588 个 · 按相关度排序
Investigate failed GAIA benchmark questions by inspecting execution records and classifying causes such as missing tools, reasoning errors, or answer extraction bugs. Follow targeted fixes, verify them through another run, and save findings for future debugging.
中文简介正在准备中。当前显示英语简介。
Investigate LazyCodex and Codex bugs using reproduction results and source code. Identify the responsible repository, then prepare or submit an English GitHub report with evidence, likely causes, fix guidance, and a verification plan.
中文简介正在准备中。当前显示英语简介。
When a user corrects a factual error, trace it through stored knowledge, memory, identity settings, and fact records. Fix the underlying source, check related records where needed, and report the cause, changes, and safeguards against recurrence.
中文简介正在准备中。当前显示英语简介。
Investigate errors and unexpected behavior through reproduction, isolation, diagnosis, and a proposed fix. Receive a structured report covering the root cause, necessary code or configuration changes, and suggested tests to prevent the issue from returning.
中文简介正在准备中。当前显示英语简介。
Investigate difficult bugs by adding temporary logs to the actual execution path and reproducing the reported behavior. Analyze JSONL logs, which store one structured event per line, then fix the cause, verify regression tests, and remove debugging artifacts.
中文简介正在准备中。当前显示英语简介。
Investigate difficult bugs through explicit hypotheses, targeted logs, and repeated checks against actual data. Keep an investigation journal to track findings, examine environment differences and leftover state, and confirm the root cause before applying a fix.
中文简介正在准备中。当前显示英语简介。
Retrieve BigQuery execution records and resource metrics using the right tool for each task. The skill guides monitoring tool selection and SQL queries for performance investigations, capacity analysis, and reviews of billable compute and storage usage.
中文简介正在准备中。当前显示英语简介。
Draft incident postmortems by aligning channel updates, GitHub deploys and merges, and Datadog spikes. It opens a review PR with a correlated timeline, proposed causes, and candidate follow-up actions for humans to confirm.
中文简介正在准备中。当前显示英语简介。
Investigate production errors using Sentry stack traces, which show the code execution path, and events leading up to the failure. Identify likely causes, triggering conditions, affected users, and releases before changing code.
中文简介正在准备中。当前显示英语简介。
Investigate errors and unexpected behavior through reproduction, isolation, diagnosis, and a proposed fix. Receive a structured report covering the root cause, necessary code or configuration changes, and suggested tests to prevent the issue from returning.
中文简介正在准备中。当前显示英语简介。
Investigate failed GitHub Actions jobs using logs and recent runs. Receive a report explaining the actual failure trigger, recurrence, any verified breaking commit, and existing pull requests that may fix the issue.
中文简介正在准备中。当前显示英语简介。
Investigate unexpected LoopX behavior, such as stalled progress or conflicting next steps. Identify whether agent decisions, state reporting, or workflow rules caused the problem, then repair, validate, and record the correction.
中文简介正在准备中。当前显示英语简介。
Turn a recently solved research problem into searchable Markdown documentation. Capture symptoms, failed attempts, root causes, working code, and prevention checks, then organize the solution by category and link it to related records.
中文简介正在准备中。当前显示英语简介。
Explore open-ended design, architecture, and naming decisions through parallel agents with different perspectives. The skill groups and scores ideas, flags hidden traps, and develops promising options with concrete first steps and key risks.
中文简介正在准备中。当前显示英语简介。
Finds the root cause of a bug, test failure, or unexpected behavior before proposing any fix. Use this whenever something is broken and the cause is not yet proven — a failing test, a production error, intermittent behavior, or a symptom that appeared after a change. Also use when a fix has been attempted and did not work, or when the same bug keeps coming back.
中文简介正在准备中。当前显示原文说明。
Run a blameless postmortem for an incident caused by an AI agent or LLM feature — hallucinated facts shipped to users, runaway tool use, prompt injection, cost blowouts, or wrong actions taken autonomously. Use when asked to write up an AI incident, analyse why an agent did something wrong, or produce corrective actions after an LLM failure. Produces a structured postmortem with trace reconstruction, a root-cause layer analysis, and corrective actions including a permanent regression case. For non-AI production incidents use incident-postmortem.
中文简介正在准备中。当前显示原文说明。
Use when a GSD run failed, stalled, or produced the wrong result and the cause is unclear. Reads git history and .planning/ state and phase artifacts to diagnose root cause, then writes a report to .planning/forensics/.
中文简介正在准备中。当前显示原文说明。
Root cause analysis and debugging
中文简介正在准备中。当前显示原文说明。
Evidence-before-action diagnosis of failing ML experiments. Probes the system before guessing causes, process list, dmesg, GPU stats, log scrollback, checkpoint state, then states a hypothesis as a hypothesis and runs a smoke before claiming a root cause. Use when the user asks why a run is failing, diverging, OOMing, hanging, slow, producing weird metrics, has crashed, or asks to debug, diagnose, troubleshoot, or investigate a training issue.
中文简介正在准备中。当前显示原文说明。
Fix rsky-pds createRecord/putRecord hanging indefinitely with no error logs. Use when: (1) createSession succeeds but createRecord never returns, (2) No error appears in PDS logs despite request hanging for 60+ seconds, (3) PDS health endpoint works but write operations hang, (4) readiness probes intermittently fail on rsky-pds pod. Root cause: PDS_CRAWLERS env var configures crawler notification URLs that are called via reqwest HTTP client WITHOUT any timeout in crawlers.rs. If the crawler URL is unreachable from the cluster, every write hangs forever. Also: setting PDS_CRAWLERS="" produces [""] (one empty string element) which causes a "builder error" instead — must fully unset the env var.
中文简介正在准备中。当前显示原文说明。
Fix silent data loss when mutating Nostr replaceable events (Kind 0 profile, Kind 3 contact/follow list, Kind 10002 relay list, etc.) in client apps. Use when: (1) Following someone wipes the user's entire follow list, (2) Updating profile metadata loses existing fields, (3) Fresh browser session or mobile login causes data loss on first action, (4) Replaceable event mutation uses stale or null cached state. Root cause: Nostr replaceable events are full-replace (no partial update), so publishing based on stale/unloaded cache overwrites the canonical version. Applies to any Nostr client using React, Flutter, or similar reactive frameworks where query state may not be loaded when a mutation fires.
中文简介正在准备中。当前显示原文说明。
Fix black camera/microphone preview in Flutter macOS apps launched via `flutter run` from a terminal emulator (cmux, iTerm, Terminal.app, VS Code integrated terminal, Cursor, etc.). Use when: (1) camera plugin reports initialized but preview is black with no frames, (2) logs show "initialization completed via timeout" or similar first-frame timeout fallback, (3) AVCaptureSession.startRunning() returns without error but zero frames arrive, (4) the app's Info.plist has NSCameraUsageDescription and entitlements (com.apple.security.device.camera, audio-input) are correctly set, (5) no permission dialog ever appears, (6) same failure mode for microphone. Root cause is macOS TCC attributing camera/mic requests to the *responsible process* (the parent terminal) rather than the Flutter app itself. TCC refuses to prompt because the terminal is hardened-runtime without a camera entitlement, and silently denies. Not a bug in the camera plugin — would reproduce with ANY camera code.
中文简介正在准备中。当前显示原文说明。
Fix misleading Flutter/Dart test failures where expected data is empty ([]) or default values instead of the mocked response, caused by stale Mockito generated mocks or missing stubs being silently swallowed by try/catch in provider/repository code. Use when: (1) Test expects non-empty data but gets [], (2) Mock stubs for a method are set up but the code under test returns fallback/empty results, (3) A PR added new methods to a service class and tests that previously passed now fail with misleading "expected X, actual: empty" assertions, (4) "Generated files are out of date" CI error alongside test failures. The root cause is MissingStubError thrown by unstubbed mock methods, caught by production try/catch blocks, causing silent fallback to empty state.
中文简介正在准备中。当前显示原文说明。
Explain why counterexamples violate specifications by analyzing formal specifications (temporal logic, invariants, pre/postconditions, code contracts), informal requirements (user stories, acceptance criteria), test specifications (assertions, property-based tests), and providing step-by-step traces showing state changes, comparing expected vs actual behavior, identifying root causes, and assessing violation impact. Use when debugging test failures, understanding model checker output, explaining runtime assertion violations, analyzing static analysis warnings, or teaching specification concepts. Produces structured markdown explanations with traces, comparisons, state diagrams, and cause chains. Triggers when users ask why something failed, explain a violation, understand a counterexample, debug a specification, or analyze why a test fails.
中文简介正在准备中。当前显示原文说明。