Deep Debug
The single entry point for ALL debugging — bugs, test failures, CI failures, Metaflow run failures, Jenkins build failures, or any unexpected behavior. Trigger phrases include "debug this", "why is this failing", "find the bug", "fix the bug", "root cause", "what's wrong with", "this is broken", "diagnose", "troubleshoot", "investigate this failure", "the test is failing", "this used to work", "why doesn't this work", "where's the bug", "CI failed", "PR is red", "why did my flow fail", "build failed", "Jenkins failure". Composes specialized sub-skills internally (debug-pr for CI, debug-run for
Install
/plugin marketplace add npow/claude-skillsThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add npow/claude-skills --skill deep-debuggit clone --depth 1 https://github.com/npow/claude-skills.git /tmp/claude-skills
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills/deep-debug ~/.claude/skills/deep-debugPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Deep Debug Skill Adversarial hypothesis-driven debugging. Given a bug, generate competing hypotheses across orthogonal dimensions, judge each independently (two-pass blind), run discriminating probes that falsify the weaker, fix the survivor with test-first discipline, and escalate to architectural review after 3 failed attempts. Output is a verified fix with a failing-test-now-passes proof, OR an honest termination label naming why the bug resisted a code-level fix. ## Execution Model All operations use Claude Code primitives. These contracts are non-negotiable: - **All data passed to agents via files, never inline.** Evidence, hypothesis lists, probe specs, known-hypothesis IDs — all written to disk before the agent prompt. Inline data is silently truncated. - **State written before agent spawn, not after.** `spawn_time_iso` is written to state.json before the Agent tool call. Spawn failure records `spawn_failed` status. Resume uses persisted state, never in-memory reconstruction. - **Structured output is the contract; free-text is ignored.** Every judge, probe-verdict, and validator produces machine-parseable structured lines. Coordinator reads only structured fields. Unparseable output triggers fail-safe classification (`disputed`, never `rejected`). Hypothesis output files MUST contain `STRUCTURED_OUTPUT_START`/`STRUCTURED_OUTPUT_END` markers; files without these markers are treated as failed.
Details
- Skill name
deep-debug- Repository
- npow/claude-skills
- Path
deep-debug/SKILL.md- License
- Apache-2.0
- Repo updated
- 20 August 2026
FAQ
What does the Deep Debug skill do?
The single entry point for ALL debugging — bugs, test failures, CI failures, Metaflow run failures, Jenkins build failures, or any unexpected behavior. Trigger phrases include "debug this", "why is this failing", "find the bug", "fix the bug", "root cause", "what's wrong with", "this is broken", "diagnose", "troubleshoot", "investigate this failure", "the test is failing", "this used to work", "why doesn't this work", "where's the bug", "CI failed", "PR is red", "why did my flow fail", "build failed", "Jenkins failure". Composes specialized sub-skills internally (debug-pr for CI, debug-run for
How do I install the Deep Debug skill?
Claude Code plugin: /plugin marketplace add npow/claude-skills. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Deep Debug popular?
It lives in npow/claude-skills, which has 5 GitHub stars and 1 forks.
Related skills
Autopilot
5npow/claude-skills
Use when the user says "autopilot", "build this", "make it", "ship it", "just do it", "do it", "implement this", or gives a vague idea, spec, task list, or bug fix and expects autonomous execution. Handles decomposition, agent coordination, and verification automatically. "build me end to end", "go from idea to code", "do everything", "run this autonomously". Follows the Spec-Driven Development workflow: specify → clarify → plan → tasks → analyze → implement.
Build Python Library
5npow/claude-skills
Implements pip-installable Python libraries from scratch using src layout, pyproject.toml, and pytest. Use when the user asks to build, create, implement, or scaffold a Python library, package, pip package, middleware, SDK, or wrapper. Covers project scaffolding, proxy/wrapper patterns, provider-agnostic interfaces, async/sync support, and test infrastructure.
Canon Design Review
5npow/claude-skills
Architecture-level design review evaluating 15 Tier 2 best practices drawn from DDD (Evans), POEAA (Fowler), Release It! (Nygard), DDIA (Kleppmann), Team Topologies (Skelton/Pais), How Buildings Learn (Brand), and Systemantics (Gall). Auto-invoke when a PR touches: - Service definitions, infrastructure code, API boundaries, or database schemas - Files matching **/architecture*, **/design*, **/api/*, **/schema*, **/migrations/* - Any directory named services/, infrastructure/, platform/, domain/, core/ Also invoke when the user says: - "design review", "architecture review", "review the design"
Deep Debug Ensemble V1
5npow/claude-skills
Use when the user asks to debug with ensemble judges, or explicitly requests the ensemble variant of deep-debug. Benchmark variant that uses three heterogeneous providers for hypothesis-plausibility judging instead of a single judge. Same triggers as deep-debug but with multi-provider ensemble scoring.
Code Quality Trends
5npow/claude-skills
Use when checking code quality trends, tech debt accumulation, TODO/FIXME growth, test coverage ratios, PR size distribution, or generating a code quality report. Trigger phrases: code quality, code trends, tech debt trends, quality report.
Deep Plan
5npow/claude-skills
Use before touching code for any multi-step task — features, refactors, migrations, architectural decisions, bug fixes, or any work that needs to be broken into verifiable steps. Trigger phrases include "write a plan", "implementation plan", "plan this", "plan the work", "break this down", "how should I approach this", "make a plan", "design the approach", "before I code this", "I need a plan", "write up the plan", "spec to plan", "requirements to plan". Produces SDD-compatible plan.md, research.md, data-model.md, contracts/, and tasks.md via a Planner → Architect → Critic consensus loop.
Browse the most popular Claude skills, all software development skills, or write your own with the skills generator.