1.6K skills · sorted by relevance
Manages agent isolation levels and resource boundaries. Configures strict, moderate, and permissive isolation profiles. Activate on 'isolation level', 'agent isolation', 'resource boundaries', 'sandboxing', 'agent containment'. NOT for permission validation (use dag-permission-validator) or runtime enforcement (use dag-scope-enforcer).
The English summary is being prepared. Showing the original description.
Modifies DAG structure during execution in response to failures, new requirements, or runtime discoveries. Supports node insertion, removal, and dependency rewiring. Activate on 'replan dag', 'modify workflow', 'add node', 'remove node', 'dynamic modification'. NOT for initial DAG building (use dag-graph-builder) or scheduling (use dag-task-scheduler).
The English summary is being prepared. Showing the original description.
Time-travel debugging for DAG executions. Inspect agent state at any node, replay decisions with modified inputs, compare execution traces side-by-side, and identify where reasoning diverged. Inspired by LangGraph Studio's state-editing model and Temporal's event history. Activate on "debug DAG", "replay execution", "time travel debug", "inspect node state", "what went wrong at step", "compare runs", "execution diff". NOT for live monitoring (use dag-runtime + websocket-streaming), failure analysis (use dag-ops), or general code debugging.
The English summary is being prepared. Showing the original description.
Analyze hierarchical DAG-like systems by separating undirected substrate from ordering metadata, then classifying diamonds, mixers, shortcuts, and hidden cycle structure. Use for workflow architecture, citation or genealogy DAG comparison, and information-flow diagnosis. NOT for ordinary cycle detection in arbitrary graphs, one-node runtime debugging, or systems with no real ordering constraint.
The English summary is being prepared. Showing the original description.
Choose, compare, and decompose work into the right coordination topology: dag, workflow, manager-driven team, swarm, blackboard, team-builder, or recurring loop. Use when the coordination shape is unclear, when you need topology-native breakdown instructions instead of a generic DAG, or when planning topology and runtime topology may differ. NOT for actual execution, node-level skill matching, or framework/tool installation.
The English summary is being prepared. Showing the original description.
Operations, debugging, and optimization for DAG workflows. Performs root cause analysis on failures, profiles execution performance, aggregates results from parallel branches, bridges context between nodes, and learns patterns from execution history. Activate on "DAG failed", "why did it fail", "root cause", "performance profile", "aggregate results", "merge branches", "execution patterns", "optimize DAG". NOT for planning DAGs (use dag-planner), executing DAGs (use dag-runtime), or validating outputs (use dag-quality).
The English summary is being prepared. Showing the original description.
Validates agent outputs against schemas and quality criteria, scores confidence, detects hallucinations, monitors convergence, decides when to iterate, and synthesizes actionable feedback. Use when checking if a node's output is acceptable, scoring confidence, detecting fabricated content, deciding whether to re-execute, or generating improvement feedback. Activate on "validate output", "check quality", "confidence score", "hallucination check", "should we iterate", "improvement feedback". NOT for executing DAGs (use dag-runtime), planning DAGs (use dag-planner), or matching skills (use dag-skills-matcher).
The English summary is being prepared. Showing the original description.
Use when wrangler deploys silently fail or produce wrong artifacts, secrets upload as empty strings, custom domain DNS is not resolving, route assignment broke after rename, observability/tail logs are needed, D1/KV/R2 bindings are missing, OAuth scope errors block a command, cookies on a redirect are not attaching, or the worker exceeds CPU time. Triggers: "Tenant or user not found", "Authentication error" on wrangler d1 push, secret length is 0 after upload, route returns origin not worker, "compatibility_date too old", 1101 errors, custom_domain assignment lost on script rename. NOT for AWS Lambda / Vercel Edge / Deno Deploy (different runtimes), Cloudflare Zero Trust, or R2-specific tuning.
The English summary is being prepared. Showing the original description.
Implement executable BDI reasoning with explicit negation, paraconsistent revision, trigger-based commitment updates, and abduction. Use for runtime agent semantics and conflicting desires. NOT for purely axiomatic modal logic, black-box planners, or classical logic without operational semantics.
The English summary is being prepared. Showing the original description.
Expert guide for Backend.AI distributed computing platform. Automatically activates when users ask about: - Backend.AI architecture, components (Manager, Agent, Storage Proxy, Webserver, App Proxy) - Features (session scheduling, Sokovan orchestrator, multi-tenancy, resource allocation) - APIs (REST, GraphQL), authentication, RBAC authorization - Container runtime (kernels, jail sandbox, hook library, virtual folders) - Accelerator support (CUDA, ROCm, TPU, NPU, Graphcore IPU) - Client SDKs (Python, Java, JavaScript, PHP) - Setup, requirements (Python 3.13+, Docker, PostgreSQL, Redis, etcd) - How WebUI connects to/interacts with Backend.AI backend - Plugin interfaces, development setup, infrastructure Use when user mentions "Backend.AI", "backend.ai", "Sokovan", component names, or asks about the backend platform this WebUI connects to. allowed-tools: WebFetch, Read
The English summary is being prepared. Showing the original description.
Load when creating, auditing, refactoring, or repairing an Agent Skill for reuse, governance, and runtime efficiency.
The English summary is being prepared. Showing the original description.
Safely localize unknown Unity games, especially Japanese-to-Chinese projects. Use to discover Unity version/layout/backend, migrate translations across game versions, extract occurrence-mapped text from serialized assets, embedded CSV, bytecode, UI, Localization StringTables, Utage, or middleware, bridge rows through AiNiee-style translation, validate and transactionally write approved candidates, audit residual and runtime-only text or AutoTranslator diffs, diagnose TMP fonts and Addressables/IL2CPP failures, locate saves, or acceptance-test SHA-verified patches.
The English summary is being prepared. Showing the original description.
Auto-activate for uv build, hatch build, PyApp, PYAPP_*, wheel assets, GitHub release matrices, cargo-zigbuild, or python-build-standalone. Not for runtime deployment.
The English summary is being prepared. Showing the original description.
Auto-activate for litestar_granian, GranianPlugin, litestar run Granian options, runtime threads, HTTP/2, TLS, access logs, metrics, static mounts, or worker lifecycle. Not for non-Granian servers.
The English summary is being prepared. Showing the original description.
Auto-activate for Dockerfile, compose, Railway, Cloud Run, GKE, systemd, Kubernetes, Terraform, deploy scripts, or granian/litestar run at runtime. Not for packaging artifacts.
The English summary is being prepared. Showing the original description.
Auto-activate for Google ADK, LlmAgent, Runner, SQLSpecSessionService, google-genai, AgentRuntime, AgentGroup, SpecTree, DynamicWorkflow, FunctionTool, or SSE agent chats. Not for offline ML training.
The English summary is being prepared. Showing the original description.
Use when publishing a local PRD Markdown file to DingTalk Docs or Drive with version-history preflight and read-back, or when validating an approved Product Delivery Package through its fail-closed dry-run path. Package mode real writes require a trusted host approval capability and are unavailable in the current Agent runtime.
The English summary is being prepared. Showing the original description.
方案到交付 Workflow：当用户显式调用 `$solution-to-delivery`，或明确要求运行“方案到交付”完整流程时使用。 把已确认产品方案转成经过独立 Review 的 PRD、适用的 UI/HTML/截图、版本拆分和 Product Delivery Package；当前 Agent Runtime 只做 Package 发布 dry-run，真实写入保持 authorization_required。
The English summary is being prepared. Showing the original description.
Audit agent runtimes and their tests for lifecycle inference, capability overload, context pollution, correlated verification, prompt-only control, false success, dead compatibility paths, test-only seams, and complexity without contribution. Use for whole-repository agent audits, slop or dead-code triage, test contribution reviews, large refactors, tool/context simplification, and cleanup requests that need proof before deleting code or tests.
The English summary is being prepared. Showing the original description.
Align, run, audit, and publish GEODE benchmark comparisons against Agent-World arXiv 2604.18292v1 across MCP-Mark, BFCL V4, and tau2-bench. Use for Agent-World or AgentWorld comparison requests, cross-suite agent benchmark design, Tau2 comparator/profile diagnosis, paired thin-runtime-versus-GEODE experiments, mean-accuracy@8 replication, or benchmark comparability and artifact reviews.
The English summary is being prepared. Showing the original description.
GEODE prompt-writing standards. Use when creating or editing runtime prompts, system prompts, tool/developer instructions, model-facing identity text, prompt templates, or scaffold rules that affect model behavior; especially when avoiding identity assertions such as "You are ...".
The English summary is being prepared. Showing the original description.
Runtime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for agent-tree overhead audit (context-audit).
The English summary is being prepared. Showing the original description.
Coordinate staged or parallel jobs across coding-agent runtimes and subagents: routes by capability/risk, isolates writers in worktrees, arbitrates results. NOT for a single-agent task (mk:cook).
The English summary is being prepared. Showing the original description.
Runtime router for context decisions: read-more/stop/ask/assume/delegate, minimal read-set, compaction timing. Model: Write/Select/Compress/Isolate. NOT for .codex/ overhead audit (mk:context-audit).
The English summary is being prepared. Showing the original description.