Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated second-model consult at dead ends
Scanned 9/3/2026
Install to Claude Code
Skills Directorynpx -y skills add crenshawdev/cadence --skill cad-debug --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Cad Debug?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/crenshawdev-cad-debug)More formats (shields.io, HTML) on the badges page.
---
name: cad-debug
description: "Systematic debugging - hypothesis and symptom tracked in a state file that survives /clear, with a user-gated second-model consult at dead ends"
argument-hint: "[list | status <slug> | continue <slug> | --diagnose] [symptom]"
allowed-tools:
- Read
- Write
- Edit
- Bash
- Grep
- Glob
- AskUserQuestion
---
<objective>
Debug a symptom by the scientific method - form hypotheses, run the cheapest
discriminating test for each, confirm a root cause, fix it, verify the symptom
is gone. The investigation is persisted to `.planning/debug/<slug>.md` after
every step, so a `/clear` or a new session resumes it losslessly. At a genuine
dead-end (repeated failed fixes, exhausted hypotheses), OFFER a second-model
consult (references/consult.md) - user-gated, decision-support only.
Routing: parse `$ARGUMENTS` per the workflow's Route table (debug.md) -
`list`, `status <slug>`, `continue <slug>`, `--diagnose`, else a new symptom.
The table lives in the workflow, once.
</objective>
<execution_context>
@${CLAUDE_PLUGIN_ROOT}/cadence-core/workflows/debug.md
</execution_context>
<process>
Route on `$ARGUMENTS`, then run the debug workflow single-pass end-to-end.
Persist the state file after every hypothesis test and fix attempt. Never
auto-loop fixes and never auto-consult - both are deliberate, and the consult
is always user-gated.
</process>
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
**Complete production-ready guide for Google Gemini embeddings API** This skill provides comprehensive coverage of the `gemini-embedding-001` model for generating text embeddings, including SDK usage, REST API patterns, batch processing, RAG integration with Cloudflare Vectorize, and advanced use cases like semantic search and document clustering. ---
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
