adr
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as…
Remove AI artifacts from documents. Use when: cleaning AI-generated text, removing tool names, fixing boilerplate patterns. Not for: doc review (use doc-review), doc refactoring (use doc-refactor). Output: cleaned document preserving original intent.
Claude Code
$ npx -y skills add sd0xdev/sd0x-harness --skill de-ai-flavor --agent claude-code
Codex
$ npx skills add sd0xdev/sd0x-harness --skill de-ai-flavor -a codex -y
Cursor
$ npx skills add sd0xdev/sd0x-harness --skill de-ai-flavor -a cursor -y
Gemini CLI
$ npx skills add sd0xdev/sd0x-harness --skill de-ai-flavor -a gemini-cli -y
GitHub Copilot
$ npx skills add sd0xdev/sd0x-harness --skill de-ai-flavor -a github-copilot -y
OpenCode
$ npx skills add sd0xdev/sd0x-harness --skill de-ai-flavor -a opencode -y
Windsurf
$ npx skills add sd0xdev/sd0x-harness --skill de-ai-flavor -a windsurf -y
name: de-ai-flavor description: "Remove AI artifacts from documents. Use when: cleaning AI-generated text, removing tool names, fixing boilerplate patterns. Not for: doc review (use doc-review), doc refactoring (use doc-refactor). Output: cleaned document preserving original intent." allowed-tools: Read, Grep, Glob, Edit
/de-ai-flavor docs/xxx.md # Process specified file /de-ai-flavor docs/ # Process all .md in directory /de-ai-flavor # Process .md in git diff
| Type | Pattern | Action | | ----------------- | --------------------------------------------------- | ------- | | Tool names | Claude/Codex/GPT/AI assistant | Remove | | Boilerplate | "Let me...", "First...then...", "In conclusion" | Rewrite | | Over-structuring | One sentence per heading, too many #### levels | Simplify| | Service tone | "Hope this helps", "If you have questions..." | Remove | | Self-description | "Next I will...", "I will proceed to..." | Remove | | Iteration leaks | "Round 1/Round 2/Round N" | Rewrite |
Scan file -> Mark AI traces -> Remove/Rewrite/Simplify -> Output summary
## De-AI-Flavor Results **File**: `docs/xxx.md` | Line | Original | Change | Reason | | ---- | --------------------- | ----------------------- | ---------------- | | 15 | Let me explain... | Removed | AI self-description | | 32 | Claude suggests... | Changed to "Suggest..." | Tool name | **Stats**: Removed 3 tool names | Rewrote 5 boilerplate | Simplified 2 structures
Input: /de-ai-flavor docs/tech-spec.md Action: Scan -> Remove "Claude suggests" -> Rewrite "Let me explain" -> Output summary
Input: This document feels very AI-generated, please clean it up Action: Detect git diff -> Mark AI traces -> Batch process -> Output stats
Language: English | 繁體中文 | 简体中文 | 日本語 | 한국어 | Español The harness layer for Claude Code. Let the model choose the path. Keep "done" verifiable. Claude has discretion inside a closed, test-pinned anchor set.
Write an Architecture Decision Record (ADR) for a feature — Context / Decision / Status / Consequences / Alternatives, filed as…
Install and set up the optional agentctl mod (task scope, refusal before execution, evidence that goes stale, model-free…
Architecture design and documentation. Produces 3-architecture.md with component diagrams, data flow, integration points, and…
Context-aware Q&A with auto context gathering. Use when: user has a quick question about codebase, git history, rules, docs, or…
Industry best practices conformance audit with mandatory adversarial debate. Produces audit artifact: verdict (OK/WARN/FAIL) +…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.