systematic-debugHypothesis-driven debugging — observe / hypothesize / isolate / verify / fix
Install via ClawdBot CLI:
clawdbot install 534422530/systematic-debugGrade Fair — based on market validation, documentation quality, package completeness, maintenance status, and authenticity signals.
Calls external URL not in known-safe list
https://www.bilibili.com/video/BV1rNNRedEbnAudited Jun 3, 2026 · audit v1.0
Generated Oct 7, 2026
An on-call engineer uses the five-step workflow (observe, hypothesize, isolate, verify, fix) to trace a memory leak in a Node.js API that only manifests under load. Errors and logs are collected first, three candidate causes are ranked, then a binary search through recent commits isolates the leak to a caching layer.
A firmware team applying an OTA update sees intermittent boot failures on a subset of IoT devices. Using the systematic-debug skill, they build a minimal reproducer on a bench unit, verify the hypothesis that a timing race in the bootloader is the cause, and ship a targeted patch with a regression test.
A data engineer notices daily ETL jobs producing null aggregates. The skill guides them to gather Airflow logs, form hypotheses about upstream schema drift versus a timezone bug, and isolate by replaying a single partition, confirming the fix with a dbt test.
A mobile developer receives a Crashlytics spike tied to a new SDK. They use the workflow to collect stack traces, hypothesize three root causes, isolate via an internal build with feature flags toggled off, and verify with a unit reproducer before releasing a hotfix.
A solutions engineer debugging a customer's failing webhook integration uses the systematic-debug method to capture payload samples, hypothesize signature-mismatch or retry-storm issues, isolate by replaying requests with a proxy, and confirm a fix with a Postman regression suite.
Offer the systematic-debug workflow as a free CLI/IDE plugin, then upsell a cloud-hosted assistant that stores hypotheses, evidence, and postmortems across team sessions. The paid tier adds shared timelines, AI-suggested hypotheses, and audit trails.
Sell the structured hypothesis-driven methodology as a consulting engagement for firmware and automotive teams shipping safety-critical code. Deliverables include incident playbooks, on-site workshops, and retrospective audits using the five-step workflow.
Package the systematic-debug skill, anti-patterns, and reproducer discipline into a paid course and certification for SRE and support engineers. Include labs where learners take a failing service and must produce a verified minimal reproducer to pass.
💬 Integration Tip
Trigger it whenever a user says 'debug', '调试', or 'root cause' and enforce the reproducer step as a required artifact. Keep the five-step workflow visible as a checklist so the agent does not jump straight to code changes.
Scored Oct 7, 2026
Control desktop applications on Windows — launch, close, focus, resize, move windows, simulate keyboard/mouse input, manage processes, control VSCode, read clipboard, and capture screen info. Use when the user wants to interact with any running program, switch windows, type text, press shortcuts, open files in VSCode, manage running processes, or get system display information.
Conduct rigorous, adversarial code reviews with zero tolerance for mediocrity. Use when users ask to "critically review" my code or a PR, "critique my code", "find issues in my code", or "what's wrong with this code". Identifies security holes, lazy patterns, edge case failures, and bad practices across Python, R, JavaScript/TypeScript, SQL, and front-end code. Scrutinizes error handling, type safety, performance, accessibility, and code quality. Provides structured feedback with severity tiers (Blocking, Required, Suggestions) and specific, actionable recommendations.
Pragmatic coding standards for writing clean, maintainable code — naming, functions, structure, anti-patterns, and pre-edit safety checks. Use when writing new code, refactoring existing code, reviewing code quality, or establishing coding standards.
Claude Code integration for OpenClaw. This skill provides interfaces to: - Query Claude Code documentation from https://code.claude.com/docs - Manage subagents and coding tasks - Execute AI-assisted coding workflows - Access best practices and common workflows Use this skill when users want to: - Get help with coding tasks - Query Claude Code documentation - Manage AI-assisted development workflows - Execute complex programming tasks
Plan, draft, version, and refine written content with enforced versioning and quality audits.
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.