adrkit-init
Use when initializing ADR Kit in a repository or when the agent cannot find an adr/ directory.
Skill by luochang212
Chalk Labs
Need help deploying adrkit-init?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/luochang212-adrkit-init
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/adrkit-init
What's inside
- Skill name
adrkit-init- Description
- Use when initializing ADR Kit in a repository or when the agent cannot find an adr/ directory.
- License
- MIT
- Instructions
- 31 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# ADR Kit Init Installing ADR Kit puts a repository's decision memory where agents can see it: records live in `adr/`, and the `adrkit` CLI reads them. Run `adrkit init [path]` for a new repository, or to repair an existing `adr/` whose `config.yaml` is missing. Repair fills missing files and preserves existing records and integrations. Use `adrkit update` to refresh integrations in an initialized repository. Confirm the four lifecycle folders: `proposed/`, `implemented/`, `rejected/`, and `archived/`. The CLI installs workflow skills but does not rewrite a project's AGENTS.md. Record language follows the repository: match the language of existing records, or the user's language when the repository has no records yet, and keep that language for both titles and bodies rather than switching per conversation. Offer one of the sections below for `AGENTS.md` — suggest the one matching the repository's language, judged from the existing AGENTS.md, README, and records, defaulting to English when nothing decides — and paste it only with the user's agreement. A section in another language is a translation of the Chinese source; translate it and keep the `adrkit` invocations verbatim. If AGENTS.md already mentions adrkit in the user's own words, respect that text and suggest nothing. The section names the tool and the record-worthiness bar, and leaves whether or when an agent runs the commands to its judgment. ## 架构决策记录 本仓库用 `adr-kit` 这个 npm 包管理架构级决策,记录保存在 `adr/` 目录。可以用 `adrkit list` 列出全部记录,`adrkit show <编号>` 读取某一条,`adrkit relevant <路径>` 查找与某文件相关的记录。记录是有代价的:每记一件事,就要在代码之外多维护一份真相源。但记录又是必要的——代码只是根因衍生的现象,知道根因却不记录,未来的 agent 只能从代码反猜。例行修改留给 Git 和测试;没有值得记的就跳过。何时记录的四问与写法见 `adrkit-propose`、`adrkit-record` 技能。 ## Architecture decisions This repository uses the `adr-kit` npm package to keep architecture-level decisions; the records live in `adr/`. Browse them with `adrkit list`, read one with `adrkit show <N>`, and find the records relevant to a file with `adrkit relevant <path>`. Recording has a cost: every record is a second source of truth to maintain outside the code. It is also necessary — code is only the symptom a root cause produced, and a root cause left unrecorded forces future agents to reverse-guess it from the code. Routine edits belong to Git and tests; skip what is not worth recording. The `adrkit-propose` and `adrkit-record` skills carry the four-question recording test and the format. After installation, continue the original task; initializing ADR Kit is not itself a reason to create a record.
From luochang212/adr-kit, MIT.
More from luochang212/adr-kit
- 0.587score
adrkit-grill
luochang212
Use when a decision is still being shaped, or the user asks to grill a plan; interrogate the design against the active records until no branch is silently…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adrkit-note
luochang212
Use when you notice a choice future work must live with but cannot shape a record right now — park it as one line in the buffer and keep moving; the buffer is…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adrkit-propose
luochang212
Use when you catch yourself settling a choice future work must live with — a dependency, format, boundary, or default — and adr/ does not already own it; the…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adrkit-record
luochang212
Use when a choice that will constrain future work has already shipped and adr/ does not own it yet; record it directly, with no pending proposal.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adrkit-review
luochang212
Use when checking whether changed code and changed decision records still agree; scoped to record coherence, not general code review.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
adrkit-reject
luochang212
Use when a formal proposal is declined and its anti-pattern should be recorded.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
adrkit-supersede
luochang212
Use when one implemented decision fully replaces another and the old record must become archived history.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
adrkit-validate
luochang212
Use when checking ADR record format before implementation, rejection, archival, or commit.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
adrkit-archive
luochang212
Use when an implemented record no longer guides work and current behavior has another authoritative owner.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
adrkit-implement
luochang212
Use when a proposal has shipped and should become a numbered, active decision.
SkillAFreshness: A★ 1Claude Code +9 - 0.562score
adrkit-visualize
luochang212
Use when the user asks to visualize an existing ADR, its deliberation tree, or the whole decision set and its relationships.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 24, 2026 (12 days ago)
- Last release
- Oct 23, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/luochang212/adr-kit
- Website
- www.luochang.ink/adr-kit/
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from luochang212
- 0.587score
adrkit-grill
luochang212
Use when a decision is still being shaped, or the user asks to grill a plan; interrogate the design against the active records until no branch is silently…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adrkit-note
luochang212
Use when you notice a choice future work must live with but cannot shape a record right now — park it as one line in the buffer and keep moving; the buffer is…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adrkit-propose
luochang212
Use when you catch yourself settling a choice future work must live with — a dependency, format, boundary, or default — and adr/ does not already own it; the…
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adrkit-record
luochang212
Use when a choice that will constrain future work has already shipped and adr/ does not own it yet; record it directly, with no pending proposal.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
adrkit-review
luochang212
Use when checking whether changed code and changed decision records still agree; scoped to record coherence, not general code review.
SkillAFreshness: A★ 1Claude Code +9 - 0.581score
adrkit-reject
luochang212
Use when a formal proposal is declined and its anti-pattern should be recorded.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get adrkit-init running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
adrkit-init skill. Agent Mart. https://agentmart.dev/skills/luochang212-adrkit-init (last updated 2026-10-24)