mycc

Query SwanLab experiment metrics and run status. Use when checking training/producer metrics, comparing runs, or investigating experiment health. Keywords: swanlab, metrics, experiment, loss, reward, training progress, wandb.

Launch a background agent to monitor a long-running remote job (K8s, SLURM, CI). Use when submitting jobs that need async monitoring. Keywords: monitor, watch job, background agent, submit and watch, check job status.

Generate a weekly report summarizing commits and PRs across the main repo and all external/ submodules. Keywords: weekly report, 周报, work summary, 工作总结.

Capture reusable knowledge after milestones. Systematically review what was learned and persist it to the right layer. Keywords: sediment, crystallize, capture, persist, remember, learned, milestone, retrospective.

Hypothesis-first bug diagnosis. Verify the user's diagnosis before proposing alternatives. Keywords: bug, diagnose, debug, fix, hypothesis, root cause, crash, error, timeout, traceback.

Build a first-failure timeline for distributed incidents. Use when debugging crashes, hangs, watchdog timeouts, collective mismatches, or cascading errors where the last error is often not the root cause.

Convert local debugging results into high-quality upstream issues or RFC comments. Use when filing bugs to external projects with clear reproduction, first-failure evidence, root-cause hypothesis, and scoped fix suggestions.

Use when the user asks or you need codex'suggestion to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing

Execute-observe-diagnose-fix loop for verifying code changes through execution. Covers local tests (pytest, unittest), local services, remote jobs (kubectl, submit), CI/CD pipelines, and cluster deployments. Use when code correctness requires runtime verification. Keywords: run tests, submit, deploy, verify, debug, resubmit, pytest, kubectl, check logs, watch, diagnose, tail logs.

Query pod logs via Victoria Logs API. Use when checking remote job logs, debugging errors, or searching for specific log patterns across K8s pods. Keywords: logs, query logs, victoria logs, check logs, pod logs, search logs.

Create and manage Claude Code skills following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns, file paths, content patterns), enforcement levels (block, suggest, warn), hook mechanisms (UserPromptSubmit, PreToolUse), session tracking, and the 500-line rule.

Guidance for developing under a projects managed by pixi. Always use when workspace managed by pixi (have pixi.toml or pixi.lock in root directory.) Covers all you should know while developing under a pixi-based project: pixi environment commands (install, run, shell, add, task), multi-environment management (-e flag, features), task configuration in pixi.toml, dependencies (conda vs PyPI), lock files, and development workflows. Helps with environment setup, package management, running tasks, debugging pixi.toml errors, and production deployment patterns.