钉钉群聊与消息。Use when 收发/搜索消息、建群、群治理、Bot/Webhook、文件、AI/A2UI 卡片流式，或仅限 IM 的消息谓词筛选。跨源主题/行为轨迹走 dingtalk-aisearch；DING/班级群走 dingtalk-misc；邮件走 dingtalk-mail。

Reviews, validates, and safely merges Dependabot pull requests for the sq.io site (site/, Bun lockfile). Use when clearing site dependency PRs, triaging Dependabot failures, or checking Lighthouse impact before merge.

Diagnose and fix a reproducible failure in an existing project. Use for crashes, broken behavior, or failing checks, not greenfield planning.

Diagnose and fix a reproducible failure in an existing project. Use for crashes, broken behavior, or failing checks, not greenfield planning.

Diagnose and fix a reproducible failure in an existing project. Use for crashes, broken behavior, or failing checks, not greenfield planning.

Agent runbook for evaluating an existing PDB directory through the separately installed first-party Proteina-Complexa CLI. Use to refold or score designs, compute interface pAE, i_pLDDT, scRMSD, motif RMSD, or designability, run complexa analysis, or assess third-party BindCraft, AlphaProteo, or RFdiffusion outputs. SKILL.md selects and invokes the evaluation configuration; bundled executables only inspect local readiness and write a run manifest.

Applies Dart 3 pattern matching, switch expressions, and destructuring idiomatically to validate data schemas, handle algebraic data types, and decompose control flow. Use when refactoring complex if-else chains, parsing polymorphic JSON or API responses, destructuring Lists, URI/path segments, String.split() tokens, Records, or Maps, or enforcing exhaustiveness on sealed classes. Don't use for simple boolean conditions, single-variable type promotion (use `is`), or basic collection filtering.

Apply Tranmere-Web's established archive UI language when designing or changing site pages, React components, result lists, player tables, match reports, team sheets, honours, filters, statistics and calls to action. Use for any visual or interaction work in packages/site that should match the Results, Match and Players pages.

Triage all open GitHub issues, PRs, and discussions in the current repository by fanning out up to 100 parallel subagents (one per item), then produce a single prioritized report ranking which PRs to review first, which issues to address first, and which discussions need maintainer attention. Use when the user asks to "triage open issues/PRs", "triage discussions", "prioritize the backlog", "what should I review first", "sweep the repo", or any request to bulk-evaluate open GitHub work and recommend an order.

Triage all open GitHub issues, PRs, and discussions in the current repository by fanning out up to 100 parallel subagents (one per item), then produce a single prioritized report ranking which PRs to review first, which issues to address first, and which discussions need maintainer attention. Use when the user asks to "triage open issues/PRs", "triage discussions", "prioritize the backlog", "what should I review first", "sweep the repo", or any request to bulk-evaluate open GitHub work and recommend an order.

The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase 1 = propose the team (no files created, wait for user confirm). Phase 2 = create .squad/ scaffolding, casting state, .gitattributes for merge drivers, and the always-on built-ins (Scribe, Ralph, Rai, Fact Checker). Loaded on demand when the coordinator detects no .squad/team.md exists.

Run PowerToys UITest.Next suites in persistent Hyper-V VMs over PowerShell Direct. Validate full default and constrained suites on Windows 10 and Windows 11, plus applicable ARM64 guests, then automatically hand implementation tasks to ui-tests-pipeline-ci for commit/push and CI validation. Local green is not end-to-end completion. Use for agentic UI-test iteration, reusable standard-user desktops, payload staging, evidence export, VM customization, clean baselines, or hosts without nested virtualization. Keywords: Hyper-V, local VM, virtual machine, PowerShell Direct, Copy-VMFile, VMBus, checkpoint, unattend, autounattend, ISO, Windows 10 LTSC, Windows 11, ARM64, Windows on ARM, UI tests, UITest.Next, winappcli, TRX, CI handoff.

Check local Basic Memory projects with bm doctor, explain the findings, and run the suggested fixes once the user agrees. Use when search misses or repeats notes, or a save looks lost.

Value bar for tests. Use when writing, changing, reviewing, or pruning tests: an authoring gate for new tests plus an audit workflow for low-value, implementation-coupled, or duplicative tests and the test-only production seams they keep alive.

Black-box security audit of a DEPLOYED AI agent (not the MCP server behind it) — tool-call hijacking, cross-session memory poisoning, confused-deputy via connected tools, agent-to-agent IDOR, excessive agency / unconfirmed destructive actions, and privilege compromise where the agent holds broader perms than the user. Use when the target is a live assistant/agent product with tool access (bookings, email, payments, file/RAG, browsing) rather than a raw LLM chat box or an MCP server you can read.

CI/CD pipeline security hunting — GitHub Actions workflow injection, secret exfiltration, self-hosted runner poisoning, dependency confusion, OIDC token theft, and supply chain attacks. Covers sisakulint scanning, manual workflow analysis, and chaining CI/CD bugs into critical findings. Use when a target has public repos, GitHub Actions, CircleCI, Jenkins, or GitLab CI.

Audits Android codebases for ANR risks and diagnoses ANR stack dumps. Use this skill when scanning Android code for ANR risks or triaging ANR stack dumps. Don't use for non-ANR crashes, dropped frames, general CPU profiling, or Perfetto system traces.

Wire an existing ecosystem into the LoRA training system so it appears as a trainable base model in the training form. Adds the base-model entry, schema enums, orchestrator validation, feature flag, and per-ecosystem default params. Use when a model family (already in basemodel.constants.ts) needs training support — e.g. AI-Toolkit ecosystems like Anima, HiDream, Boogu. Always checks @civitai/orchestration-client for the ecosystem's training input type first.

Add a new ecosystem and base model to basemodel.constants.ts. Use when onboarding a new model family from providers like Baidu, ByteDance, Google, etc. Handles ECO constants, BM constants, ecosystem record, family (creates new if needed), license (creates new if needed), and base model record. Optionally triggers add-generation-support at the end.

Screenshot localhost/local dev-server pages across viewports and compare them for visual regression. Use when asked to "screenshot my local site", "capture localhost pages", "visual diff", "compare screenshots", "responsive screenshots", "check breakpoints", "visual regression", or capture a Portless app at a named .localhost URL. Not for public URLs or writing e2e tests.