Agent 工作流

可复用的 Agent 工作流和编排模式

1513 个 Skills 可用

Skills 列表

remembering-conversations

remembering-conversations

435agent-workflows

在说“我不知道”、猜测或将任何话题视为新话题之前,你必须调用此技能,无论问题看起来多么琐碎。它补充了其他仅保存部分记录的记忆系统。搜索过去的对话是恢复实际所说内容的唯一方法。

obra avatarobra
获取
shared

shared

434agent-workflows

Retired — its runtime-neutrality contract moved to docs/contracts/runtime-neutrality.md. Triggers: none — not routable.

boshu2 avatarboshu2
获取
heal-skill

heal-skill

433agent-workflows

Check or repair structural hygiene in AgentOps skill packages. Triggers: \"heal skill\", \"repair skill hygiene\", \"audit skill structure\", \"check skill package\".

boshu2 avatarboshu2
获取
pr-prep

pr-prep

433agent-workflows

Prepare PR commits and body. Triggers: \"pr-prep\", \"pr prep\", \"prepare pr commits and body.\".

boshu2 avatarboshu2
获取
hungarian-humanizer

hungarian-humanizer

432agent-workflows

Detect and remove AI-generated markers from Hungarian text, making it sound like a native Hungarian speaker wrote it. Use when asked to "humanize", "naturalize", or "remove AI feel" from Hungarian text, or when editing .md/.txt files containing Hungarian content. Identifies 26 patterns (12 Hungarian-specific + 14 universal) and 4 style markers.

bencium avatarbencium
获取
security

security

431agent-workflows

Run authorized repository security scans for vulnerabilities, dependency risk, secrets, and binary policy. Triggers: "security", "run repository security scans for", "security skill".

boshu2 avatarboshu2
获取
research

research

430agent-workflows

Answer a bounded question with current cited evidence. Triggers: "research", "investigate this question", "find evidence". (Investigating a repository routes to codebase-recon.)

boshu2 avatarboshu2
获取
plan

plan

430agent-workflows

Shape or refine the existing bead or caller intent without a second planning artifact. Triggers: "plan", "discover and plan", "shape this goal".

boshu2 avatarboshu2
获取
anti-ceremony

anti-ceremony

430agent-workflows

Guard outcome work against process overhead. Triggers: RPI pre-Plan guard; explicit "full anti-ceremony audit" requests.

boshu2 avatarboshu2
获取
product

product

430agent-workflows

Create or refine PRODUCT.md while separating evidence, aspiration, users, value, and non-goals. Triggers: "product", "create PRODUCT.md", "product boundary".

boshu2 avatarboshu2
获取
implement

implement

430agent-workflows

执行一个从 bead 或调用者意图出发的有界 RED 到 GREEN 实验;返回派生的主体身份并核对事实。触发词:“implement”、“implement this bead”、“run the experiment”。完整的从计划到验证的请求路由到 rpi。

boshu2 avatarboshu2
获取
status

status

430agent-workflows

Report observable AgentOps evidence without selecting work. Triggers: "status", "show AgentOps status".

boshu2 avatarboshu2
获取
goals

goals

430agent-workflows

兼容性别名——已重命名为 fitness。使用 fitness 来衡量声明的项目健身目标。触发词:"goals"(已弃用)。

boshu2 avatarboshu2
获取
swarm

swarm

429agent-workflows

Dispatch explicit disjoint packets exactly once through a caller-selected executor. Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".

boshu2 avatarboshu2
获取
analyzing-data

analyzing-data

429agent-workflows

Queries the data warehouse with SQL and answers business questions about data. Use when answering anything that needs warehouse data - counts, metrics, trends, aggregations, joins across tables, data lookups, or ad-hoc SQL analysis (for example "who uses X", "how many Y", "show me Z", "find customers", "what is the count").

astronomer avatarastronomer
获取
sf-industry-cme-epc-model

sf-industry-cme-epc-model

424agent-workflows

Salesforce Industries CME EPC product-modeling skill for Product2-based catalog creation. Use when creating EPC products, configuring product attributes, building offer bundles with Product Child Items, or reviewing EPC DataPack JSON metadata for product catalog changes. TRIGGER when: user creates or updates Product2 EPC records, AttributeAssignment payloads, AttributeMetadata/AttributeDefaultValues, Offer bundles, or ProductChildItem relationships. DO NOT TRIGGER when: designing OmniScripts/FlexCards/Integration Procedures (use sf-industry-commoncore-* skills), implementing Apex business logic (use sf-apex), or troubleshooting deployment pipelines (use sf-deploy).

jaganpro avatarjaganpro
获取
nelson

nelson

415agent-workflows

Orchestrates multi-agent task execution using a Royal Navy squadron metaphor — from mission planning through parallel work coordination to stand-down. Use when work needs parallel agent orchestration, tight task coordination with quality gates, structured delegation with progress checkpoints, or a documented decision log.

aspegio avataraspegio
获取
council

council

414agent-workflows

Collect independent perspectives for an explicitly high-stakes or contested judgment. Triggers: "council", "multi-judge review", "independent perspectives".

boshu2 avatarboshu2
获取
dispatch

dispatch

411agent-workflows

Dispatch background AI worker agents to execute tasks via checklist-based plans. Use when the user says 'dispatch' to delegate work to background agents, e.g. 'dispatch sonnet to review this', 'dispatch opus to fix the bug', 'dispatch a worker to research X'.

bassimeledath avatarbassimeledath
获取
dart-setup-ffi-assets

dart-setup-ffi-assets

406agent-workflows

指导智能体使用 Dart 的 Native Assets 钩子系统(通过 hook/build.dart 和 hook/link.dart,利用 package:hooks 和 package:native_toolchain_c)将 C/C++ 源代码编译并打包为动态或静态库(Code Assets)。当用户要求“设置原生资产”、“编译 C/C++ 源代码”、“打包动态库”、“构建原生 C 代码”、“链接原生资产”、“实现 build.dart 或 link.dart 钩子”或“在 Dart/Flutter 中集成 C/C++ 互操作”时使用。帮助智能体避免手动工具链编排,并配置安全的哈希验证二进制下载或使用 package:record_use 映射的高级链接器树摇优化。

dart-lang avatardart-lang
获取
heygen

heygen

406agent-workflows

[DEPRECATED] Use `create-video` for prompt-based video generation or `avatar-video` for precise avatar/scene control. This legacy skill combines both workflows — the newer focused skills provide clearer guidance.

heygen-com avatarheygen-com
获取
humanizer-ru

humanizer-ru

406agent-workflows

Качество русского текста для агента. Russian text quality for agents: proofreading and AI-slop cleanup for Cyrillic text. Триггеры: очеловечь, вычитай, отредактируй, поправь, причеши, проверь текст, убери канцелярит, humanizer. Молча снимает жёсткие запреты в собственном русском выводе агента; чужой текст молча не трогает. Use when надо убрать из русского текста канцелярит, воду и нейросетевую манеру, не сломав смысл, факты и голос автора. Три режима по запросу: редактура, аудит без переписывания, точечная правка одной категории. Со скиллом едет детерминированный сканер scripts/scan.py: считает хард-баны, категории маркеров, ритм и морфологию, печатает ЧИСТОТА: N/100, поэтому правка измерима («было N, стало M»). Флаг --genre academic/legal/fiction/news снимает маркеры, законные для научного, юридического и новостного регистра. Работает ТОЛЬКО с русским: для английского humanizer, для итальянского humanizer-it. НЕ используй для: перевод, написание с нуля, грамматика без стилистики, код.

ilyautov avatarilyautov
获取
avoid-feature-creep

avoid-feature-creep

405agent-workflows

Prevent feature creep when building software, apps, and AI-powered products. Use this skill when planning features, reviewing scope, building MVPs, managing backlogs, or when a user says "just one more feature." Helps developers and AI agents stay focused, ship faster, and avoid bloated products.

waynesutton avatarwaynesutton
获取
convex

convex

405agent-workflows

Routes Convex work to the right builder skill and covers the handful of rules that apply everywhere: validators on every function, withIndex over filter, idempotent mutations, internal functions for scheduling. Use when a task mentions Convex and no more specific skill matches, or as the first stop before picking one.

waynesutton avatarwaynesutton
获取