Guide observability setup, metrics design, and alerting configuration. Use when: new service instrumentation, SLO definition, alert design, maturity assessment. Keywords: observability, metrics, traces, golden signals, alerting, SLO, 可觀測性, 告警.
Set up Skene configuration for a project. Use when starting a new PLG analysis, when .skene.config is missing, or when the user says "skene init", "set up skene", or "configure skene".
Autonomous plan execution - fresh subagent per task with automated code review between tasks. No human-in-loop, high throughput with quality gates.
Skill testing methodology - run scenarios without skill (RED), observe failures, write skill (GREEN), close loopholes (REFACTOR).
Gate 4 of development cycle - dispatches 5 specialized reviewers (code, business-logic, security, test, nil-safety) in parallel for comprehensive code review feedback.
Evidence-first completion gate - requires running verification commands and confirming output before making any success claims.
Branch completion workflow - guides merge/PR/cleanup decisions after implementation is verified complete.
Isolated workspace creation - creates git worktrees with smart directory selection and safety verification for parallel feature development.
Review reception protocol - requires technical verification before implementing suggestions. Prevents performative agreement and blind implementation.
Core orchestration protocol for StatsClaw agent teams framework
Deploy vLLM to Kubernetes (K8s) with GPU support, health probes, and OpenAI-compatible API endpoint. Use this skill whenever the user wants to deploy, run, or serve vLLM on a Kubernetes cluster, including creating deployments, services, checking existing deployments, or managing vLLM on K8s.
Automate traffic violation reporting through Chengdu Police official WeChat account using Open-AutoGLM and ADB. This skill handles the complete workflow: starting mitmproxy for location mocking, launching WeChat, navigating to Chengdu Police official account, entering Rong-E-Xing service, selecting traffic violation reporting type, choosing video import mode, selecting violation location with mocked GPS coordinates, setting violation time, inputting violation description, uploading video evidence, and submitting the report. Use this skill whenever the user mentions traffic violation reporting, automated reporting, WeChat police account reporting, Rong-E-Xing service, or wants to automatically report traffic violations detected from dashcam or security camera footage.
This skill should be used when working with Graphite (gt) for stacked pull requests. Use when users mention gt commands, stack management, PR workflows, or when dealing with dependent branches. Essential for understanding stack navigation, branch relationships, and Graphite's mental model.
This skill should be used when running CI checks iteratively and fixing failures. Use when executing make targets (fast-ci, all-ci, ci), iterating on lint/format/type/test errors, or needing the devrun agent pattern for pytest/ty/ruff/prettier/make/gt commands.
Write section/subsection prose into per-unit files under `sections/`, so each unit can be QA’d independently before merging into `output/DRAFT.md`. **Trigger**: subsection writer, per-section writing, split sections, sections/, 分小节写, 按章节拆分写作. **Use when**: `Approve C2` is recorded and evidence packs exist; you want evidence-first drafting without a monolithic one-shot draft. **Skip if**: `DECISIONS.md` approval is missing, or `outline/evidence_drafts.jsonl` is incomplete/scaffolded. **Network**: none. **Guardrail**: do not invent facts/citations; no ellipsis/TODO/placeholder leakage; keep citations subsection- or chapter-scoped (prefer subsection); H3 body files must not contain headings.
Initialize a new workspace by copying the standard artifact template (STATUS.md, CHECKPOINTS.md, UNITS.csv, DECISIONS.md + folders). **Trigger**: workspace init, initialize workspace, workspace template, 初始化 workspace. **Use when**: 启动任何 pipeline run（必须先有 workspace 工件与目录骨架）。 **Skip if**: workspace 已初始化且不希望覆盖既有文件（除非显式 `--overwrite`）。 **Network**: none. **Guardrail**: 不要修改 `.codex/skills/workspace-init/assets/` 模板；默认不覆盖已有文件。
This skill should be used when working with GitHub CLI (gh) for pull requests, issues, releases, and GitHub automation. Use when users mention gh commands, GitHub workflows, PR operations, issue management, or GitHub API access. Essential for understanding gh's mental model, command structure, and integration with git workflows.
Scaffold a complete AWS Lambda function project using the terraform-aws-lambda Terraform module (moritzzimmer/lambda/aws). Generates Terraform configuration, runtime-specific build tooling (Makefile), and minimal function code with correct event source wiring and IAM setup. Use this skill whenever the user wants to create a new Lambda function, scaffold a Lambda project, set up a serverless function with Terraform, or asks about using the terraform-aws-lambda module. Also trigger when the user mentions "new lambda", "lambda scaffold", "lambda boilerplate", or wants to add a Lambda function to their infrastructure.
