Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Record Adr

ASecurity

Add a ratified Fishhawk ADR to the in-repo decision record — transcribe the tracker issue into docs/adr/NNN-slug.md with correct front matter, infer status and applies_to by the documented rules, wire supersession both ways, update the README table, and regenerate index.json. Use when an ADR is accepted/superseded, or when asked to "record", "backfill" or "add" an ADR.

9 stars
0 votes
0 copies
0 views
Added 10/7/2026
ai-agentsgit

Security Analysis

A100/100

Scanned 10/7/2026

$npx -y skills add kuhlman-labs/fishhawk --skill record-adr --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Record Adr?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Record Adr
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/kuhlman-labs-record-adr/badge)](https://www.skillsdirectory.com/skills/kuhlman-labs-record-adr)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: record-adr
description: Add a ratified Fishhawk ADR to the in-repo decision record — transcribe the tracker issue into docs/adr/NNN-slug.md with correct front matter, infer status and applies_to by the documented rules, wire supersession both ways, update the README table, and regenerate index.json. Use when an ADR is accepted/superseded, or when asked to "record", "backfill" or "add" an ADR.
---

# Record an ADR

The format contract is `docs/adr/README.md`; read it before writing. The record **transcribes and never corrects**: the body below the H1 is the tracker issue body byte for byte. The only normalisations are CRLF → LF and exactly one trailing newline.

## 1. Fetch the source

```sh
gh issue view <N> --json number,title,body,url
```

- **Number:** the ADR number comes from the title (`[ADR-NNN] …`).
- **File name:** `docs/adr/NNN-<kebab-slug>.md`, with a zero-padded 3-digit prefix.

## 2. Write the record

```
---
id: ADR-NNN
title: "<issue title without the [ADR-NNN] prefix>"
status: <accepted|proposed|rejected|superseded|unknown>
date: YYYY-MM-DD
issue: https://github.com/kuhlman-labs/fishhawk/issues/<N>
supersedes: []
superseded_by: []
applies_to: []
---

# ADR-NNN: <title>

<issue body, verbatim>
```

### Front-matter grammar

It is restricted:

- one `key: value` per line
- strings are JSON double-quoted, or a bare token
- list keys are JSON arrays, always present (`[]` when empty)
- no unknown or duplicate keys
- `date` is optional

### `status`: fail-closed inference

- **`accepted`:** only when a Decision-headed section states acceptance (`Recorded <date>`, `Accepted`, `Approved`, `Decided`, `Adopt option X`).
- **`unknown`:** a placeholder (`_To be recorded._`) or a design with no acceptance statement. **Never guess upward.** List unknowns for the user to confirm.
- **`superseded` / `rejected`:** only when a source says so.

### `date`

The date the Decision section states. Omit it if none is stated; it is not the implementation date.

### `applies_to`

- **Default:** `[]`, unless the Decision or Consequences section names a repo path as the decision's *subject*. Citations and "see also" don't count.
- **Wildcards:** a `<placeholder>` segment becomes `*`; a directory gets a trailing `**`.
- **Check:** the gate verifies that each glob's literal stem appears in the body as a bounded path token.
- **When in doubt:** `[]`.

### Supersession

Supersession is reciprocal. If the new ADR states it supersedes ADR-X:

- add `ADR-X` to the new record's `supersedes`
- add the new id to ADR-X's `superseded_by`
- set ADR-X's `status: superseded` if the source says so

Both records must exist.

## 3. Index and table

```sh
scripts/check-adr --write-index      # regenerates docs/adr/index.json; never hand-edit it
scripts/check-adr                    # the gate; must pass
```

In `docs/adr/README.md`:

- Add the row under "Records", matching the existing rows:
  ```
  | [ADR-NNN](NNN-slug.md) | <title> | `<status>` | [#N](<issue url>) |
  ```
- If the status is `unknown`, also add a bullet under "Status unknown — needs captain confirmation" that quotes the source verbatim.

## 4. Gate and ship

- **Gate:** `scripts/check-adr` also runs inside `scripts/test verify`.
- **Timing:** commit in the same change that records the ratification, or the one right after. ADR-081 onward are added one at a time under the upkeep rule.
- **Tracker:** if the ADR was just resolved, also edit the issue's Decision section and close it (Git flow step 7).

Attribution

kuhlman-labskuhlman-labs
View sourceSee grades on GitHubMore from kuhlman-labs →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →