AI & ML

arcasilesgroup Bundle

Decomposes an approved spec into a phased execution plan with bite-sized tasks, agent assignments, and gate criteria — the contract /ai-build executes. Trigger for 'break this down', 'create a plan', 'what tasks do we need', 'lets start implementing', 'scope changed re-plan'. Hard gate: user approves before /ai-build can run. Not for ambiguous requirements; use /ai-brainstorm instead. Not for execution; use /ai-build instead.

arcasilesgroup Bundle

Canonical implementation gateway: reads approved plan.md, resolves stack from manifest, deterministic-routes each task to its adapter, dispatches the build agent in an isolated worktree, runs TDD self-validation per task, then a single final quality loop with one bounded quality-remediation pass on the full changeset before /ai-pr. Trigger for 'go', 'start building', 'execute the plan', 'implement it', 'lets do this', 'build the plan', 'resume', 'continue'. Not without an approved plan; run /ai-plan first. Not for multi-concern specs needing decomposition; use /ai-autopilot instead. Not for a single function or subcomponent; use /ai-code.

arcasilesgroup Skill

Reviews code changes with human-quality judgment: PR reviews, file reviews, diff analysis, architecture feedback. Default mode runs the full specialist roster through 3 macro-agents; pass `--full` for one agent per specialist. Trigger for 'review this', 'give me feedback', 'look over my PR', 'any issues with this', 'is this merge-ready'. Not for evidence-backed gates; use /ai-verify instead. Not for narrative writing; use /ai-prose instead.

arcasilesgroup Skill

Codebase-only read-only research dispatcher. Thin wrapper around the ai-explore agent for architecture mapping, dependency tracing, pattern identification, and risk surfacing — dispatch for any question spanning >= 1 file, module, or import edge. Trigger for 'explore the codebase', 'where does X live', 'map this module', 'what depends on Y', 'trace this import chain'. Not for external evidence with citations; use /ai-research instead.

arcasilesgroup Skill

Runs security gates: SAST with OWASP/CWE mapping, dependency vulnerability scans, secret detection, SBOM generation for compliance, pre-release security verdict. Trigger for 'is this secure', 'audit dependencies', 'check for secrets', 'security report', 'is this package safe', 'compliance review'. Not for governance process; use /ai-governance instead. Not for runtime payload inspection; use prompt-injection-guard hook instead. Not for code quality metrics; use /ai-verify quality instead.

45ck Skill

Define state machines and lifecycles, then create Beads issues from the findings. Converts ambiguous states, silent transitions, and undefined exits into trackable Beads tasks with priorities and dependencies.

45ck Skill

Build a conceptual model and create Beads issues from the findings. Converts ambiguities, overloaded concepts, and unclear states into trackable Beads tasks with priorities and dependencies.

unicomai Bundle

Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say "write a report", "draft a proposal", "make a contract", "fill in this form", "reformat to match this template", or any task whose final output is a .docx file. Even if the user doesn't mention "docx" explicitly, if the task implies a printable/formal document, use this skill.

unicomai Bundle

【首选技能】凡涉及知识网络的任何操作，优先使用 bkn-creator，不要直接触发 create-bkn。 bkn-creator 是 BKN 全生命周期管理器，负责流程路由识别、阶段门禁、子流程编排与结果回执。 覆盖新增、查找、更新、删除（CRUD）并采用渐进式执行。 触发词：创建知识网络、新建BKN、BKN建模、本体建模、对象类、关系类、动作类、 概念组、BKN文件、BKN push、BKN pull、对象类绑定、关系类映射、 对象类提取、关系类提取、实体关系抽取、 知识网络查询、知识网络更新、知识网络删除。 不应触发：仅查询平台功能、Agent 对话、Vega/Catalog 操作、 健康巡检、数据源连接器等非 BKN 生命周期操作时，应由 ontology-core 等其他技能处理。

unicomai Bundle

Generate, edit, and read PowerPoint presentations. Create from scratch with PptxGenJS (cover, TOC, content, section divider, summary slides), edit existing PPTX via XML workflows, or extract text with markitdown. Triggers: PPT, PPTX, PowerPoint, presentation, slide, deck, slides.

unicomai Bundle

name: knowledge-spider

unicomai Skill

全局归档协议。只要任务需要写入任何文件（含 PLAN.md、报告、JSON 等归档物），必须按本技能执行 Session→ARCHIVE_ID、TIMESTAMP、双轨路径（根段须为 archives/）、回读校验与状态回执；WebUI 的 archive_grid 必须用 Markdown 中语言标识为 json 的围栏代码块输出。

unicomai Skill

指导业务知识网络（BKN）建模，输出符合 BKN 2.0.0 的对象类型、关系类型、操作类型、风险类型与概念分组定义。适用于用户提出本体设计、知识网络建模、实体关系梳理、Action 设计、Schema 评审、从文档提取初稿或扩展现有 BKN 的场景。

unicomai Bundle

官方Microsoft Playwright CLI网页自动化工具，支持所有主流浏览器的无头/有头自动化操作，包括页面导航、元素交互、截图、录制、测试等功能。当用户提到网页自动化、浏览器操作、爬虫、截图、录制用户操作、E2E测试时触发。

unicomai Bundle

从 Markdown 文件或网页链接提取文章并发布到微信公众号。适用于需要“自动创建草稿/提交发布”、统一微信样式（standard/viral）和批量复用发布流程的场景。

kitfunso Bundle

Maximize agent capability by spawning sub-agents, leveraging all available resources, thinking deeply, and making no mistakes. Use when tackling complex or high-stakes tasks that demand thoroughness.

kitfunso Bundle

Two-pass development pattern for cleaner output. Use after implementing a large feature, complex refactor, or any substantial code change. Separates implementation from cleanup for better results. Two focused agents beat one constrained agent.

kitfunso Bundle

Research-before-coding workflow. Use BEFORE implementing any significant feature to check for existing libraries, MCP servers, patterns, or solutions. Prevents reinventing the wheel. Use when adding new dependencies, building integrations, or starting features that might have existing solutions.

kitfunso Bundle

Eval-Driven Development (EDD) — treating evals as unit tests for AI-assisted development. Use when building or modifying AI workflows, agent pipelines, prompt engineering, or any feature where output quality needs measurement. Define success criteria BEFORE implementing.

zaxbyhub Skill

Mandatory publication protocol for the GitHub Copilot coding agent and custom Copilot agents in ragappv3. Load when assigned to an issue or when committing, pushing, opening/updating/readying a PR, or closing out remote CI. Routes to the single canonical commit-pr source of truth.

ronald-koh Bundle

Move issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.

ronald-koh Bundle

Build and sharpen a project's domain model. Use when the user wants to pin down domain terminology or a ubiquitous language, record an architectural decision, or when another skill needs to maintain the domain model.

stiron92-byte Bundle

텍스트(에세이/명언/스크립트)를 입력하면 AI 이미지 + TTS 나레이션 + 자막 + BGM을 조합하여 완성된 롱폼 나레이션 영상(1920x1080, 30fps)을 자동 생성합니다. 모든 처리는 MCP 서버를 통해 호스트 머신에서 실행되므로 컨테이너 환경에서도 동작합니다. 최종 영상은 사용자의 바탕화면(~/Desktop/narration_output/)에 저장됩니다. 사용: /narration-video [텍스트파일경로 또는 주제]

snowbanksdk Skill

How to use CrystalJson, the custom JSON library in SnowBank.Core (namespace SnowBank.Data.Json). Covers the JsonValue DOM (JsonObject / JsonArray / JsonString / JsonNumber / JsonBoolean / JsonNull / JsonDateTime), the read-only vs mutable model, the CrystalJson static API (Serialize / Parse / Deserialize) and CrystalJsonSettings, the Roslyn source generator for fast reflection-free serializers and read-only/writable proxies ([CrystalJsonConverter] / [CrystalSerializable]), the IJsonSerializable / IJsonPackable / IJsonDeserializable interfaces, MutableJsonValue / ObservableJsonValue and JsonPath. Use whenever code parses, builds, reads, mutates, or serializes JSON with these types, reads optional fields with defaults, declares a generated JSON converter/proxy, or implements custom JSON (de)serialization. Use it even when the request only says "serializer", "converter", or "serialize/deserialize a record, document, or model" without naming JSON: in SnowBank-based code (document stores, sync layers, Layers, mode

snowbanksdk Skill

Advanced engineering for sophisticated FoundationDB layers with the .NET client (FoundationDB.Client / SnowBank) — the cluster model and transaction lifecycle (proxies, resolvers, tlogs, storage servers, the sequencer/version clock), latency/throughput optimization (batching reads with GetValuesAsync / Task.WhenAll, removing round-trip dependencies, snapshot reads), high-contention avoidance, and distributed patterns (change feeds, version-stamp logs, watch fan-out, version-as-clock leases, retention, fencing/tombstones). Use when building or reviewing a performance-sensitive or distributed layer (a change feed, queue, pub/sub, worker pool, multi-node observable view), tuning transaction latency/throughput, or reasoning about conflicts, the 5-second limit, or cross-node liveness. Builds on the foundationdb-keys-and-layers and foundationdb-transactions skills — read those first.

sethdford Skill

Run a complete SCRUM sprint with all ceremonies — Product Owner authors stories, Tech Lead designs, Scrum Master orchestrates implementers, Verifier+Aspect-Panel guard quality, Sprint Auditor adversarially audits, Retro feeds back to /tune-agent. Triggers on /scrum, "run a sprint", "scrum me this", "ship this with full process".

sethdford Skill

Prove that work actually behaves correctly by spawning the verifier agent to run the code and capture evidence. Use before claiming a task complete, before commit, when in doubt about whether tests prove the right thing. Triggers on /verify, "prove it works", "verify this", "did the change actually work", and any request phrased "verify that <function/file/behavior> works", "verify the function …", "run the tests and report the truth", or "check that <X> really does <Y>" — these all mean spawn the verifier agent, not run the tests yourself in the parent.

sethdford Skill

Show the RL value-function snapshot for all agents — mean reward, recent trend, anomalies, top tuning candidates. Use weekly to monitor agent quality. Triggers on /rl-status, "agent rewards", "rl status", "which agents are degrading".

sethdford Skill

Propose a Reflexion-style patch to a specific agent's prompt based on evidence of recurring failures. Use when the same agent makes the same class of mistake twice, when /mine-transcripts surfaces an agent in agent-tuning.md, or when /eval flags a regression on an agent. Triggers on /tune-agent, "tune the X agent", "fix the agent prompt".

sethdford Skill

Show prompt cache hit rate trends and flag regressions. Use when user asks about cache performance, asks why sessions feel expensive, or wants to verify cache health. Triggers on /cache-report, "cache hit rate", "cache stats", "is caching working".

different-ai Bundle

Create new OpenCode agents with a gpt-5.2-codex default.

different-ai Bundle

Automate the worktree-based UX PR workflow: rebase against origin/dev, verify via Chrome MCP, and attach evidence. Triggers when user mentions: - "rebase against origin/dev and run chrome mcp" - "one pr per worktree with screenshots" - "worktree ux improvements PR flow"

first-fluke Bundle

Product manager that decomposes requirements into actionable tasks with priorities and dependencies

first-fluke Bundle

Bug diagnosis and fixing specialist - analyzes errors, identifies root causes, provides fixes, and writes regression tests

first-fluke Bundle

Automated multi-agent orchestrator that spawns CLI subagents in parallel, coordinates via Serena Memory, and monitors progress

first-fluke Bundle

Backend specialist for APIs, databases, authentication, and server-side logic using FastAPI, Node.js, or other frameworks