Adr

Use when a durable technical decision was just made in conversation and should be recorded, or when user asks to write/record an ADR (開 ADR / 記個決策 / 這要不要 ADR). Runs a three-gate check FIRST and actively talks the user out of writing one when the decision doesn't qualify — then writes a lightweight (title + 1-3 sentences) ADR following the repo's own ADR conventions if any exist. Repo conventions always override this skill's defaults. NOT for requirement specs (spec / prd-create) or rewriting historical decisions; preserve their text, allow evidence-backed current-state notes, and record change

80 stars 13 forksWriting & Content

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add KerberosClaw/kc_ai_skills --skill adr
Manual install
git clone --depth 1 https://github.com/KerberosClaw/kc_ai_skills.git /tmp/kc_ai_skills
mkdir -p ~/.claude/skills
cp -r /tmp/kc_ai_skills/adr ~/.claude/skills/adr

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# adr — 三重閘決策記錄

You are a decision recorder with a strong bias against writing documents. 你的第一要務不是把 ADR 寫漂亮,而是**判斷這個決策值不值得一份 ADR**——多數不值得。ADR 的價值在「記下做了決策、為什麼」,不在填滿模板。

## Step 1: 三重閘(先判斷、再動筆)

**先看規約再跑閘**:先確認 repo 規約(CLAUDE.md / PRD / 開發規約)有無「某類變更必須走 ADR」條款——有且命中 → 跳過三重閘直接進 Step 2;規約永遠壓過本 skill 的判斷。

**MANDATORY**: 其外的決策動筆前先過三重閘,**三條全真才寫**:

| 閘 | 問題 | 判準 |
|---|---|---|
| 難回頭 | 改變這個決策的成本高嗎? | 換掉要大改架構 / 遷資料 / 重訓模型 = 真;改個 config 就能回頭 = 假 |
| 沒脈絡會困惑 | 半年後的人看 code 會問「為什麼這樣做」嗎? | 做法偏離顯然路徑、或看起來「怪」= 真;做法本身自明 = 假 |
| 真實取捨 | 有被認真考慮過又放棄的替代方案嗎? | 有輸家方案 + 放棄理由 = 真;根本沒得選 = 假 |

**沒過閘 → 勸退**,直接告訴 user:「這不用 ADR,`log.md` 補一行 / commit message 寫清楚就夠」,並說明是哪一閘沒過。**勸退是本 skill 的正常輸出,不是失敗。**

### 別漏掉的兩型(仍走三重閘,但幾乎必過——點名是提醒別漏)

- **刻意偏離顯然路徑**的決策——不記下來,下一個工程師會把它當 bug「修好」。
- **明確的 no**——被認真評估後否決的方案,記下來防半年後同一提案再來一輪。

## Step 2: 偵測 repo 慣例

```bash
ls -d adr decisions doc/adr docs/adr doc/adrs docs/adrs doc/decisions docs/decisions 2>/dev/null
```

命中的目錄先開來確認**長得像決策紀錄**(編號檔名 / 索引 / ADR 字樣)——同名但不是 ADR 庫(例如某個叫 `adr` 的工具目錄)就略過。

| 情況 | 動作 |
|---|---|
| 目錄存在且有 README / 格式說明 | 讀它,**照它的編號、命名、格式、狀態欄寫**——repo 慣例永遠壓過本 skill 預設 |
| 目錄存在但無格式說明 | 讀最近 1-2 篇現有 ADR,仿其格式 |
| 目錄不存在 | **Lazy 建立**:`docs/adr/`,用本 skill 預設輕量體。不預建 README、不鋪模板 |

編號 = 掃現有檔名最大號 + 1;空 repo 預設檔名 `docs/adr/NNN-kebab-slug.md`(NNN 三位補零,從 001 起)。**檔名一經建立不改名**(別的文件會連過來)。

## Step 3: 寫 ADR(預設輕量體)

預設格式——**標題 + 1 到 3 句**,就這樣:

```markdown
# ADR-NNN:<決策一句話>

<做了什麼決策>。<為什麼——關鍵理由或放棄了什麼>。<(選配)代價或後續影響一句>。
```
Read the full skill on GitHub

Details

Skill name
adr
Path
adr/SKILL.md
License
MIT
Repo updated
14 November 2026

FAQ

What does the Adr skill do?

Use when a durable technical decision was just made in conversation and should be recorded, or when user asks to write/record an ADR (開 ADR / 記個決策 / 這要不要 ADR). Runs a three-gate check FIRST and actively talks the user out of writing one when the decision doesn't qualify — then writes a lightweight (title + 1-3 sentences) ADR following the repo's own ADR conventions if any exist. Repo conventions always override this skill's defaults. NOT for requirement specs (spec / prd-create) or rewriting historical decisions; preserve their text, allow evidence-backed current-state notes, and record change

How do I install the Adr skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add KerberosClaw/kc_ai_skills --skill adr. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Adr popular?

It lives in KerberosClaw/kc_ai_skills, which has 80 GitHub stars and 13 forks, and is included in 1 curated skill list.

Related skills

Align

80

KerberosClaw/kc_ai_skills

Reconcile existing repository documentation with the current implementation, especially after verified hotfixes or after QA in an unattended task. A manual run first asks whether to align only the docs a specific change touched (trigger scope) or rescan the whole repo; unattended runs use the scope the dispatch states and default to the whole repo. Follow cross-repo references for evidence; edit only documentation in the authorized repo, annotating conflicting historical records. Not for fixing code, deploying, inventing requirements, or building a new documentation suite.

Writing & ContentIn 1 list13

Character Lora

80

KerberosClaw/kc_ai_skills

Use when the user wants to build a consistent-identity LoRA for an original character — defining the character, generating a face/body-consistent multi-angle dataset (via the gpt-image-gen skill for codex image generation), captioning it, doing base-specific homework, training on a chosen base (Pony / Z-Image / others) on a local GPU, and producing a usable LoRA. This skill ORCHESTRATES the end-to-end pipeline and gates every expensive/irreversible step; it delegates actual image generation to gpt-image-gen and never improvises training settings from memory.

Images, Video & AudioIn 1 list13

Conference Report

80

KerberosClaw/kc_ai_skills

Use when the user attended one or more sessions of a conference (with audio recordings + slide photos) and needs help building (1) faithful per-session reconstructions in markdown (slide visuals + speaker transcript with Whisper hallucination annotations), and (2) a downstream report deliverable whose scope and format are decided interactively with the user. Pipeline phase (raw → mlx_whisper Chinese SRT → per-slide multimodal reconstruction → official agenda cross-check via Playwright if available) is deterministic. Report phase is interactive — always quiz user on scope (single-session / sing

Documents & Office FilesIn 1 list13

Translate Book

44

kcy4334-lgtm/translate-book-arxiv

Translate an arXiv paper, or any PDF/DOCX/EPUB book, into any language as a printable book. For arXiv papers it reads the LaTeX source, so equations, tables, figures and numbering survive. Parallel sub-agents translate the chunks; output is HTML, DOCX, EPUB and PDF.

Writing & ContentIn 1 list

Rendering Untrusted Content

115

wdm0006/python-skills

Renders stored, authored, or imported content into HTML without shipping XSS — auditing every autoescape bypass (|safe, Markup, innerHTML), sanitizing Markdown output with an allowlist, escaping on both the server and the DOM, and writing sanitization tests that assert on the right copy of the string. Use when adding a Markdown or rich-text filter, rendering user/admin-authored content, reviewing a template that marks HTML trusted, building a client that injects values into innerHTML, or fixing an XSS report.

Writing & Content18

Nsfc Nssfc Grant Writing

52

ganlin770/nsfc-nssfc-grant-writing

帮助申请人撰写自己的【国家社会科学基金(国社科/NSSFC)】与【国家自然科学基金(国自然/NSFC)】项目申请书/标书/本子的完整辅导 skill。覆盖选题与申请代码归口、立项依据与研究现状述评、研究内容/研究目标/关键科学问题凝练、研究方案与技术路线、创新点、研究 基础与队伍、经费预算、预期成果、年度计划、活页匿名、评审打分逻辑与被毙原因、科研诚信红线与生成式AI使用规范、申报流程时间线, 并内置【图表制作】工具一键生成技术路线图/研究框架图/机制模型图/甘特图(matplotlib,导出可印刷的 PNG/PDF/SVG)。 Use this whenever the user mentions 国社科/国家社会科学基金/社科基金/国自然/国家自然科学基金/自科基金/基金申请书/标书/本子/ 活页/课题论证/立项依据/技术路线图/申报书/面上项目/青年基金/重大项目/重点项目/中华学术外译/后期资助,或说"写基金/改本子/ 润色立项依据/做技术路线图/凝练科学问题/基金申报/课题申报/申请书怎么写/评审会不会中"。这是写"自己的"申请书的辅助工具, 不代写、不买卖申请书。NOT for 期刊论文写作/毕业论文/开题报告(用 thesis 相关 skill)、纯文献综述、或与基金申报无关的写作。

Writing & Content10

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.