[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M780JVTAYDQ7BAB57VKT8J9P":3,"skill-same:01M780JVTAYDQ7BAB57VKT8J9P":63},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":38,"repositoryHtmlUrl":39,"repositoryHomepageUrl":6,"ownerHtmlUrl":40,"ownerBlogUrl":6,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M780JVTAYDQ7BAB57VKT8J9P","runesleo-systematic-debugging",null,"Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.","HKU-MMLab\u002FUniClawBench","HKU-MMLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F218629317?v=4","01M7808YETMPBKR5WJNJRFSCDJ","01M7808YFS0WMXB5QAF8YG01BA",40,"MIT","https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F101_skill_usage\u002Ftask_101_31_postmortem_merge\u002Fskills\u002Frunesleo-systematic-debugging\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: runesleo-systematic-debugging\ndescription: Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.\nmetadata:\n  {\n    \"openclaw\":\n      {\n        \"version\": \"1.0.0\",\n        \"author\": \"runesleo\",\n        \"license\": \"MIT-0\",\n        \"tags\": [\"debugging\", \"rca\", \"root-cause\", \"framework\", \"incident-analysis\"],\n        \"category\": \"engineering-practice\"\n      }\n  }\n---\n\n# Systematic Debugging\n\nA five-phase debugging framework prioritizing root cause investigation\nbefore fixes.\n\n## The Iron Law\n\n> **NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST**\n> **NO INVESTIGATION WITHOUT CONTEXT RECALL FIRST**\n\n\"ALWAYS find root cause before attempting fixes. Symptom fixes are failure.\"\n\nThe framework enforces sequential completion: Phase 0 → Phase 1 → Phase 2 →\nPhase 3 → Phase 4. Skipping ahead is the most common failure mode.\n\n## Phase 0 — Context Recall\n\n* Search prior knowledge: error keywords, documentation, git history.\n* Extract recurring tokens \u002F signals from the symptom.\n* Output a recall summary BEFORE proceeding.\n* Do not attempt repro yet.\n\n## Phase 1 — Root Cause Investigation\n\n* Read the error message **completely** — every line.\n* Reproduce the issue consistently before forming hypotheses.\n* Check recent changes (git log, deploy log, config drift).\n* Gather diagnostic evidence at component boundaries (logs, traces, state dumps).\n* Trace data flow back to the source.\n\n## Phase 2 — Pattern Analysis\n\n* Find a known-working example or reference implementation.\n* Read the working example completely.\n* Identify differences between working and broken code \u002F state.\n* Understand transitive dependencies.\n\n## Phase 3 — Hypothesis & Testing\n\n* Form **one** specific hypothesis at a time.\n* Test minimally — change one variable, isolate the effect.\n* Verify before continuing. If the test refutes the hypothesis, return to\n  Phase 2 (don't escalate to a different hypothesis without analysis).\n\n## Phase 4 — Implementation\n\n* Create a failing test case first.\n* Implement a single fix that addresses the root cause.\n* Verify the fix works against the failing test and the original repro.\n* If three or more fix attempts fail, **stop** and question architectural\n  soundness — do not stack a fourth fix.\n\n## Cross-incident application\n\nWhen this framework is applied to multiple incident postmortems together\n(the cross-incident pattern):\n\n* Phase 0 = scan all postmortems and pull recurring keywords (e.g. \"config drift\",\n  \"WAF regex\", \"DB migration\", \"BGP\", \"CIDR\").\n* Phase 1 = for each candidate root-cause family, re-read the postmortems'\n  Detection \u002F Recovery \u002F Contributing-Factors sections; map each incident\n  to which root-cause families it touches.\n* Phase 2 = compare incidents that share a family — what's common, what's\n  different? Look for the same trigger surfaced through different blast\n  radii.\n* Phase 3 = formulate a small set of cross-incident hypotheses (\"we keep\n  failing at config-drift detection because X\").\n* Phase 4 = for each confirmed cross-incident pattern, propose a single\n  preventative action with a concrete owner and signal.\n\n## Red flags — restart at Phase 1\n\n* \"Quick fix for now, investigate later.\"\n* \"Just try changing X.\"\n* Proposing a fix before tracing data flow.\n* \"One more fix\" attempt after multiple failures.\n* Stacking 3+ fixes without architectural review.\n\n## Runtime\n\nThis skill is instruction-only. The workspace injects it at\n`\u002Froot\u002Fskills\u002Frunesleo-systematic-debugging`. There is nothing to install.\n","# Systematic Debugging\n\nA five-phase debugging framework prioritizing root cause investigation\nbefore fixes.\n\n## The Iron Law\n\n> **NO FIXES WITHOUT ROOT CAUSE INVESTIGATION FIRST**\n> **NO INVESTIGATION WITHOUT CONTEXT RECALL FIRST**\n\n\"ALWAYS find root cause before attempting fixes. Symptom fixes are failure.\"\n\nThe framework enforces sequential completion: Phase 0 → Phase 1 → Phase 2 →\nPhase 3 → Phase 4. Skipping ahead is the most common failure mode.\n\n## Phase 0 — Context Recall\n\n* Search prior knowledge: error keywords, documentation, git history.\n* Extract recurring tokens \u002F signals from the symptom.\n* Output a recall summary BEFORE proceeding.\n* Do not attempt repro yet.\n\n## Phase 1 — Root Cause Investigation\n\n* Read the error message **completely** — every line.\n* Reproduce the issue consistently before forming hypotheses.\n* Check recent changes (git log, deploy log, config drift).\n* Gather diagnostic evidence at component boundaries (logs, traces, state dumps).\n* Trace data flow back to the source.\n\n## Phase 2 — Pattern Analysis\n\n* Find a known-working example or reference implementation.\n* Read the working example completely.\n* Identify differences between working and broken code \u002F state.\n* Understand transitive dependencies.\n\n## Phase 3 — Hypothesis & Testing\n\n* Form **one** specific hypothesis at a time.\n* Test minimally — change one variable, isolate the effect.\n* Verify before continuing. If the test refutes the hypothesis, return to\n  Phase 2 (don't escalate to a different hypothesis without analysis).\n\n## Phase 4 — Implementation\n\n* Create a failing test case first.\n* Implement a single fix that addresses the root cause.\n* Verify the fix works against the failing test and the original repro.\n* If three or more fix attempts fail, **stop** and question architectural\n  soundness — do not stack a fourth fix.\n\n## Cross-incident application\n\nWhen this framework is applied to multiple incident postmortems together\n(the cross-incident pattern):\n\n* Phase 0 = scan all postmortems and pull recurring keywords (e.g. \"config drift\",\n  \"WAF regex\", \"DB migration\", \"BGP\", \"CIDR\").\n* Phase 1 = for each candidate root-cause family, re-read the postmortems'\n  Detection \u002F Recovery \u002F Contributing-Factors sections; map each incident\n  to which root-cause families it touches.\n* Phase 2 = compare incidents that share a family — what's common, what's\n  different? Look for the same trigger surfaced through different blast\n  radii.\n* Phase 3 = formulate a small set of cross-incident hypotheses (\"we keep\n  failing at config-drift detection because X\").\n* Phase 4 = for each confirmed cross-incident pattern, propose a single\n  preventative action with a concrete owner and signal.\n\n## Red flags — restart at Phase 1\n\n* \"Quick fix for now, investigate later.\"\n* \"Just try changing X.\"\n* Proposing a fix before tracing data flow.\n* \"One more fix\" attempt after multiple failures.\n* Stacking 3+ fixes without architectural review.\n\n## Runtime\n\nThis skill is instruction-only. The workspace injects it at\n`\u002Froot\u002Fskills\u002Frunesleo-systematic-debugging`. There is nothing to install.\n",{"name":5,"metadata":23,"description":7},{"openclaw":24},{"tags":25,"author":31,"license":32,"version":33,"category":34},[26,27,28,29,30],"debugging","rca","root-cause","framework","incident-analysis","runesleo","MIT-0","1.0.0","engineering-practice","main","a8ac4df6c554178c339f42696e3afe688a61f4b7","injection\u002F101_skill_usage\u002Ftask_101_31_postmortem_merge\u002Fskills\u002Frunesleo-systematic-debugging",1,"https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench","https:\u002F\u002Fgithub.com\u002FHKU-MMLab","Multimedia Lab at The University of Hong Kong, a top-notch research cohort dedicated to research and educating the best minds.","2026-07-28 16:29:51",{"source":8,"skillName":5,"commands":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add HKU-MMLab\u002FUniClawBench --skill runesleo-systematic-debugging",{"tool":49,"command":50},"bunx","bunx skills add HKU-MMLab\u002FUniClawBench --skill runesleo-systematic-debugging",{"tool":52,"command":53},"pnpm","pnpm dlx skills add HKU-MMLab\u002FUniClawBench --skill runesleo-systematic-debugging","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F101_skill_usage\u002Ftask_101_31_postmortem_merge\u002Fskills\u002Frunesleo-systematic-debugging\u002FSKILL.md",true,[57],{"path":58,"resourceType":59,"resourceTypeDesc":60,"sizeBytes":61,"sourceHtmlUrl":62},"_meta.json","REFERENCE","参考文档",125,"https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F101_skill_usage\u002Ftask_101_31_postmortem_merge\u002Fskills\u002Frunesleo-systematic-debugging\u002F_meta.json",[64,71,78,85,92,99],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":70,"publishedAt":18},"01M78127EY3XPHMS16Y8A8B6NR","cli-anything-zoom","Command-line interface for Zoom — manage meetings, participants, and recordings from the command line via the Zoom REST API.","https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F205_cross_platform_zh\u002Ftask_205_33_calendar_scheduling\u002Fskills\u002Fcli-anything-zoom\u002FSKILL.md",[],[],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":75,"categories":76,"keywords":77,"publishedAt":18},"01M78123F7PCSTEZ8CT3DBEGBT","netease-music-cli","CLI for NetEase Cloud Music — search songs\u002Falbums\u002Fplaylists, get lyrics, and manage your music library from the terminal.","https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F205_cross_platform_zh\u002Ftask_205_26_music_crossid\u002Fskills\u002Fnetease-music-cli\u002FSKILL.md",[],[],{"skillNo":79,"name":80,"nameZh":6,"description":81,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":82,"categories":83,"keywords":84,"publishedAt":18},"01M78120M9QEN0MQB9X0FCKSZX","google-calendar-gcalcli","Install and use gcalcli for live Google Calendar read access using the provided OAuth cache.","https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F203_long_context_zh\u002Ftask_203_08_hk_jpop_calendar_ticketing\u002Fskills\u002Fgoogle-calendar-gcalcli\u002FSKILL.md",[],[],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":18},"01M7811TTCHD4JW4FG5HG1PVY9","Excel \u002F XLSX","Create, inspect, and edit Microsoft Excel workbooks and XLSX files with reliable formulas, dates, types, formatting, recalculation, and template preservation. Use when (1) the task is about Excel, `.xlsx`, `.xlsm`, `.xls`, `.csv`, or `.tsv`; (2) formulas, formatting, workbook structure, or compatibility matter; (3) the file must stay reliable after edits.","https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F201_skill_usage_zh\u002Ftask_201_40_excel_dashboard_qa\u002Fskills\u002Fexcel-xlsx\u002FSKILL.md",[],[],{"skillNo":93,"name":94,"nameZh":6,"description":95,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":96,"categories":97,"keywords":98,"publishedAt":18},"01M7811PGJQ4XDQ7XJ0TKNSEE6","duckdb-en","DuckDB CLI specialist for SQL analysis, data processing and file conversion. Use for SQL queries, CSV\u002FParquet\u002FJSON analysis, database queries, or data conversion. Triggers on \"duckdb\", \"sql\", \"query\", \"data analysis\", \"parquet\", \"convert data\".","https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F201_skill_usage_zh\u002Ftask_201_40_excel_dashboard_qa\u002Fskills\u002Fduckdb-cli-ai-skills\u002FSKILL.md",[],[],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":9,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":105,"publishedAt":18},"01M7811JSJW78171B25VJ285A0","automate-excel","Automates reading, writing, merging, transforming, and validating Excel (.xlsx\u002F.xls) files. Use when the user works with spreadsheets, .xlsx files, Excel data — for cleaning, joining, validating, deduplicating, aggregating, filtering, or auditing tabular data.","https:\u002F\u002Fgithub.com\u002FHKU-MMLab\u002FUniClawBench\u002Fblob\u002Fmain\u002Finjection\u002F201_skill_usage_zh\u002Ftask_201_40_excel_dashboard_qa\u002Fskills\u002Fautomate-excel\u002FSKILL.md",[],[]]