cladding-init
Use only when the user explicitly names Cladding and asks to initialize, adopt, or refresh it; never use for an ordinary project creation or implementation…
Classify a natural-language prompt to one of cladding's verbs. Use when the user describes work in their own words and you want to see which built-in verb cladding's intent classifier would pick — primarily a debugging tool for the orchestrator persona and for verifying the
$ npx -y skills add qwerfunch/cladding --skill route --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/routeContext preview
The summary Claude sees to decide when to auto-load this skill.
Classify a natural-language prompt to one of cladding's verbs. Use when the user describes work in their own words and you want to see which built-in verb cladding's intent classifier would pick — primarily a debugging tool for the orchestrator persona and for verifying the
description: Classify a natural-language prompt to one of cladding's verbs. Use when the user describes work in their own words and you want to see which built-in verb cladding's intent classifier would pick — primarily a debugging tool for the orchestrator persona and for verifying the router's coverage after adding new verbs. Activate only when the connected project contains spec.yaml or the user explicitly names Cladding; ignore ordinary requests in uninitialized projects.
Run `clad route <prompt>` from anywhere — the verb is read-only and does not require a workspace. It calls `classifyIntent(prompt)` from `src/router/intent.js` and emits the resolved verb name as a Pulse note. Exit code is `0` on a confident match and `1` when the intent resolves to `unknown`.
clad route "scan my codebase and write the conventions doc" clad route "is the LLM host healthy?" clad route "I'm stuck, what's next?"
The verb is the smallest surface that exercises the router in isolation. Production callers typically reach the router indirectly through the orchestrator persona (`src/agents/orchestrator.md`) or through `clad_route` over MCP.
The classifier is intentionally conservative — when no rule matches strongly enough, the result is `unknown` and the verb exits `1` so callers can fall back to an explicit verb lookup instead of guessing.
For an organization to trust AI with its code, three things must hold — trust, traceability, and stability at scale. cladding wraps your AI coding agent: your intent goes in before it writes, and the result is verified against your spec after, so those three are earned, not assumed. First L4 implementation of the Ironclad standard.
Repo: qwerfunch/cladding
Use only when the user explicitly names Cladding and asks to initialize, adopt, or refresh it; never use for an ordinary project creation or implementation…
Impl-blind test/oracle author — writes conformance tests from a spec-only brief. Tool-restricted by definition (no Read/Grep/Glob/Edit), so "authored blind" is…
Render release notes / a changelog from the cladding spec. Use when the user asks for release notes, a changelog, 릴리즈 노트, 변경 이력, or "what changed (since…
Run every Iron Law stage and the drift detector suite. Use when the user wants the full project health snapshot, a CI gate, or to verify nothing regressed…
Record a feature checkpoint event pinning the current git HEAD plus a spec digest, so a later rollback can restore the exact pre-change state. Use before a…
Advance Cladding onboarding after the user answers a pending product question. Use the MCP prepare/apply flow, preserve the answer verbatim, and never invent…