Menu
Use when generating or updating CLAUDE.md files โ defines what belongs vs. what stays in skills/docs, format rules (JSON for data, markdown for rules/instructions), and line budget. Load before any CLAUDE.md write.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Consolidated view of the add-pro ecosystem - commands, skills, relationships and dependencies. Loaded by /add as source of truth.
Source of truth for ADD doc rules, depth floors, IDs, refs, validation gate. Load before any doc write.
Use when running agent-judged QA validation (read-PNG by default; the playwright plugin adds live driving) โ the Level C judge rubric, severity taxonomy, dual-judge (@ux-agent review โฅ @qa-agent) method, report schema/template, and the config.json/screens.json formats. Consumed by /add.qa and both judges.
Use when a state-materializing command starts or is asked to upgrade โ reads the setup receipt, compares the recorded contract against the shipped one, executes the declared upgrade deltas sequentially, and rewrites the receipt even on a verified-current no-op. Consumed by /add.qa-setup STEP 1.5 and STEP 11.
Internal skill for developing ADD framework artefacts (commands, skills, agents, scripts). Use when add-framework--plan analyzes viability of new framework features, when add-framework--build implements framework artefacts, or when creating/modifying commands, skills, or agents. Always use this skill before proposing or implementing changes to the framework itself.
Use when building, styling, or theming UI components, pages, layouts, dashboards, charts, tables, or forms for SaaS products.
| name | add-claude-md-style |
| description | Use when generating or updating CLAUDE.md files โ defines what belongs vs. what stays in skills/docs, format rules (JSON for data, markdown for rules/instructions), and line budget. Load before any CLAUDE.md write. |
Defines content rules for CLAUDE.md files generated by ADD commands (primarily add.wiki STEP 6). Source: Anthropic official docs (code.claude.com/docs/en/memory).
This skill is only for CLAUDE.md files. Do not load when:
add-doc-schemas insteadSKILL.md) โ use add-skill-creator and add-token-efficiencyadd-saas-copy or general docs guidanceCLAUDE.md is injected into every session as a user message (not system prompt). Oversized files:
Official target: under 200 lines per CLAUDE.md file.
Facts the AI needs in every session, not available elsewhere:
Target: 80-150 lines total (the managed Project Knowledge Base block is ~15 lines and is accounted for within this budget).
This is the fundamental rule. JSON minified is for structured data that the agent looks up (configs, mappings, paths, tech stack). Rules, instructions, orientation, and behavioral guidance use markdown (lists, tables, prose).
Minified JSON โ when:
Markdown (lists, tables, prose) โ when:
# โ WRONG โ rule as JSON
{"hierarchy":"domain โ backend โ workers โ apps","rule":"inner never imports outer"}
# โ
RIGHT โ rule as markdown, data as JSON
### Layers
domain โ backend/database โ workers โ apps. Inner never imports outer.
### Packages
{"domain":"@rd/domain","backend":"@rd/backend","database":"@rd/database","workers":"@rd/workers"}
Same principle applies to import rules and placement maps: render them as tables (behavioral guidance), not JSON objects.
Rules and constraints the agent must follow. Uses markdown (tables, lists, prose).
## Architecture Contract
> Dependency hierarchy. Check BEFORE implementing or reviewing.
### Layers
domain โ backend/database โ workers โ apps. Inner never imports outer.
### Import Rules
| Package | Can import |
|---|---|
| domain | nothing |
| backend, database | domain |
| workers | domain, database |
| api | all libs |
| frontend | domain |
### Placement
| What | Where |
|---|---|
| Entities | libs/domain/src/entities |
| Services | libs/backend/src/services |
| Repositories | libs/app-database/src/repositories |
| NestModules | apps/backend/src/api/modules |
Data the agent looks up. Uses minified JSON (one object per line).
## Technical Spec
{"pkg":"npm","build":"turbo","lang":"typescript"}
{"backend":{"framework":"NestJS","version":"10","entry":"apps/backend/src/api/main.ts"}}
{"database":{"engine":"PostgreSQL","orm":"Kysely"}}
Do NOT include: full entity lists, all enum names, all type names, all API routes, all guard names, worker handler names.
Auto-derived data block emitted by add-architecture-discovery. Maps the 5 universal gate intents (lint, typecheck, test, build, format) to the actual command this project uses. Consumed by add.plan, add.build, add.autopilot, add.review to inject and enforce checklist items in tasks.md.
Uses minified JSON (it's data, not behavior). Only includes gates that actually exist โ absence is meaningful. The format gate, when present, MUST be a non-mutating check command.
## Validation Gates
{"validation_gates":{"lint":"npm run lint","typecheck":"npm run typecheck","test":"npm test","build":"npm run build","format":"npm run format:check"}}
Language-agnostic โ the keys are intents, the values are the real commands for whatever ecosystem this project uses (Node, Python, .NET, Go, Rust, Ruby, Elixir, Java, etc.). If no gates are detected, omit the section entirely. Do not emit {"validation_gates":{}}.
Written and owned by /add.wiki STEP 6 โ not authored by hand. Delimited by
link-reference-definition markers, deliberately NOT HTML comments: the build
pipeline strips HTML comments (<!-- -->) from command sources uniformly (the same
mechanism that powers feature/plugin injection anchors), so a template using
<!-- codeadd-wiki:start --> inside a command source would be destroyed at build
time. [//]: # (...) is a link-reference-definition โ invisible when rendered,
untouched by the build strip, and trivially matched for replace-or-append at
runtime.
[//]: # (codeadd-wiki:start)
## Project Knowledge Base
`.codeadd/wiki/` holds this project's patterns, conventions, workflows, and architecture
rationale. Entrypoint: `.codeadd/wiki/index.md`.
- CONSULT BEFORE exploring source for: project conventions, established patterns,
workflow/how-to questions, architecture rationale ("why is it built this way").
- Do NOT consult for live structural facts (callers, impact, dependencies) โ derive those
from the code graph or the code itself.
- Pages carry `commit` + `sources` frontmatter. If sources changed since (see index.md
staleness check), verify against code before relying on the page.
- Do not hand-edit generated pages; run /add.wiki update instead. INSTRUCTIONS.md is
user-owned and steers regeneration.
[//]: # (codeadd-wiki:end)
Replace-or-append semantics: if the markers are found, the block between them is
replaced in place; if absent, the block is appended (with a separating blank line).
This is /add.wiki's responsibility, not a manual edit.
Legacy cleanup: a CLAUDE.md carrying the old, unmarked "Implementation Patterns"
section (pointing at project-patterns/ and pattern-search.sh) predates this
mechanism and carries no markers, so replace-or-append cannot remove it automatically.
Any updater agent regenerating this file MUST detect and DELETE a legacy
"Implementation Patterns" section (or any section referencing project-patterns or
pattern-search.sh) before writing the managed block.
Before finalizing any generated CLAUDE.md:
{}); format only when non-mutating?[//]: # (codeadd-wiki:start) โฆ [//]: # (codeadd-wiki:end)), and no legacy unmarked "Implementation Patterns" section remains?{{skill:add-token-efficiency/SKILL.md}} โ generic compression rules (JSON=data, markdown=instructions){{skill:add-doc-schemas/SKILL.md}} โ doc generation standards (separate pipeline, not for CLAUDE.md)