Systematic debugging with root cause investigation. Use when debugging, investigating bugs, or tracing errors. Use before fixing any non-trivial bug.
Scanned 9/2/2026
Install to Claude Code
Skills Directorynpx -y skills add imoonkey/yaco --skill investigate --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Investigate?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/imoonkey-investigate)More formats (shields.io, HTML) on the badges page.
---
name: investigate
description: Systematic debugging with root cause investigation. Use when debugging, investigating bugs, or tracing errors. Use before fixing any non-trivial bug.
---
# Investigate
Phases 1-3 are INVESTIGATION ONLY — no code changes until the root cause is confirmed.
## Phases
1. **Reproduce & gather evidence.** Reproduce it. Define expected vs actual. Collect logs, traces, stack traces, repro steps.
2. **Form hypotheses.** Rank 1-3 by likelihood. Each MUST cite specific evidence (log line, stack frame, state value) — "maybe it's X" with no evidence is not a hypothesis.
3. **Test hypotheses.** Add temporary logging, inspect state, trace execution paths. Confirm or eliminate each. Still no fixes.
4. **Fix the root cause.** Fix only the confirmed cause, one atomic commit. Remove the debug instrumentation. If the fix is non-trivial, run a full plan → build → verify.
5. **Validate.** Confirm the original repro is gone and related tests pass. On failure, return to phase 2.
## Hard limits
- **Max 3 fix attempts.** If all fail, stop and report: what was tried, what was learned, what remains unknown.
- **Done = root cause identified + fix verified.** "Seems to work" is not done.
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. ---
Interview, source-challenge, verify, save, and ADR-gate fuzzy coding requests into Codex-ready implementation specs. Use when a feature, bugfix, refactor, migration, repo-wide change, or architecture task needs user-verified requirements, source-backed decisions, durable architecture decisions, acceptance criteria, validation commands, rollout notes, saved spec/ADR files, and a Codex execution prompt. Do not use when already fully specified or when the user wants direct implementation now.
