agentsclimarketplace

Debug & triage

5,150 rows, by stacks then stars

1,113 of these skill files have been read, by 1,020 distinct authors, and what they tell an agent counted. What Debug & triage authors agree on, and what they forbid

  • Simplified project management

    celeryhq/simplified-ai/skills/simplified-project-management Skill

    2★ repo

    Manage Simplified project-management boards, statuses, tasks, assignees, tags, dependencies, comments, activity, and searches through the Simplified hosted MCP connector. Use when the user explicitly asks to inspect or change Simplified PM data, create or triage tasks, update assignments or status, manage boards and columns, review dependencies, or complete tracked work. Do not invoke for generic coding or debugging unless the request also involves updating Simplified project-management records.

  • Systematic debug

    IrfanSadiqRahat/constellation/methodology/systematic-debug Skill

    no license2★ repo

    Five-phase root cause process with role-aware diagnostics. Bisect, minimize, hypothesize, verify, document.

  • Vbot cli

    Vironnimo/vbot/resources/skills/vbot-cli Skill

    2★ repo

    Configure, inspect, and operate vBot through the vbot CLI, including locating the vBot root and runtime data. Use when asked to start, stop, restart, update, or uninstall vBot, set up provider credentials (API key or OAuth), find vBot files or diagnose stored state, or list/add/edit/remove agents, projects, sessions, channels (Telegram, Discord), cron jobs, task-model bindings, prompts, skills, extensions, or settings — or to inspect models, tools, logs, debug traces, Provider subscription usage, and Session usage statistics (tokens, runs, errors, tool and skill usage).

  • Review pro triage

    tufantunc/review-pro/core/skills/review-pro-triage Skill

    2★ repo

    Stage 1 of review-pro: classify changed files, detect relevant specialist reviewers, detect active stacks, scope context per reviewer, and emit a dispatch plan. Use to start a review-pro review, triage a PR/branch, or fan out reviewers.

  • Systematic debugging

    grimaldost/craft-collection/plugins/humblepowers/skills/systematic-debugging Skill

    2★ repo

    Root-cause-first debugging in four phases — investigate (read the full error, reproduce, check recent changes, instrument component boundaries), pattern-match against working examples, test one hypothesis at a time, then fix the cause with a failing test. Use when any bug, test failure, or unexpected behavior lacks a proven cause, when a fix is being proposed before the data flow was traced, when the previous fix didn't work, especially under time pressure (guessing is slower than the protocol), and when three or more fixes have failed — treat that as an architecture signal and raise it with the user instead of attempting a fourth. The bright line: no fix before the root cause is identified with evidence; in multi-component systems, log what enters and exits each boundary before theorizing. Hands the reproducing test to test-driven-development and the resolution claim to verification-before-completion. Not for changes whose cause is already proven (just fix them) and not for performance tuning without a defect (profile first).

  • Feedback triage

    grimaldost/craft-collection/plugins/session-workflow/skills/feedback-triage Skill

    2★ repo

    Triage a tool's accumulated dogfooding feedback reports into a leverage-ordered improvement backlog — reconcile what already shipped, cluster findings by underlying cause rather than symptom, assign each cluster a disposition (attack this tool, route out to the tool that owns it, or decline), apply a promotion gate (reinforced across reports, specific, actionable), and emit a triage document with a status-tracked promotion table. Use on "triage the feedback backlog", "cluster the feedback reports", "what should this tool fix next", "promote the recurring feedback", or "/feedback-triage". Explicitly invoked maintenance — never run proactively; it reads a whole corpus. If the tool's binding registers its own triage template (e.g. keel's reflection-triage), follow that template. Not for consolidating journal entries into guidance (that is consolidate-knowledge), not for a corpus of one report with no prior triage (nothing to cluster yet — a 1-report delta over an existing baseline IS a valid later pass), not for triaging GitHub issues or a PR queue, and not for triaging a governed series' own reflections into durable checks — the owning method tool's triage skill (e.g. keel's keel-triage) does that, not this generic feedback pass.

  • No debug

    logicleap-labs/claude-plugins/plugins/no-debug/skills/no-debug Skill

    2★ repo

    MANDATORY before declaring code "done", "ready", or ending a turn after writing or debugging a function/handler/module. Use whenever you added a debug print while working something out — console.log, debugger, pdb.set_trace(), breakpoint(), binding.pry, byebug, dd()/var_dump()/print_r(), dbg!(), a "print('here')" or "console.log('DEBUG', x)". Forces you to strip the debug noise before shipping, and to reach for a real logger when you actually need persistent logs. Triggers on "let me add a log to see", "just debugging", "temporary print", "I'll remove this later", "console.log to check", "drop a breakpoint".

  • Observability review

    tunahanaliozturk/secure-dotnet-skills/skills/observability-review Skill

    2★ repo

    Use when reviewing logging, tracing, and metrics in a .NET app — structured logging, OpenTelemetry, correlation, and avoiding PII / secret leakage in telemetry.

  • Systematic debugging

    Alex7develop/my-agent-skills/skills/systematic-debugging Skill

    2★ repo

    Находить корневую причину бага системно — через сужение области, а не через угадывание и случайные правки. Используй при сообщениях "не работает", "падает с ошибкой", "неожиданное поведение", "баг", когда причина неочевидна из первого взгляда на стектрейс. Особенно важно применять вместо того, чтобы менять код наугад и смотреть, помогло ли.

  • Diagnosing bugs

    toverux/grimoire/skills/diagnosing-bugs Skill

    2★ repo

    Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

  • Issue triage

    risadams/ink-and-agency/skills/business-product/issue-triage Skill

    no license2★ repo

    Triage a bug or Jira ticket into ranked root-cause candidates and proposed solution paths. Read-only unless the user opts in to publish. Use when the user says "triage this", "triage [TICKET-KEY]", "what's causing this bug", "help me find the root cause", or invokes /issue-triage.

  • Debug

    risadams/ink-and-agency/skills/codebase-build/debug Skill

    no license2★ repo

    Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.

  • Debugger

    risadams/ink-and-agency/skills/quality-security/debugger Skill

    no license2★ repo

    Use when you need to diagnose and fix bugs, identify root causes of failures, or analyze error logs and stack traces to resolve issues.

  • Hoi4 review debug

    Fostanico/hoi4-ai-modding-skills/skills/hoi4-review-debug Skill

    2★ repo

    Diagnose, review, improve, balance, optimize, migrate, and test existing Hearts of Iron IV mods from source through an isolated in-game run. Use for whole-mod health audits, gameplay design/balance/UX review, error.log triage, Windows crash dumps/minidumps, parser or scope bugs, broken GUI/assets/localisation, AI behavior, performance, save/lifecycle risks, compatibility, version updates, template audits, regression plans, or user-approved Steam and game testing.

  • Doc triage

    jamestexas/agents/skills/doc-triage Skill

    2★ repo

    Curated library of Claude Code subagents and skills (23 agents, 20 skills) with an idempotent installer that symlinks into ~/.claude. Frontmatter-driven; spec-compliant with Anthropic and Gemini schemas.

  • Linear escalation triage

    jamestexas/agents/skills/linear-escalation-triage Skill

    2★ repo

    Curated library of Claude Code subagents and skills (23 agents, 20 skills) with an idempotent installer that symlinks into ~/.claude. Frontmatter-driven; spec-compliant with Anthropic and Gemini schemas.

  • Marimo

    nibzard/skills/skills/marimo Skill

    2★ repo

    Assistant for creating, editing, and debugging reactive Python notebooks with marimo. Use when you need to build marimo notebooks, debug reactive execution, add interactive UI elements, or convert traditional notebooks to marimo format. Provides code patterns, utility functions, and best practices for marimo development.

    The same file is in 2 other repositories

  • Marimo

    nibzard/skills/skills/marimo/skills/marimo Skill

    2★ repo

    Assistant for creating, editing, and debugging reactive Python notebooks with marimo. Use when you need to build marimo notebooks, debug reactive execution, add interactive UI elements, or convert traditional notebooks to marimo format. Provides code patterns, utility functions, and best practices for marimo development.

    The same file is in 2 other repositories

  • Github issue

    eddmann/agent-toolkit/skills/github-issue Skill

    no license2★ repo

    Create a GitHub issue from context or conversation

  • Spark operations cli

    kimtth/ms-fabric-skills-dev-starter/.agents/skills/spark-operations-cli Skill

    no license2★ repo

    Diagnose failed Spark jobs, unhealthy Livy sessions, and performance bottlenecks in Microsoft Fabric via read-only CLI triage. Use when the user wants to: (1) diagnose why a Spark job, notebook run, or Lakehouse job failed, (2) triage stuck or dead Livy sessions, (3) identify OOM, shuffle spill, or data skew, (4) retrieve driver and executor logs or Spark Advisor findings, (5) copy event logs and start a local Spark History Server, (6) diagnose all Spark activities within a failed pipeline run. Triggers: "diagnose my failed notebook", "why did my spark job fail", "triage spark failure", "diagnose pipeline run failure", "why did my pipeline fail", "livy session stuck in starting", "spark executor OOM", "check spark advisor findings", "shuffle spill diagnosis", "why did my lakehouse job fail", "diagnose lakehouse table load", "data skew diagnosis", "open spark history server locally", "analyze spark failure logs", "spark job triage".

  • Redis cli

    chaunsin/agent-skills/skills/redis-cli Skill

    2★ repo

    Redis command-line interface (redis-cli) reference and usage guide. Use this skill whenever the user mentions redis-cli, Redis CLI, or any task involving querying, inspecting, debugging, or managing Redis from the command line. Triggers on key/value reads and writes, SCAN or keyspace inspection, INFO or MONITOR troubleshooting, latency and bigkeys analysis, Pub/Sub, Lua scripts, ACL and client management, cluster operations, import/export, and Redis module workflows such as RediSearch, RedisJSON, Bloom/CF/TopK, vector search, and time series commands. Use even if the user does not explicitly say "redis-cli" when the work is clearly terminal-based Redis operations.

  • It service desk triage

    agent-blueprint/agent-blueprint-skills/plugins/agent-blueprint-skills/skills/it-service-desk-triage Skill

    no license2★ repo

    Blueprint pattern for an AI agent team for IT help desk and service desk automation: ticket triage, incident classification, and ticket resolution. 5-agent architecture with routing orchestration. Use when a user asks you to build IT help desk automation, ticket triage, incident classification, service desk agents, or ITSM AI. Triggers: IT help desk, ticket triage, service desk automation, incident classification, ITSM agents, auto-resolve tickets, L1 support automation, help desk AI, incident routing, service request automation, ticket categorization.

  • Debugging and error recovery

    GuillemRoca/agent-skills-android/skills/debugging-and-error-recovery Skill

    2★ repo

    Use when encountering unexpected behavior, crashes, or test failures in Android. Six-step triage from reproduction to regression guard, using Logcat, Android Studio debugger, and profiling tools.

  • Observability and instrumentation

    GuillemRoca/agent-skills-android/skills/observability-and-instrumentation Skill

    2★ repo

    Use when adding logging, crash reporting, or performance monitoring, or before shipping a release that must be watched in production. Covers Crashlytics, Play Vitals thresholds, structured logging with Timber, reportFullyDrawn, release-health monitoring, and CI performance gates.

  • Bug report writing

    The-AI-Directory-Company/agents-and-skills/skills/bug-report-writing Skill

    2★ repo

    Write actionable bug reports with precise reproduction steps, expected vs actual behavior, environment details, severity classification, and root cause analysis templates.

  • Debugging guide

    The-AI-Directory-Company/agents-and-skills/skills/debugging-guide Skill

    2★ repo

    Step-by-step debugging methodology for systematic bug finding — covers reproduction, isolation, hypothesis testing, root cause analysis, and fix verification.

  • Debugger

    kevinaimonster/skill-hub/skills/debugger Skill

    no license2★ repo

    快速调试助手。帮用户快速定位和修复代码 bug。当用户说「帮我调试」「这个 bug 怎么修」「代码报错了」「不知道为什么不工作」「运行出错」「debug」「找 bug」「这段代码有问题」「排查问题」「定位错误」「fix this bug」「why is this not working」「error」「报错」「异常」时触发。关键词:调试、debug、bug、报错、异常、错误、fix、排查、定位、修复、不工作、出错、崩溃、undefined、null pointer、stack trace、error message

  • Error explainer

    kevinaimonster/skill-hub/skills/error-explainer Skill

    no license2★ repo

    报错解读助手。帮用户看懂错误信息、排查问题原因、给出修复方案。当用户说「这个报错什么意思」「帮我看看这个错误」「为什么报错」「运行出错了」「debug」「报错了怎么办」「这个error怎么解决」「错误排查」「看不懂报错」「error message」「stack trace」「异常」「崩溃了」时触发。关键词:报错、错误、error、bug、异常、exception、stack trace、traceback、崩溃、crash、debug、调试、排错、排查、故障、500错误、404、TypeError、NullPointerException、segfault、OOM、内存溢出、编译错误、运行时错误、syntax error、npm error、pip error、docker error、git error、permission denied、connection refused、timeout

  • Incident report

    kevinaimonster/skill-hub/skills/incident-report Skill

    no license2★ repo

    故障复盘与事故报告助手。帮用户撰写故障复盘报告、Postmortem、RCA根因分析、事故时间线。当用户说「写个故障复盘」「事故报告」「postmortem」「RCA分析」「故障总结」「线上事故」「故障报告」「incident report」「根因分析」「复盘报告」时触发。关键词:故障复盘、事故报告、postmortem、RCA、根因分析、故障总结、事故时间线、故障影响、修复方案、改进措施、SLA、SLO、SLI、MTTR、MTTD、五个为什么、5 Whys、鱼骨图、incident report、outage、downtime、故障等级、P0、P1、P2、线上故障、系统故障、服务降级、故障定级

  • Cron doctor

    suryast/free-ai-agent-skills/cron-doctor Skill

    2★ repo

    Diagnose and triage cron job failures. Checks job states, identifies error patterns, prioritizes by criticality, generates health reports. Triggers on: cron failures, job health check, scheduled task errors, cron diagnosis, job not running, backup failed.

  • Debug detective

    xmqywx/claude-code-skills/skills/debug-detective Skill

    no license2★ repo

    Systematically debug an error by tracing its origin through the codebase, identifying root causes, and suggesting targeted fixes. Produces a structured investigation log.

  • Systematic debugging

    jtsang4/efficient-coding/skills/systematic-debugging Skill

    2★ repo

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    The same file is in 30 other repositories

  • Nestjs workers transports ops

    xirothedev/skills/skills/nestjs-workers-transports-ops Skill

    no license2★ repo

    Use for NestJS production worker and integration tasks involving microservice transports, hybrid apps, queues, scheduled jobs, cache stores, health checks, structured logging, lifecycle events, shutdown hooks, WebSocket gateways, or non-HTTP Nest runtimes.

  • Debug

    sssstwee/tastedistill/plugins/tastedistill/claude-skills/debug Skill

    2★ repo

    Diagnose failures, broken behavior, regressions, test failures, runtime errors, stale state, rendering bugs, and repeated failed fixes. Use when something does not work, used to work, crashes, fails tests, or needs root-cause proof. Not for product planning or release readiness.

  • Tasted debug

    sssstwee/tastedistill/plugins/tastedistill/skills/tasted-debug Skill

    2★ repo

    Diagnose failures, broken behavior, regressions, test failures, runtime errors, stale state, rendering bugs, and repeated failed fixes. Use when something does not work, used to work, crashes, fails tests, or needs root-cause proof. Not for product planning or release readiness.

  • Ci failure triage

    ClarentCinematics/Codex-Skills-for-Enterprise/skills/ci-failure-triage Skill

    2★ repo

    Diagnose failed CI runs, build logs, test output, deployment checks, or pipeline summaries and produce a root-cause hypothesis, reproduction path, likely owner, fix plan, and escalation guidance. Use when Codex needs to triage broken builds, flaky tests, failed checks, or release-blocking automation failures.

  • Data quality triage

    ClarentCinematics/Codex-Skills-for-Enterprise/skills/data-quality-triage Skill

    2★ repo

    Review CSV exports, dataset samples, schema notes, metric inputs, or dashboard source data for null rates, duplicate keys, stale dates, inconsistent enum values, schema gaps, and quality caveats. Use when Codex needs to turn data-quality evidence into a triage report without inventing missing values or metric definitions.

  • Debugging and error recovery

    qiuy-collab/AutoFlow.skill/integrations/agent-skills/debugging-and-error-recovery Skill

    2★ repo

    Guides systematic root-cause debugging. Use when tests fail, builds break, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need a systematic approach to finding and fixing the root cause rather than guessing.

    The same file is in 2 other repositories

  • Systematic debugging

    qiuy-collab/AutoFlow.skill/integrations/superpowers/systematic-debugging Skill

    2★ repo

    Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

    The same file is in 8 other repositories

  • Debugging playbook

    ralfyishere/rules-with-receipts/.claude/skills/debugging-playbook Skill

    2★ repo

    Debug systematically instead of guessing - symptom, reproduction, hypotheses, discriminating tests, evidence, root cause, fix, regression test. Activate whenever something is broken, failing, wrong, or behaving unexpectedly - error messages, failing tests, crashes, wrong output, performance regressions, "it worked yesterday", "why is this happening", intermittent issues. Also applies to non-code failures: a report with wrong numbers, a workflow producing bad results, a prompt giving bad outputs.

  • 25 NODE INSPECT DEBUGGER

    subhansh-dev/agent-maxxing/engineering/25-NODE-INSPECT-DEBUGGER Skill

    2★ repo

    Debug Node.js with node inspect, --inspect, breakpoints, CDP, heap, and CPU profiles.

  • Debugging patterns

    subhansh-dev/agent-maxxing/engineering/debugging-patterns Skill

    2★ repo

    Systematic debugging methodology — read errors completely, reproduce first, bisect, add logging, trace flow.

  • Workflow debugging

    subhansh-dev/agent-maxxing/examples/workflow-debugging Skill

    2★ repo

    Systematically debug a production issue using the debugging chain.

  • 23 TASKFLOW INBOX TRIAGE

    subhansh-dev/agent-maxxing/workflows/23-TASKFLOW-INBOX-TRIAGE Skill

    2★ repo

    Example TaskFlow pattern for inbox triage, intent routing, waiting on replies, and later summaries.

  • Debugger

    rakibulism/agent-skills-os/skills/debugger Skill

    2★ repo

    Diagnose bugs from error messages, stack traces, logs, or reproductions. Produces a root-cause hypothesis, a minimal verification step, and a concrete fix. Use when the user reports an error, a crash, unexpected output, or a test failure.

  • Engineering debug

    rakibulism/agent-skills-os/skills/engineering-debug Skill

    2★ repo

    Structured debugging session — reproduce, isolate, diagnose, and fix. Trigger with an error message or stack trace, "this works in staging but not prod", "something broke after the deploy", or when behavior diverges from expected and the cause isn't obvious.

    The same file is in 3 other repositories

  • Blameless postmortem

    tbhb/social-skills/plugins/process-theater/skills/blameless-postmortem Skill

    2★ repo

    Runs industry-standard blameless postmortems with severity classification, timeline reconstruction, and five-whys root cause analysis. Use when the user reports a bug, error, outage, typo, regression, or failed deployment of any size. Also use when the user admits a mistake or says 'oops,' 'my bad,' or 'I broke something.'

  • Triage

    shikanime-labs/skills/skills/workflow/triage Skill

    2★ repo

    A curated catalog of self-improved agent skills for Hermes and compatible agents

  • Flaky test triage

    jukrap/ai-agent-playbook/skills/delivery/flaky-test-triage Skill

    2★ repo

    Use when diagnosing, reproducing, stabilizing, quarantining, or documenting flaky, nondeterministic, timing-dependent, or intermittent tests.

  • Ci failure triage

    jukrap/ai-agent-playbook/skills/devops/ci-failure-triage Skill

    2★ repo

    Use when diagnosing failing CI jobs, build pipelines, deployment checks, flaky tests, environment drift, or release automation failures.

  • Observability incident triage

    jukrap/ai-agent-playbook/skills/devops/observability-incident-triage Skill

    2★ repo

    Use when triaging incidents, production errors, alerts, latency, error rates, queue backlogs, job failures, logs, metrics, traces, or post-incident runbooks.

  • Issue planning triage

    jukrap/ai-agent-playbook/skills/project/issue-planning-triage Skill

    2★ repo

    Use when converting specs, bugs, reviews, or worklogs into scoped issues and task batches.

  • Truestack observability

    adtn0810/truestack/skills/truestack-observability Skill

    2★ repo

    Instrument a self-hosted backend so you can see what it's doing in production — structured logging, metrics, distributed tracing, health-check monitoring, and SLO/burn-rate alerting. Use whenever the user wants to "make this service observable", "add observability", set up "structured logging" / "JSON logs", add "OpenTelemetry" / "OTel" / "OTLP" / an "OTel Collector", add "metrics" / "Prometheus" / "Grafana" / "RED" / "USE", add "distributed tracing" / "spans" / a "correlation ID" / "request ID" / "trace ID in logs", monitor or alert on an existing "health" / "readiness" / "liveness" endpoint (creating or wiring the endpoint itself belongs to truestack-deploy-and-runtime), set up "SLOs" / "error budget" / "burn-rate alerts", or fix "noisy alerts", "high cardinality" / "too many timeseries", "logs filling the disk", "add a redaction processor to the telemetry pipeline", or "I have no telemetry yet / can't see what my service is doing".

  • Truestack root cause debugging

    adtn0810/truestack/skills/truestack-root-cause-debugging Skill

    2★ repo

    Investigate a bug, error, crash, failing test, regression, or unexpected/slow behavior that is a DEFECT, and fix it at the root (slowness owned by a specific discipline — a slow migration, deploy-time downtime — routes to that skill). Use the moment something is reported broken or an error/stack trace is pasted — even a one-line "this isn't working". Confirms the real root cause with evidence before changing anything, and applies a permanent fix, never a temporary patch.

  • Pacsomatic

    Lord1Egypt/scientific-agent-toolkit/scientific-skills/pacsomatic Skill

    2★ repo

    Operator toolkit for nf-core/pacsomatic matched tumor-normal workflows from BAM inputs. Use this skill when the user needs to validate run inputs, generate pacsomatic-compliant samplesheets, prepare reproducible Nextflow launch artifacts, run locally or submit to schedulers (LSF/Slurm/PBS/SGE), and triage execution failures. Triggers on requests to run pacsomatic, prepare launch commands/scripts, perform dry-run checks, or troubleshoot pipeline startup and scheduler submission errors.

    The same file is in 1 other repository

  • Observability

    m-binimran/dev-pack/skills/observability Skill

    2★ repo

    Add error monitoring and structured logging to a Next.js + Supabase app — Sentry for errors, request-scoped logs, and useful context without leaking PII. Use when setting up monitoring or debugging production issues.

  • Lean tautology triage

    r-irbe/proof-skills/skills/lean-tautology-triage Skill

    2★ repo

    USE FOR: triaging Lean 4 theorem statements or proof sites that may be vacuous, tautological, smoke-test-only, reflexive-by-rfl, `: True` placeholders, bare `decide` closures, or automation-only proofs of supposedly substantive claims. Use this skill whenever proof review reports "vacuous", "tautology", "trivial", "placeholder", "smoke theorem", "rfl self-projection", "DEFINITE", or "HIGH" proof-quality risk. DO NOT USE FOR: ordinary proof writing (use @lean-proof); whole-project QA lifecycle (use @lean-quality-engine); running one enforcement script without interpretation (use @lean-enforcement); theorem search (use @lean-research). TRIGGERS: tautology, vacuous, trivial proof, smoke theorem, placeholder theorem, proof quality, `: True`, `by decide`, `by rfl`, rfl self-projection, suspicious automation, non-triviality audit.

  • Node inspect debugger

    john-data-chen/hermes-agent-backup/skills/software-development/node-inspect-debugger Skill

    2★ repo

    Debug Node.js via --inspect + Chrome DevTools Protocol CLI.

    The same file is in 3 other repositories

  • Systematic debugging

    john-data-chen/hermes-agent-backup/skills/software-development/systematic-debugging Skill

    2★ repo

    4-phase root cause debugging: understand bugs before fixing.

    The same file is in 1 other repository

  • Diagnosing bugs

    maurigre/mgr-method/skills/diagnosing-bugs Skill

    no license2★ repo

    Discipline for diagnosing hard bugs and performance regressions — requires a reproduction loop that goes RED on the bug BEFORE any hypothesis (signal before theory). Finds the root cause and stops; the non-trivial fix is handed to spec-create. Use when the user asks to diagnose or debug something, or reports something broken, throwing, failing or slow.