[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-majiayu000-trajectory-review-en":3,"guides-for-majiayu000-trajectory-review":431,"similar-k1797wq7825nd9yhz5q538asgn86nq05-en":432},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":15,"identity":244,"isFallback":239,"parentExtension":249,"providers":250,"relations":255,"repo":257,"tags":427,"workflow":428},1778692607327.23,"k1797wq7825nd9yhz5q538asgn86nq05",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":13,"sourceUrl":14},"Post-hoc diagnosis of a failed agent trajectory. Classifies the first unrecoverable step into one of nine failure categories (plan adherence, hallucinated information, invalid tool call, misread tool output, intent–plan mismatch, under-specified intent, unsupported intent, guardrail trigger, system failure) and produces an evidence-backed root-cause report.",{"claudeCode":12},"majiayu000/vibeguard","trajectory-review","https://github.com/majiayu000/vibeguard",{"_creationTime":16,"_id":17,"extensionId":5,"locale":18,"result":19,"trustSignals":225,"workflow":242},1778692729089.6216,"kn72dchpqcwm360xybfxmpgx1n86nk0h","en",{"checks":20,"evaluatedAt":193,"extensionSummary":194,"features":195,"nonGoals":201,"promptVersionExtension":206,"promptVersionScoring":207,"purpose":208,"rationale":209,"score":210,"summary":211,"tags":212,"targetMarket":218,"tier":219,"useCases":220},[21,26,29,32,36,39,44,48,51,54,58,62,65,69,72,75,78,81,84,87,91,95,100,104,108,111,114,117,121,124,127,130,133,136,139,143,147,151,154,158,161,164,167,170,174,177,180,183,186,190],{"category":22,"check":23,"severity":24,"summary":25},"Practical Utility","Problem relevance","pass","The description clearly names the problem of diagnosing failed agent trajectories and identifies the need for post-hoc analysis and root-cause reporting.",{"category":22,"check":27,"severity":24,"summary":28},"Unique selling proposition","The skill provides a structured, four-stage diagnostic procedure and a nine-category taxonomy for classifying failure modes, offering significant value beyond a generic LLM's ability to review logs.",{"category":22,"check":30,"severity":24,"summary":31},"Production readiness","The skill is designed for post-hoc analysis of captured trajectories and provides a clear output format, making it suitable for real-world debugging workflows.",{"category":33,"check":34,"severity":24,"summary":35},"Scope","Single responsibility principle","The skill focuses exclusively on diagnosing failed agent trajectories and classifying their root causes, without extending into unrelated domains like code generation or general LLM evaluation.",{"category":33,"check":37,"severity":24,"summary":38},"Description quality","The displayed description accurately reflects the skill's functionality as described in the SKILL.md, detailing its purpose of classifying and reporting on failed agent trajectories.",{"category":40,"check":41,"severity":42,"summary":43},"Invocation","Scoped tools","not_applicable","This skill does not expose individual tools; its functionality is encapsulated within a single invocation.",{"category":45,"check":46,"severity":42,"summary":47},"Documentation","Configuration & parameter reference","The skill does not appear to have configurable parameters or options that require explicit documentation beyond its core functionality.",{"category":33,"check":49,"severity":42,"summary":50},"Tool naming","The skill does not expose individual tools or commands with distinct names.",{"category":33,"check":52,"severity":42,"summary":53},"Minimal I/O surface","As a skill that processes a provided trajectory, it does not expose traditional tool parameters or response shapes in a way that can be evaluated for minimal I/O.",{"category":55,"check":56,"severity":24,"summary":57},"License","License usability","The MIT license is clearly provided in a LICENSE file, making it permissible for use and distribution.",{"category":59,"check":60,"severity":24,"summary":61},"Maintenance","Commit recency","The latest commit was on 2026-05-13, indicating recent maintenance.",{"category":59,"check":63,"severity":42,"summary":64},"Dependency Management","The skill does not appear to have external dependencies that require management.",{"category":66,"check":67,"severity":42,"summary":68},"Security","Secret Management","The skill's function of analyzing a provided trajectory does not involve the use or handling of secrets.",{"category":66,"check":70,"severity":24,"summary":71},"Injection","The skill processes a provided trajectory and does not appear to load or execute external, untrusted data as instructions.",{"category":66,"check":73,"severity":24,"summary":74},"Transitive Supply-Chain Grenades","The skill analyzes a captured trajectory and does not fetch remote content or execute code not included in the bundle.",{"category":66,"check":76,"severity":24,"summary":77},"Sandbox Isolation","The skill analyzes data and does not perform file system modifications or operations outside its defined scope.",{"category":66,"check":79,"severity":24,"summary":80},"Sandbox escape primitives","The skill's code does not contain primitives for detaching processes or retrying denied tool calls.",{"category":66,"check":82,"severity":24,"summary":83},"Data Exfiltration","The skill analyzes provided data and does not make outbound calls or submit confidential information.",{"category":66,"check":85,"severity":24,"summary":86},"Hidden Text Tricks","The bundled content appears free of hidden steering tricks, and descriptions use clean, printable ASCII.",{"category":88,"check":89,"severity":24,"summary":90},"Hooks","Opaque code execution","The bundled scripts are plain and readable, with no obfuscation techniques like base64 payloads or runtime fetching.",{"category":92,"check":93,"severity":42,"summary":94},"Portability","Structural Assumption","The skill operates on a provided trajectory and does not make assumptions about the user's project structure.",{"category":96,"check":97,"severity":98,"summary":99},"Trust","Issues Attention","info","In the last 90 days, 10 issues were opened and 48 were closed, indicating active maintenance but a closure rate below 50%.",{"category":101,"check":102,"severity":24,"summary":103},"Versioning","Release Management","The skill's SKILL.md frontmatter declares a meaningful semver version, and the repository has recent commits and a CHANGELOG.",{"category":105,"check":106,"severity":42,"summary":107},"Code Execution","Validation","The skill processes a provided trajectory and does not involve executable code or structured output that requires validation by a schema library.",{"category":66,"check":109,"severity":42,"summary":110},"Unguarded Destructive Operations","The skill is analytical and does not perform any destructive operations.",{"category":105,"check":112,"severity":24,"summary":113},"Error Handling","The skill is designed to report on errors within a trajectory and handles errors gracefully by providing specific classification and root cause attribution.",{"category":105,"check":115,"severity":42,"summary":116},"Logging","The skill analyzes a provided trajectory and does not perform actions that require local audit logging.",{"category":118,"check":119,"severity":42,"summary":120},"Compliance","GDPR","The skill analyzes trajectories and does not operate on personal data.",{"category":118,"check":122,"severity":24,"summary":123},"Target market","The skill's functionality is not tied to any specific geographic or legal jurisdiction and is globally applicable.",{"category":92,"check":125,"severity":24,"summary":126},"Runtime stability","The skill is designed to run within the Claude Code environment and does not make assumptions about specific OS, shells, or editors.",{"category":45,"check":128,"severity":24,"summary":129},"README","The README file is comprehensive and clearly outlines the purpose and functionality of VibeGuard, including installation and usage.",{"category":33,"check":131,"severity":42,"summary":132},"Tool surface size","This is a single skill and does not expose multiple tools or commands.",{"category":40,"check":134,"severity":42,"summary":135},"Overlapping near-synonym tools","The skill does not expose multiple tools, so there are no overlapping near-synonym tools.",{"category":45,"check":137,"severity":24,"summary":138},"Phantom features","All features advertised in the README are supported by the skill's functionality and documentation.",{"category":140,"check":141,"severity":24,"summary":142},"Install","Installation instruction","The README provides clear, copy-pasteable installation instructions and verification steps.",{"category":144,"check":145,"severity":24,"summary":146},"Errors","Actionable error messages","The skill's output format includes a 'Root cause' section with classification, step index, failed check, contributing steps, and evidence, providing actionable insights.",{"category":148,"check":149,"severity":42,"summary":150},"Execution","Pinned dependencies","The skill does not rely on third-party dependencies that require pinning.",{"category":33,"check":152,"severity":42,"summary":153},"Dry-run preview","The skill is analytical and does not perform state-changing operations.",{"category":155,"check":156,"severity":42,"summary":157},"Protocol","Idempotent retry & timeouts","The skill analyzes provided data and does not involve remote calls or state-changing operations requiring idempotency or timeouts.",{"category":118,"check":159,"severity":24,"summary":160},"Telemetry opt-in","The extension's documentation does not mention telemetry collection, and the default assumption is opt-in or non-existent.",{"category":40,"check":162,"severity":24,"summary":163},"Precise Purpose","The skill's purpose is precisely defined, stating it diagnoses failed agent trajectories and classifying them into specific categories, with clear 'when to use' and 'do not use' sections.",{"category":40,"check":165,"severity":24,"summary":166},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the skill's core capability and purpose.",{"category":45,"check":168,"severity":24,"summary":169},"Concise Body","The SKILL.md body is well-structured and concise, delegating deeper material to separate files as appropriate.",{"category":171,"check":172,"severity":24,"summary":173},"Context","Progressive Disclosure","The SKILL.md outlines the diagnostic procedure and links to external documentation for detailed rule references and known issues.",{"category":171,"check":175,"severity":42,"summary":176},"Forked exploration","The skill analyzes a provided trajectory and does not involve deep exploration or code review requiring forked context.",{"category":22,"check":178,"severity":24,"summary":179},"Usage examples","While the SKILL.md doesn't contain explicit end-to-end examples of invoking the skill itself, the README provides a detailed demo GIF and clear installation/usage instructions that serve a similar purpose.",{"category":22,"check":181,"severity":24,"summary":182},"Edge cases","The SKILL.md explicitly lists failure modes for the trajectory analysis, such as missing stages or partial captures, and describes how to handle them.",{"category":105,"check":184,"severity":42,"summary":185},"Tool Fallback","The skill does not rely on external tools like an MCP server and operates internally.",{"category":187,"check":188,"severity":24,"summary":189},"Safety","Halt on unexpected state","The skill's diagnostic procedure specifies that it stops processing if stages are missing and does not invent data, effectively halting on unexpected pre-state.",{"category":92,"check":191,"severity":24,"summary":192},"Cross-skill coupling","The skill operates on a provided trajectory and does not implicitly rely on other skills being loaded in the same session.",1778692728984,"This skill analyzes captured agent trajectories to identify the first unrecoverable step, classifying it into one of nine failure categories and providing an evidence-backed root-cause report. It normalizes trajectories, synthesizes tool contracts, and evaluates steps against constraints to pinpoint failures.",[196,197,198,199,200],"Classifies failures into nine categories","Identifies the first unrecoverable step","Provides evidence-backed root-cause reports","Normalizes trajectories for analysis","Synthesizes tool contracts and goal checklists",[202,203,204,205],"Evaluating passing agent runs.","Rerunning or debugging trajectories automatically.","Rewriting agent prompts or skills directly; provides recommendations only.","Generalizing findings from a single trajectory to system-wide claims without further analysis.","3.0.0","4.4.0","To provide a systematic and evidence-based diagnosis of failed agent runs, enabling users to understand the root cause of errors and improve agent reliability.","The skill has a clear purpose, robust documentation, and excellent security posture. Minor info finding on issue closure rate does not impact overall quality.",99,"A high-quality skill for diagnosing and classifying agent trajectory failures with comprehensive documentation and security.",[213,214,215,216,217],"debugging","troubleshooting","agent-performance","error-analysis","trajectory-analysis","global","verified",[221,222,223,224],"Diagnosing why an agent run produced an incorrect or incomplete result.","Investigating user-reported agent failures and performing postmortems.","Characterizing failure modes after model upgrades or new capability releases.","Reviewing agent trajectories when a user requests an explanation for a failure.",{"codeQuality":226,"collectedAt":228,"documentation":229,"maintenance":232,"security":238,"testCoverage":241},{"hasLockfile":227},true,1778692713464,{"descriptionLength":230,"readmeSize":231},359,20185,{"closedIssues90d":233,"forks":234,"hasChangelog":227,"openIssues90d":235,"pushedAt":236,"stars":237},48,2,10,1778682269000,8,{"hasNpmPackage":239,"license":240,"smitheryVerified":239},false,"MIT",{"hasCi":227,"hasTests":227},{"updatedAt":243},1778692729089,{"basePath":245,"githubOwner":246,"githubRepo":247,"locale":18,"slug":13,"type":248},"skills/trajectory-review","majiayu000","vibeguard","skill",null,{"evaluate":251,"extract":253},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":252,"targetMarket":218,"tier":219},[213,214,215,216,217],{"commitSha":254},"HEAD",{"repoId":256},"kd7b0vh258xpbyerk68bk3e1ks86mk58",{"_creationTime":258,"_id":256,"identity":259,"providers":260,"workflow":423},1778692601876.5544,{"githubOwner":246,"githubRepo":247,"sourceUrl":14},{"classify":261,"discover":402,"github":405},{"commitSha":254,"extensions":262},[263,274,283,291,299,307,312,326,334,344,353,383,392],{"basePath":264,"description":265,"displayName":266,"installMethods":267,"rationale":268,"selectedPaths":269,"source":273,"sourceLanguage":18,"type":248},"skills/agentsmd-audit","Audit AGENTS.md / CLAUDE.md against the five high-leverage patterns (progressive disclosure, procedural workflows, decision tables, production code examples, domain rules with concrete alternatives). Reports per-pattern coverage, anti-patterns, and a prioritized fix list.","agentsmd-audit",{"claudeCode":12},"SKILL.md frontmatter at skills/agentsmd-audit/SKILL.md",[270],{"path":271,"priority":272},"SKILL.md","mandatory","rule",{"basePath":275,"description":276,"displayName":277,"installMethods":278,"rationale":279,"selectedPaths":280,"source":273,"sourceLanguage":282,"type":248},"skills/awk-posix-compat","Shell 脚本中 awk 的 POSIX 兼容性指南。\nUse when: 编写或审查包含 awk 的 shell 脚本，\n尤其是需要 macOS + Linux 跨平台运行的场景。\n触发词: awk, BSD awk, POSIX regex, [[:space:]],\nguard 脚本, 跨平台 shell\n","awk-posix-compat",{"claudeCode":12},"SKILL.md frontmatter at skills/awk-posix-compat/SKILL.md",[281],{"path":271,"priority":272},"zh-CN",{"basePath":284,"description":285,"displayName":286,"installMethods":287,"rationale":288,"selectedPaths":289,"source":273,"sourceLanguage":18,"type":248},"skills/eval-harness","Assessment-driven development — Quantify code generation quality with pass@k / pass^k metrics, automatically scored by Grader.","eval-harness",{"claudeCode":12},"SKILL.md frontmatter at skills/eval-harness/SKILL.md",[290],{"path":271,"priority":272},{"basePath":292,"description":293,"displayName":294,"installMethods":295,"rationale":296,"selectedPaths":297,"source":273,"sourceLanguage":18,"type":248},"skills/iterative-retrieval","Iterative retrieval — 4-stage loop (DISPATCH→EVALUATE→REFINE→LOOP) to pinpoint relevant information in the code base. Up to 3 rounds.","iterative-retrieval",{"claudeCode":12},"SKILL.md frontmatter at skills/iterative-retrieval/SKILL.md",[298],{"path":271,"priority":272},{"basePath":300,"description":301,"displayName":302,"installMethods":303,"rationale":304,"selectedPaths":305,"source":273,"sourceLanguage":18,"type":248},"skills/strategic-compact","Strategic compression — Manual compression of contexts at logical boundaries rather than arbitrary automatic compression. Key decisions and constraints are preserved and intermediate exploration is discarded.","strategic-compact",{"claudeCode":12},"SKILL.md frontmatter at skills/strategic-compact/SKILL.md",[306],{"path":271,"priority":272},{"basePath":245,"description":10,"displayName":13,"installMethods":308,"rationale":309,"selectedPaths":310,"source":273,"sourceLanguage":18,"type":248},{"claudeCode":12},"SKILL.md frontmatter at skills/trajectory-review/SKILL.md",[311],{"path":271,"priority":272},{"basePath":313,"description":314,"displayName":247,"installMethods":315,"rationale":316,"selectedPaths":317,"source":273,"sourceLanguage":18,"type":248},"skills/vibeguard","AI-assisted development of anti-hallucination specifications. Check out the seven-layer defense architecture, quantitative indicators, execution templates and practical cases. Used for code review, task startup inspection, and weekly review.",{"claudeCode":12},"SKILL.md frontmatter at skills/vibeguard/SKILL.md",[318,319,322,324],{"path":271,"priority":272},{"path":320,"priority":321},"references/review-template.md","medium",{"path":323,"priority":321},"references/scoring-matrix.md",{"path":325,"priority":321},"references/task-contract.yaml",{"basePath":327,"description":328,"displayName":329,"installMethods":330,"rationale":331,"selectedPaths":332,"source":273,"sourceLanguage":18,"type":248},"workflows/auto-optimize","Automate analysis, evaluation, design and optimization of target projects. Integrate VibeGuard as a baseline scan, the remediation process adheres to VibeGuard specifications, and a compliance check is run at the end. Support auto-run-agent autonomous execution.","auto-optimize",{"claudeCode":12},"SKILL.md frontmatter at workflows/auto-optimize/SKILL.md",[333],{"path":271,"priority":272},{"basePath":335,"description":336,"displayName":337,"installMethods":338,"rationale":339,"selectedPaths":340,"source":273,"sourceLanguage":18,"type":248},"workflows/fixflow","Execute coding tasks with a strict delivery workflow: build a full plan, implement one step at a time, run tests continuously, and commit by default after each step (`per_step`). Support explicit commit policy overrides (`final_only`, `milestone`) and optional BDD (Given/When/Then) when users ask for behavior-driven delivery or requirements are unclear.","fixflow",{"claudeCode":12},"SKILL.md frontmatter at workflows/fixflow/SKILL.md",[341,342],{"path":271,"priority":272},{"path":343,"priority":321},"CLAUDE.md",{"basePath":345,"description":346,"displayName":347,"installMethods":348,"rationale":349,"selectedPaths":350,"source":273,"sourceLanguage":18,"type":248},"workflows/optflow","Discover and deliver repository optimization work end to end: identify performance/reliability/maintainability/security/dx/cost optimization points, prioritize by impact-effort-risk, then execute fixes step by step with continuous testing and explicit commit policy (`final_only`, `per_step`, `milestone`). Default to `per_step` for implementation work so each feature is tested then committed before the next feature. Supports optional BDD (Given/When/Then).","optflow",{"claudeCode":12},"SKILL.md frontmatter at workflows/optflow/SKILL.md",[351,352],{"path":271,"priority":272},{"path":343,"priority":321},{"basePath":354,"description":355,"displayName":356,"installMethods":357,"rationale":358,"selectedPaths":359,"source":273,"sourceLanguage":18,"type":248},"workflows/plan-flow","Analyze repository-level duplicate/redundant design first, then build and execute a strict step-test-update plan in docs/plan. Use for deep architecture review, convergence planning, and traceable one-step-at-a-time delivery.","plan-flow",{"claudeCode":12},"SKILL.md frontmatter at workflows/plan-flow/SKILL.md",[360,361,362,364,366,368,370,372,374,376,379,381],{"path":271,"priority":272},{"path":343,"priority":321},{"path":363,"priority":321},"references/CLAUDE.md",{"path":365,"priority":321},"references/analysis-playbook.md",{"path":367,"priority":321},"references/execplan-integration.md",{"path":369,"priority":321},"references/execplan-template.md",{"path":371,"priority":321},"references/plan-accomplishments.md",{"path":373,"priority":321},"references/plan-template.md",{"path":375,"priority":321},"references/risk-impact-scoring.md",{"path":377,"priority":378},"scripts/findings_to_plan.py","low",{"path":380,"priority":378},"scripts/plan_lint.py",{"path":382,"priority":378},"scripts/redundancy_scan.sh",{"basePath":384,"description":385,"displayName":386,"installMethods":387,"rationale":388,"selectedPaths":389,"source":273,"sourceLanguage":18,"type":248},"workflows/plan-mode","Use when the user asks to enter Plan mode, says /prompts:plan or /plan, or wants a structured execution plan written to plan/.","plan-mode",{"claudeCode":12},"SKILL.md frontmatter at workflows/plan-mode/SKILL.md",[390,391],{"path":271,"priority":272},{"path":343,"priority":321},{"basePath":393,"installMethods":394,"rationale":395,"selectedPaths":396,"source":273,"sourceLanguage":18,"type":401},"vg-helper",{"cargo":393},"cli ecosystem detected at vg-helper",[397,399],{"path":398,"priority":272},"Cargo.toml",{"path":400,"priority":321},"src/main.rs","cli",{"sources":403},[404],"manual",{"closedIssues90d":233,"description":406,"forks":234,"homepage":407,"license":240,"openIssues90d":235,"pushedAt":236,"readmeSize":231,"stars":237,"topics":408},"Native rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.","https://majiayu000.github.io/vibeguard/",[409,410,411,412,413,414,415,416,417,418,419,420,421,422],"claude-code","code-quality","codex","developer-tools","guardrails","hooks","agent-harness","ai-agents","ai-safety","anti-hallucination","codex-cli","linter","llm","static-analysis",{"classifiedAt":424,"discoverAt":425,"extractAt":426,"githubAt":426,"updatedAt":424},1778692606860,1778692601876,1778692604872,[215,213,216,217,214],{"evaluatedAt":243,"extractAt":429,"updatedAt":430},1778692607327,1778693058643,[],[433,460,491,510,539,568],{"_creationTime":434,"_id":435,"community":436,"display":437,"identity":443,"providers":447,"relations":453,"tags":455,"workflow":456},1778692396032.779,"k179dznar9vdfw1akjwqm4081186nxj2",{"reviewCount":8},{"description":438,"installMethods":439,"name":441,"sourceUrl":442},"Trusted-lane debug skill for deep learning research work. Use when the user pastes a traceback, terminal error, CUDA OOM, checkpoint load failure, shape mismatch, NaN loss symptom, or training failure and wants conservative diagnosis before any patching. Do not use for broad refactoring, speculative adaptation, automatic exploratory patching, or general repository familiarization.",{"claudeCode":440},"lllllllama/ai-paper-reproduction-skill","safe-debug","https://github.com/lllllllama/ai-paper-reproduction-skill",{"basePath":444,"githubOwner":445,"githubRepo":446,"locale":18,"slug":441,"type":248},"skills/safe-debug","lllllllama","ai-paper-reproduction-skill",{"evaluate":448,"extract":452},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":449,"targetMarket":218,"tier":219},[213,450,451,216,214],"deep-learning","research",{"commitSha":254},{"repoId":454},"kd7629v5mqesxwwe9w7qtfgp7d86n6re",[213,450,216,451,214],{"evaluatedAt":457,"extractAt":458,"updatedAt":459},1778692636476,1778692396032,1778692750992,{"_creationTime":461,"_id":462,"community":463,"display":464,"identity":470,"providers":475,"relations":485,"tags":487,"workflow":488},1778697652123.895,"k179x649dvyg7xswjx2h5a199n86m32x",{"reviewCount":8},{"description":465,"installMethods":466,"name":468,"sourceUrl":469},"Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.",{"claudeCode":467},"steipete/clawdis","Node Connect","https://github.com/steipete/clawdis",{"basePath":471,"githubOwner":472,"githubRepo":473,"locale":18,"slug":474,"type":248},"skills/node-connect","steipete","clawdis","node-connect",{"evaluate":476,"extract":484},{"promptVersionExtension":206,"promptVersionScoring":207,"score":477,"tags":478,"targetMarket":218,"tier":219},100,[213,479,480,481,482,214,483],"networking","android","ios","macos","openclaws",{"commitSha":254,"license":240},{"repoId":486},"kd738npxg9yh3xf3vddzy9fyfh86nhng",[480,213,481,482,479,483,214],{"evaluatedAt":489,"extractAt":490,"updatedAt":489},1778698735523,1778697652123,{"_creationTime":492,"_id":493,"community":494,"display":495,"identity":499,"providers":501,"relations":506,"tags":507,"workflow":508},1778697652123.8813,"k175pymk0vm7xrcjj2p0jf904186nae7",{"reviewCount":8},{"description":496,"installMethods":497,"name":498,"sourceUrl":469},"Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code.",{"claudeCode":467},"openclaw-debugging",{"basePath":500,"githubOwner":472,"githubRepo":473,"locale":18,"slug":498,"type":248},".agents/skills/openclaw-debugging",{"evaluate":502,"extract":505},{"promptVersionExtension":206,"promptVersionScoring":207,"score":477,"tags":503,"targetMarket":218,"tier":219},[213,483,401,214,504],"development",{"commitSha":254},{"repoId":486},[401,213,504,483,214],{"evaluatedAt":509,"extractAt":490,"updatedAt":509},1778697754713,{"_creationTime":511,"_id":512,"community":513,"display":514,"identity":520,"providers":525,"relations":533,"tags":535,"workflow":536},1778683190010.284,"k1757t8mrzzrf8yabxrtp82mg586m6nf",{"reviewCount":8},{"description":515,"installMethods":516,"name":518,"sourceUrl":519},"Systematic debugging methodology emphasizing root cause analysis over quick fixes",{"claudeCode":517},"bobmatnyc/claude-mpm-skills","Systematic Debugging","https://github.com/bobmatnyc/claude-mpm-skills",{"basePath":521,"githubOwner":522,"githubRepo":523,"locale":18,"slug":524,"type":248},"universal/debugging/systematic-debugging","bobmatnyc","claude-mpm-skills","systematic-debugging",{"evaluate":526,"extract":531},{"promptVersionExtension":206,"promptVersionScoring":207,"score":477,"tags":527,"targetMarket":218,"tier":219},[213,214,528,529,530],"root-cause-analysis","methodology","problem-solving",{"commitSha":254,"license":532},"Apache-2.0",{"repoId":534},"kd72g55e5qeqs90bk1bvkt8wbx86nkn3",[213,529,530,528,214],{"evaluatedAt":537,"extractAt":538,"updatedAt":537},1778686304588,1778683190010,{"_creationTime":540,"_id":541,"community":542,"display":543,"identity":548,"providers":552,"relations":560,"tags":563,"workflow":564},1778683762612.1245,"k1709q7z5grftph7kb93c569qh86n56a",{"reviewCount":8},{"description":544,"installMethods":545,"name":214,"sourceUrl":547},"Uses Chrome DevTools MCP and documentation to troubleshoot connection and target issues. Trigger this skill when list_pages, new_page, or navigate_page fail, or when the server initialization fails.",{"claudeCode":546},"ChromeDevTools/chrome-devtools-mcp","https://github.com/ChromeDevTools/chrome-devtools-mcp",{"basePath":549,"githubOwner":550,"githubRepo":551,"locale":18,"slug":214,"type":248},"skills/troubleshooting","ChromeDevTools","chrome-devtools-mcp",{"evaluate":553,"extract":559},{"promptVersionExtension":206,"promptVersionScoring":207,"score":477,"tags":554,"targetMarket":218,"tier":219},[555,556,214,213,557,558],"devtools","chrome","automation","mcp",{"commitSha":254},{"parentExtensionId":561,"repoId":562},"k17evynnzmmag96rw4rpybyydx86m0py","kd7an8ppnz1q2np9tc5yw4qenn86mg6h",[557,556,213,555,558,214],{"evaluatedAt":565,"extractAt":566,"updatedAt":567},1778683958622,1778683762612,1778684097619,{"_creationTime":569,"_id":570,"community":571,"display":572,"identity":578,"providers":582,"relations":588,"tags":591,"workflow":592},1778694480889.9556,"k17cw5h9amytcw2kg63ygtqqxn86nsp8",{"reviewCount":8},{"description":573,"installMethods":574,"name":576,"sourceUrl":577},"Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior",{"claudeCode":575},"NeoLabHQ/context-engineering-kit","root-cause-tracing","https://github.com/NeoLabHQ/context-engineering-kit",{"basePath":579,"githubOwner":580,"githubRepo":581,"locale":18,"slug":576,"type":248},"plugins/kaizen/skills/root-cause-tracing","NeoLabHQ","context-engineering-kit",{"evaluate":583,"extract":587},{"promptVersionExtension":206,"promptVersionScoring":207,"score":210,"tags":584,"targetMarket":218,"tier":219},[213,214,585,412,586],"code-analysis","call-stack",{"commitSha":254},{"parentExtensionId":589,"repoId":590},"k17884m6t3p8517a1d2zjp8zbd86n13x","kd7a3rj13ezgx1wgm0jfh08hsx86n0sz",[586,585,213,412,214],{"evaluatedAt":593,"extractAt":594,"updatedAt":593},1778695268236,1778694480890]