Results for “experiment-logs”

Investigate a problem, log it to the debug changelog, cross-check past issues, and suggest a non-duplicate fix.

Debugging is the scientific method under time pressure.

Turn assumptions, funnel opportunities, and product questions into a prioritised, feasibility-checked experiment backlog. Filters by traffic reality, metric latency, and method feasibility — not just ICE/RICE scoring. Maintains a living portfolio with status (idea → designed → running → readout → archived). Load when the user says "what should we test next", "build an experiment backlog", "prioritise our tests", "where should we experiment", "what's worth testing", or when the experimentation orchestrator routes here.

实验执行全流程：准备代码 → 部署运行 → 监控状态 → 收集结果，支持三种运行模式

Turn engineering work into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates by mining Copilot CLI session logs, git history, and GitHub PRs.

Audits test code in any language using the academic testsmells.org 19-smell catalog, producing a severity-ranked report with specific locations and actionable fixes.

Analyze Linux system logs including auth.log, syslog, systemd journal, and auditd to reconstruct user activity, detect unauthorized access, and establish event timelines on compromised systems.

Logs the outcome of a skill execution to observations/<skill-name>/runs.md. Trigger on: "log this run", "skill worked", "skill failed", "this didn't work", "log the outcome", "record this", "note that", or after any skill completes with a clear success, partial, or failure outcome. Creates the observations file if it does not exist, then appends an entry with date, task description, skill used, outcome, what worked, what failed, and any error messages observed.

Routes runtime-log requests into an evidence packet to isolate the first actionable blocker, repeated signature, blast radius, or safest next read-only check.

Append-only event log — the probabilistic record of everything that happened in the project. Use whenever something notable happens that the project should remember — work items created/transitioned, decisions recorded, bindings changed, incidents occurred, releases shipped.

Diagnose your own behavior by reading the structured logs you leave behind — turns.jsonl, events.jsonl, chat_history.jsonl, scheduler.yaml. Use when something has gone wrong (a message didn't land, a scheduled job isn't firing, a communication pattern feels off), when you need to understand a pattern over many turns, or when cost / token usage needs auditing. Covers jq query recipes and points at the debugging-jobs / debugging-communication / debugging-drift companion guides for specific failure modes.

Track ML experiments with open-source run logging, local or self-hosted dashboards, and media visualization using SwanLab.

查看所有运行中实验的状态，可选自动收集已完成实验并推进流水线

debug-logging

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

Resume a paused experiment. Checkout the experiment branch, read results history, continue iterating.

Orchestrator for the experimentation skill suite — turn assumptions and product questions into rigorous, well-instrumented experiments and decision-grade readouts. Routes through backlog → spec → runbook → readout based on user need and existing artefacts. Platform-agnostic with PostHog as the primary binding. Load when the user asks to design an experiment, A/B test something, set up an experiment, run a holdout, test a hypothesis, decide what to test next, read out experiment results, analyse a test, or says "should we A/B test this", "experiment on the landing page", "is this lift real", "ship or kill this test", "what should we test next", "build an experiment backlog", "test the pricing page", "validate this with an experiment".

Design lean validation experiments — hypothesis, method, success criteria, sample size, timeline, and decision rules

Detect intrusion attempts, unauthorized access, and privilege escalation on Linux hosts using the auditd framework with ausearch and aureport utilities.

Turn vague "what did I do?" into evidence-backed impact statements for performance reviews, self-reviews, promotion packets, and weekly updates. Uniquely mines Copilot CLI session logs to reconstruct forgotten work, plus git commits and GitHub PRs. Enforces a 3-part impact contract (action → result → evidence). Works standalone with zero dependencies. Trigger for: "brag", "log work", "what did I do", "backfill my work history", "performance review", "self-review", "self assessment", "write impact statement", "review prep", "promo packet", "promotion case", "weekly update", "status report", "accomplishments", "what did I ship", "I forgot to log my work", "summarize my work", "track my wins", "what should I highlight", "end of half", "career growth", "work journal", or any request to document, summarize, or organize work accomplishments.

Debug agent execution by querying trace and metric tables, analyzing tool calls, durations, errors, and performance trends.

Detects DNS-based data exfiltration, tunneling, and DGA communication by analyzing query logs with entropy analysis, volume anomalies, and subdomain length detection in SIEM platforms.

Search and analyze your own session logs (older/parent conversations) using jq.

Parses Kubernetes API server audit logs (JSON lines) to detect exec-into-pod, secret access, RBAC modifications, privileged pod creation, and anonymous API access. Builds threat detection rules from audit event patterns.

Investigates slow responses, tool failures, and guardrail rejections by querying agent trace logs and performance metrics.

Datadog CLI for searching logs, querying metrics, tracing requests, and managing dashboards. Use this when debugging production issues or working with Datadog observability.

Log workouts, plan routines, track progress, and get intelligent coaching for any fitness level.

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.

Orchestrates structured experiments end-to-end: initialize, plan, run, and evolve with reproducibility tracking and hypothesis validation.

Search and analyze your own session logs (older/parent conversations) using jq.

Search and analyze your own session logs (older/parent conversations) using jq.

Search and analyze your own session logs (older/parent conversations) using jq.

PUA Loop — guided iterative development with recurring checks, completion evidence, and pause/abort markers. Use only when the user explicitly asks for loop/自动迭代 mode.

Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpret experimental data.