ClaudeCodeMod

All shelves / Skills

recording-decisions

riekelt/technical-writer · 13.5k installs · 29 stars

Skill

Marked No Code · Indirect Prompt Injection

Install

In your shell
npx -y skills add riekelt/technical-writer --skill recording-decisions --agent claude-code

Run in a terminal. Claude loads the skill when a task calls for it. Check the repo's README before you run it.

Open the repo

Files

SKILL.md

Recording decisions

REQUIRED BACKGROUND: the technical-writing skill (hard rules, truth rules, style).

Overview

Two formats, by weight: a full ADR for a decision with architecture-level consequences; a decision log entry for the running stream of smaller choices. Both are append-only: an accepted decision is immutable; new context is a new entry that supersedes the old one.

When to invoke, and not

Invoke when a choice has been made and needs recording, when someone asks "write down why we did this", or when an existing decision is superseded. Do NOT invoke for a decision still being argued (that is writing-design-docs; its Why & What box becomes the ADR once accepted).

Also invoke on the signals that an unrecorded decision is passing by: "we decided X instead of Y", "let's just go with", a trade-off resolved in a PR comment or chat thread, or a rationale someone has now explained twice. Each is a decision living in a non-durable place; offer to record it.

Record the decision before citing it. A chat session is not a durable source. Put the dated substance in the log, quote the decider where wording matters, commit the entry, then cite it. Record the smallest complete decision, not a transcript.

ADR

Nygard format. One decision per ADR.

# ADR-[number]: [short title of the decision]

| | |
|---|---|
| **Status** | Proposed / Accepted / Superseded by ADR-XXX |
| **Date** | YYYY-MM-DD |
| **Deciders** | [who took part] |

## Context
[The forces at play: technical, organizational, political. What must be solved.
Factual, without giving away the decision.]

## Decision
[What was decided. Active voice: "We release on tags", not "it was decided that".]

## Consequences
**Positive:** [what gets easier]
**Negative:** [what gets harder, which trade we accept]
**Neutral:** [what changes without being better or worse]

## Alternatives considered
**[Alternative]** - For: [...] Against: [...] Why not chosen: [...]

## References
[Evidence, related decisions, measurements]

Negative is mandatory and may not be empty. Each alternative carries its strongest argument for; a rejection without it is a strawman.

The sole permitted edit to an accepted ADR is its Status line gaining "Superseded by ADR-XXX". An objection raised but never answered goes in at full strength as a negative consequence with a named owner: the writer never invents a rebuttal and never withholds a decision its owner has declared. Names unknown at writing time are marked fill-before-filing, because a filed record carries real people.

Decision log (lightweight)

For the running log a full ADR would kill. Cheap enough to maintain:

## YYYY-MM-DD

### [Decision stated as an imperative sentence]
[One paragraph: the rule.]
Why:
- [reason]
- [reason]
Instead of: [rejected option] - [why not]

Rules

  • Append-only. A wrong entry gets a new dated entry that supersedes it, never an edit. Convert relative dates to absolute.
  • Record the why, not only the what.
  • When a written rule and shipped reality have diverged, record which one the team intended. Every doctrine document states what it owns and what it leaves to others.
  • Scope guard at the top when a sibling could overlap: "product ideas live in ROADMAP.md; this file is for engineering decisions."
  • Capture negative results and unknowns explicitly: "four theories, four disproved, cause not found" is a result. A search returning nothing is a result.

Facts

Kind
Skill
Repo
riekelt/technical-writer
Group
Uncategorized
Installs
13.5k
Stars
29

More on this shelf

  1. 1find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.3.8M
  2. 2grill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.3M
  3. 3grill-with-docsmattpocock/skillsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.1.1M
  4. 4agent-browservercel-labs/agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.1.1M
  5. 5improve-codebase-architecturemattpocock/skillsScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.1.1M
  6. 6tddmattpocock/skillsTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.1.1M