Testing & Writing Skills

Peer messaging between concurrent Claude Code sessions over named rooms. Fires when the user wants this session to talk to another running session: "join the bus", "connect to the bus", "join room ", "message the backend session", "tell the other session to ...", "delegate this to the frontend session", "hand this off to another session", "coordinate with the other agent", "who else is on the bus", "what rooms are open", "watch the room", "halt the room", "stop the agents". Also fires when the user asks to work alongside a session they have open in another terminal. Wraps the atomic bus CLI: join, then a Monitor on recv so peer messages arrive as prompts. Carries the reaction policy that decides when an arriving message is an instruction to act on and when it is only news.

Conventions for editing the atomic CLI and command artifacts in this repo. Auto-fires on phrases like "add a CLI subcommand", "wire a new flag", "prompt the user", "add a doctor check", "add a doctor repair", "edit cmd/atomic/main.go", "extend claudeinstall", "add an internal package", "use huh", "add a command", "create a new verb", "add a partial", "render templates", "edit a command", "edit commands/", "create a new command", "edit an agent", "edit agents/", or "add an agent". Contributor-only — never bundled, never installed.

Hypothesis-driven debugging skill. Use when a bug, test failure, crash, or unexpected behavior is reported. Auto-trigger on error pastes or "broken/doesn't work/failing" language. Explicit invocation: /atomic-debug. Output: symptom statement → hypothesis table → cheapest test first → root cause. No symptom-patching. Boundary with atomic-tdd: this skill owns diagnosing an unknown root cause. Once the cause is known and you are writing the fix, that is atomic-tdd's job (failing test first, then the fix).

Diff-driven documentation surface classifier. Given a diff (staged, branch, or range), reads the project's indexed Documentation surfaces table from CLAUDE instructions, matches the diff against it, and emits a structured list of proposed edits. Two modes: maintenance (commit flow — stale/incomplete only, never suggests new pages) and authoring (/documentation explicit — full discovery, gap detection, content generation). Auto-fires on "doc this change", "what surfaces does this touch", "doc impact for this diff", "what needs documenting". Also invoked by /documentation (authoring mode) and by ship verbs (maintenance mode, between stage and signals). Boundary: for raw prose drafting (README intro, guide narrative), atomic-writing owns. This skill owns diff-driven surface impact and content generation for stale/incomplete docs.

Compressed commit message and PR body generator. Cuts noise from both while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious; PR bodies state only what the diff can't show, ~120 words max. Use when user says "write a commit", "commit message", "generate commit", "open a PR", "PR description", or invokes /atomic-git-discipline. Auto-triggers when staging changes or authoring a pull request.

Diagnose and fix broken release-please CI in this repo. Auto-fires on "release-please CI is failing", "release branch is out of date", "release branch is stale", "release PR is red", "release-please broke", "fix the release CI", "release branch CI failing", "version branch is behind", "release PR changelog is wrong", "release PR missing work". Contributor-only — never bundled, never installed.

Compressed code review comments. Cuts noise from PR feedback while preserving the actionable signal. Each comment is one line: location, problem, fix. Use when user says "review this PR", "code review", "review the diff", or invokes /atomic-review. Auto-triggers when reviewing pull requests.

Test-first discipline. Auto-triggers on "let's implement X", "add feature Y", "fix bug Z", "write a test for", "implement", "build out", and similar pre-code-change phrases. Iron rule: failing test exists before production code. Skip only for pure docs/config changes with an explicit "skipped because:" note. Explicit invocation: /atomic-tdd. Boundary with atomic-debug: this skill owns writing or changing code — new behavior, or a fix whose root cause is already understood. Diagnosing why something is broken (unknown cause) is atomic-debug's job; debug to the root cause first, then return here to write the fix test-first.

Evidence-before-claim gate. Auto-triggers when Claude is about to claim "done", "fixed", "passing", "complete", "ready to merge", "looks good", "should work", "should pass", "green", or any synonym. Iron rule: no completion claim without a fresh verification command run in this turn. Explicit invocation: /atomic-verify.

Planning-phase visual comparison aid. Renders 2-4 side-by-side variants per decision dimension as a single throwaway, self-contained HTML file and captures the user's pick as typed terminal codes (e.g. "A2 B3"). Auto-fires on phrases like "show me a few options", "mock up some variants", "let me see this side by side", "visual options for", "compare these layouts", "show layout options", "wireframe some choices". Also invoked by /atomic-plan just-in-time when a design question is genuinely visual. Scope is strictly visual choices — mockup, layout, color, spacing, hierarchy, diagram — not conceptual or text decisions, which stay in the terminal.

Conversational wiki and capture-bucket routing. Fires when the user wants a place, space, or folder for notes, research, tickets, raw dumps, or knowledge capture — checks the block in ~/.claude/CLAUDE.md; if the cwd is under a registered realm, creates the folder as a bucket via atomic wiki bucket add rather than a bare mkdir. Also fires on "add a bucket", "set up a karpathy wiki", "karpathy realm", "set up a wiki for my projects", "add this to my wiki", "wiki this", "what does my wiki know about X", "is my wiki stale". Routes per-scope: repo wikis use references/repo.md pipeline (docs/wiki/); realm wikis use references/realm.md pipeline (wiki/ in a separate repo). Not invoked by other commands — this skill is the conversational entry point for wiki and bucket operations; /refresh-wiki is the synthesis engine.

Voice and tone rules for enduring narrative documentation — README.md, docs/guides/, CHANGELOG narrative entries, and any other long-form human-facing markdown that ships in the repo. Clear, direct, technical narrative. No marketing language, no AI-tell phrases, no em dashes, no throat-clearing. Two voices: Claude's TUI replies use atomic output style (terse, fragments); file contents split by surface — narrative docs use this skill, everything else (specs, design docs, CLAUDE.md, signals files) uses terse technical prose. Invoked by /documentation when editing README or guides. Invoked as callee by atomic-documentation when surface is human-facing prose. Auto-fires on "draft the README", "write the docs", "improve this prose", "edit the guide".