. Timeline: Seventh-edition in-text rules differ from sixth-edition first-citation rules. See the citations and reference-patterns references.

Cite AI using an undated remembered recipe

Novice: Always copy the archival 2023 ChatGPT example, or assume a citation makes AI use permissible. Expert: Check current official guidance, distinguish a helpful shareable chat from general tool use, and apply the institution/publisher policy independently. Timeline: APA replaced the 2023 post with a September 2025 series. Recheck it when handling AI; do not invent a model version or tool-update date.

Treat typography instructions as rendered proof

Novice: Declare a Markdown scaffold submission-ready after checking punctuation. Expert: Report content validation separately from observations of the final file. Inspect page headers, styles, breaks, and tables after conversion. Timeline: This is a format boundary, not an edition change.

Bundle guide

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

コメント

ログインなしで書き込めます。使ってみた感想、質問、動かなかった環境などを気軽にどうぞ。

まだコメントはありません。最初のコメントを書いてみませんか。

送信するとすぐに公開されます。メールアドレスや電話番号などの個人情報は書かないでください。URL は 2 つまでです。

0 / 1000 文字

このフォームは reCAPTCHA で保護されており、Google のプライバシーポリシーと利用規約が適用されます。

同じリポジトリのスキル

Expert in 2000s-era music visualization (Milkdrop, AVS, Geiss) and modern WebGL implementations. Specializes in Butterchurn integration, Web Audio API AnalyserNode FFT data, GLSL shaders for audio-reactive visuals, and psychedelic generative art. Activate on "Milkdrop", "music visualization", "WebGL visualizer", "Butterchurn", "audio reactive", "FFT visualization", "spectrum analyzer". NOT for simple bar charts/waveforms (use basic canvas), video editing, or non-audio visuals.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/windags-skills172026年10月26日 更新

Expert legal research agent for finding and scraping expungement data state by state. Knows authoritative sources, URL patterns, Firecrawl configuration, and 2026 legal landscape.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/windags-skills172026年10月26日 更新

Expert in 3D computer vision labeling tools, workflows, and AI-assisted annotation for LiDAR, point clouds, and sensor fusion. Covers SAM4D/Point-SAM, human-in-the-loop architectures, and vertical-specific training strategies. Activate on '3D labeling', 'point cloud annotation', 'LiDAR labeling', 'SAM 3D', 'SAM4D', 'sensor fusion annotation', '3D bounding box', 'semantic segmentation point cloud'. NOT for 2D image labeling (use clip-aware-embeddings), general ML training (use ml-engineer), video annotation without 3D (use computer-vision-pipeline), or VLM prompt engineering (use prompt-engineer).

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/windags-skills172026年10月26日 更新

Apply crisis decision-making research to agent routing, uncertainty triage, and coordination failure analysis in time-pressured systems. Use when diagnosing handoff failures, analytical paralysis, or expert judgment under incomplete information. NOT for routine coding, simple CRUD design, or static single-agent tasks with complete information.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/windags-skills172026年10月26日 更新

Use for insight, reframing, contradiction, impasse, and anomaly-driven problem solving when execution effort no longer helps. NOT for routine optimization, error correction, or well-specified tasks with known solution paths.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/windags-skills172026年10月26日 更新

Apply normative BDI reasoning to agents that must detect norms, choose which commitments to internalize, and resolve conflicts by comparing consequences. Use when obligations, prohibitions, or policies collide in autonomous systems. NOT for simple fixed-priority rules, pure constraint satisfaction, or domains where no real normative conflict exists.

日本語の概要は準備中です。原文の説明を表示しています。

curiositech/windags-skills172026年10月26日 更新

curiositech のスキルをすべて見る

このスキルの問題を報告する