全部能力

Supervise and manage an inner Claude Code instance running in tmux. Use this skill when you need to delegate implementation work to an inner Claude while focusing on task planning, progress monitoring, and end-to-end acceptance testing. Ideal for long-running tasks that would otherwise exhaust a single Claude's context window.

Use this skill for proactive backend health audits in an InsForge project — security misconfigurations, performance regressions, and system health issues surfaced by `diagnose advisor`, plus the backend-side deep-dives that pair with each advisor issue. Also use this skill when a user reports backend-wide performance degradation (high CPU/memory, all responses slow, connection pool exhaustion, lock contention) without a single failing request. Trigger on requests like "health check", "audit my backend", "review security", "check RLS policies", "find slow queries", "backend performance review", "high CPU/memory", "everything is slow", "EC2/database/system health", or pre-launch readiness audits. For reactive runtime errors with a single concrete failing request (SDK error objects, HTTP 4xx/5xx, function failures, deploy failures), use `insforge-debug` instead.

配置、部署并管理 Senpi Trading Runtime（OpenClaw 插件 @senpi-ai/runtime），用于自动化链上仓位追踪及 DSL 追踪止损保护。适用于用户需要创建或修改 runtime YAML 文件、配置 DSL（Dynamic Stop-Loss）退出引擎参数（阶段、层级、时间型减仓）、设置 position_tracker 扫描器监控 Hyperliquid 钱包仓位、通过 CLI 安装/列出/删除 runtime，或查看 DSL 追踪仓位的场景。该 runtime 不创建策略钱包；需先通过 Senpi MCP 创建/获取策略钱包，再在 runtime YAML 中关联该已有钱包。触发词包括 senpi、Senpi runtime、DSL exit、stop-loss tiers、position tracker、trailing stop、openclaw senpi、dsl_preset 或 strategy YAML configuration。

Install and configure feedgrab — the universal content grabber. Use when user needs to set up feedgrab, configure API keys, login to platforms, or diagnose…

Registers state-type triggers that automatically fire functions when key-value state is created, updated, or deleted within a scope. Use when building reactive side effects, change watchers, audit logs, cache invalidation, notification dispatchers, or any observer pattern where data changes should trigger downstream processing.

Integrates OpenTelemetry tracing, metrics, and logging into iii workers. Use when setting up distributed tracing, Prometheus metrics, custom spans, or connecting to observability backends.

Django + Celery async task patterns — configuration, task design, beat scheduling, retries, canvas workflows, monitoring, and testing. Use when adding…

黑底 + CRT 网格扫描线 + $ 命令行标题 + 薄荷绿大字 + 三档 tag

Starter Coach V2 — conversational 6-step skill that guides users to build their own automated DEX spot-trading bot on OKX DEX. Onboard → User Profile → Build Strategy → Paper Trade → Go Live. Uses OnchainOS CLI for all on-chain data, backtesting, and trade execution. No freeform trading code — emits validated JSON strategy specs. Triggers: starter coach, trading bot builder, strategy builder, help me build a bot, vibe trading, paper trade, backtest strategy, go live trading, build trading strategy, 交易机器人, 策略构建, 量化策略, 自动交易, 做单机器人, 帮我建策略

When the user wants to set up, debug, or interpret app install attribution — including SKAdNetwork (SKAN), Apple's AdAttributionKit, Google Play Install…

Use when planning, running, or learning from chaos engineering experiments. Triggers on "chaos experiment", "fault injection", "gameday", "resilience test",…

Build, modify, debug, and deploy agents with Agentforce Agent Script. TRIGGER when: user creates, modifies, or asks about .agent files or aiAuthoringBundle…

Use when writing or editing Cucumber `.feature` files, page-object classes, or step definitions in a project that depends on the `cucumber-sentences` Ruby gem…

Optimize resumes for software engineering, PM, and technical roles

Use when adding, retiring, or auditing feature flags. Triggers on "add a flag", "ship behind a flag", "rollout plan", "kill switch", "stale flags", "flag…

Pre-production audit that scans a codebase for security, database, deployment, code quality, AI/LLM, dependency, frontend, and observability issues. Intercepts deploy commands and blocks until critical items pass. Stack-agnostic. Use for "run ship gate", "am I ready to ship", "pre-launch audit", "can I deploy", "push to production", "go live checklist", "preflight check". Not for CI/CD setup or infra provisioning.

Conventional Commits 1.0.0 + best-practice workflow for git commit messages that serve four readers — `git log` scanners, `git blame` tracers, `git bisect` hunters, and AI agents (LLMs rebuilding context after `/clear`, reviewing PRs, generating changelogs, answering natural-language history queries). Five founding principles (atomic / leaves-repo-green / why-over-what / imperative / searchable), five-step workflow (diff inspection → staging → type decision tree → secrets blocklist → pre-commit checklist), explicit Breaking-Change / Revert / Amend / Trailer protocols, and a dialect scaffolder that generates per-project `docs/references/COMMIT.md` for project-specific extensions (domain proper nouns, custom trailers like `Refs:` / `Flag:` / `Plan SC:`, workflow hooks like PDCA / Linear / Jira / squash-merge PRs). ALWAYS trigger this skill when the user: (1) asks to write, generate, or improve a commit message (2) pastes a commit-message draft for review or critique (3) asks "should I split this commit?" / "what type for this change?" / "is this breaking?" (4) is finishing a logical unit of work and about to run `git commit` (5) mentions stage / staging / amend / revert / fixup / cherry-pick in a commit-authoring context (6) asks how to set up PDCA / Linear / Jira-driven auto-commits (7) requests scaffolding a `COMMIT.md` dialect file for a project Triggers (multi-lingual): EN: commit, git commit, stage, commit message, breaking change, conventional commits, revert, fixup, amend, cherry-pick, changelog KO: 커밋, 깃 커밋, 스테이지, 커밋 메시지, 커밋 룰, 컨벤셔널 커밋, 리버트, 되돌리기, 어맨드, 커밋 컨벤션, 커밋 메시지 검토 JA: コミット, git コミット, ステージ, コミットメッセージ, ブレーキング チェンジ, リバート, アメンド ZH: 提交, git 提交, 暂存, 提交信息, 提交消息, 重大变更, 回滚, 修订 ES: commit, mensaje de commit, preparar, cambio incompatible, revertir FR: commit, message de commit, indexer, changement incompatible, revert DE: Commit, Commit-Nachricht, Staging, breaking change, revert IT: commit, messaggio di commit, modifica incompatibile, revert Do NOT trigger for: pure code generation unrelated to git, branch/merge/ rebase mechanics not about message authoring, CI/CD pipeline configuration, or non-git version-control systems. Audience: developers writing git commits. Use technical terms directly. Korean prose variant available at `lang/ko/SKILL.md` for Korean-first readers — the convention itself stays English-default regardless of variant.

This skill should be used when the user asks to "search for exposed devices on the internet," "perform Shodan reconnaissance," "find vulnerable services using…

Data privacy and regulatory compliance specialist for GDPR, CCPA, HIPAA, and international data protection laws. Use when implementing privacy controls,…

This skill should be used when the user asks to "pentest SSH services", "enumerate SSH configurations", "brute force SSH credentials", "exploit SSH…