Product & Planning

rynfar Bundle

Review or incorporate Meridian contributor changes, resume that review backlog, or validate an authorized release.

stbenjam Skill

Triage incoming Jira tickets for the acme-platform board — classify, label, and assign. Use when the sprint backlog has unclassified issues.

rynfar Skill

Review or incorporate Meridian contributor changes, resume that review backlog, or validate an authorized release.

stbenjam Skill

Exercise legacy recursive skill discovery in a dual Agent and Claude package.

zhengqiuyang Skill

Prepares and maintains a public open-source repository: version tags aligned with package versions, GitHub Releases with meaningful notes, Dependabot with a PR decision policy, issue templates, and discovery metadata (topics, badges). Use when publishing a new project, cutting a release, or cleaning up a repo before promoting it.

sergeyklay Bundle

Create, edit, search, transition, close, and triage Jira tickets via the Atlassian MCP. Use when asked to file a bug, request a feature, create a task, log a defect, search the backlog, triage findings into the tracker, edit ticket fields, transition status, or manage Jira work items. Also use when the user says 'create a Jira issue', 'file a bug', 'open a ticket', 'add to backlog', 'search Jira', 'close ticket', 'move to Done', or names any Jira issue key (e.g. 'PROJ-123'). Also use for read-only backlog sweeps: which ticket to pick up next, what is unblocked, what blocks a given key, how many issues are open. Handles type discovery, parent linking, label assignment, duplicate detection via JQL, status transitions, issue-link creation, and large queries that overflow the tool output limit. Defers all field-content formatting to the `jira-syntax` skill. Do NOT use for pull requests, changelog entries, non-Jira trackers (GitHub Issues, Linear, GitLab), or managing local TODO.md.

danthamanvoiss Skill

Prepare discovery agenda, hypotheses, questions, and risks without invented prospect facts.

danthamanvoiss Skill

Review conversion friction, hierarchy, proof, CTA, and experiment backlog.

andersonlimahw Bundle

Plan and review a learning journey: build a personalized learning roadmap with milestones and practice checkpoints, or run a retrospective over progress already made. Use when the user wants to learn a technology or concept over time and asks for a study plan, learning path, roadmap, curriculum, 'how do I learn X', 'where do I start with X', or wants to review what they have learned, identify blockers, and adjust the plan. For interactive hands-on coding instruction during a task, use learning-output-style instead. For a stateful workspace with missions and lesson artifacts, use teaching-workspace.

nervous0403 Bundle

长尾产品集合技能，覆盖低频钉钉产品：OA审批查询与处理/考勤/直播/DING紧急消息/开放平台应用管理/Agoal目标管理/日志日报周报/电子表格/开放平台文档搜索与OpenAPI逃生舱/文档内嵌白板/钉钉招聘/DWS技能市场安装/组织大脑Hrbrain/原生Markdown/PAT行为授权/多组织profile。Use when 用户提到上述任一产品，或查待审批/同意拒绝转交撤销审批/打卡/排班/OKR/日报周报/单元格读写/白板节点读写/招聘职位/JD/创建职位/搜索安装技能/开发者后台应用/未封装OpenAPI/llms.txt/dws api/人才池/员工档案/职业历程/绩效/原生.md文件/Markdown版本比较/本地草稿diff/Markdown评论/PAT授权/切换组织/跨组织/profile 等相关操作。未来审批任务或实例变化的实时监听不属于本 skill，应使用 dingtalk-event。命中后由本 skill 的「产品索引表」定位具体子产品和命令前缀，再按对应子产品说明执行。

andersonlimahw Bundle

spotify-squad plugin. Routes to its sub-skills: adversary-review, agile-ceremonies, backend-patterns, data-pipeline, devops-pipeline, frontend-patterns, mobile-patterns, new-db-schema, new-feature, new-repository, new-screen, product-discovery, qa-strategy, secure-coding-patterns, squad-coordination, ui-design-system, ux-research. Use when the task matches any of the capabilities listed below.

andersonlimahw Skill

End-to-end new feature workflow for the squad. Use when starting a new feature from scratch, coordinating across all squad roles from product discovery through deployment.

andersonlimahw Skill

Agile ceremonies and rituals facilitation. Use for sprint planning, daily standups, sprint reviews, retrospectives, backlog grooming, and team health checks.

andersonlimahw Skill

Product discovery and PRD creation. Use for writing PRDs, defining user stories, setting OKRs, feature prioritization, and product strategy.

pmlaowangba-lab Bundle

把一句话需求或会议要点补全成大厂标准的工业级 PRD。输入功能点或零散会议记录， 输出含业务背景与衡量指标、用户故事与状态流转机、字段字典（含边界值校验）、 异常分支矩阵（高并发冲突／弱网抖动／过期撤销）、核心事件埋点字典表的完整 Markdown 文档。 用户说写 PRD、需求文档、产品需求文档、功能规格、评审文档、补需求、需求评审时使用。 适用于产品经理在评审前把口头需求落成研发挑不出刺的文档。 不编造业务数据与指标；不做竞品调研；不生成 UI 稿。

agent-ecosystem Skill

Benchmark skill placed OUTSIDE any recognized skills directory, in the project tree. Use when asked to probe stray skill discovery.

agent-ecosystem Bundle

Benchmark skill for testing deeply nested resource access and nested skill discovery. Use when asked to probe nesting behavior.

wikkygao Bundle

多格式需求文档分析与整合。自动解析 Markdown、Excel、Word、思维导图文件，智能去重和补充需求信息，生成标准化的 PRD.md 文档。大文件采用分层提取避免上下文溢出；支持用户指定子目录输出；支持完整版/业务摘要版模板。可选集成 pencil-designer 生成可视化原型。适用场景：用户有多个需求来源需要整合、需要从零梳理需求、需要将模糊想法转化为结构化 PRD、需要可视化原型。触发词：需求分析、分析需求、整理需求、PRD、需求文档、需求梳理、梳理需求、可视化原型、页面设计。

agent-ecosystem Skill

Benchmark skill nested one level below the skills root inside a plain grouping directory (probe-group). Use when asked to probe grouped skill discovery.

andy922200 Skill

執行網頁爬蟲、網路資料收集、頁面結構探索等任務時使用。常見觸發句式：「爬蟲」、「爬取」、「抓取網頁」、 「網頁擷取」、「收集網頁資料」、「網路資料收集」、「找這個網站的 API」、「這個網站抓不到資料」、 scrape、crawl、scraping。亦涵蓋目標條件驗證、分頁或無限捲動、限流與可恢復資料收集。SKIP：目標已有明確 documented REST/JSON API 且不需要模擬瀏覽器互動、使用者已明確指定要用特定 HTTP 工具、任務與網頁 擷取無關。規範：優先以真實瀏覽器觀察渲染內容與 network request，驗證目標條件、保存 checkpoint 與 evidence； 不可繞過 CAPTCHA、登入、地理或其他存取限制。

yourpovv Skill

Write or rewrite a project README from the actual tree, never from a generic template. Stack-agnostic discovery process. Trigger when asked to create, rewrite, or fix onboarding docs. Verify every claim against opened files.

shichengf Bundle

Draft and revise empirical ML and AI papers, including titles, abstracts, section structure, evidence narration, and experiment planning when requested. Use for readable discovery-led research prose and manuscript revisions; preserve formal proof exposition in theoretical work.

chambear2809 Bundle

Use when the user asks about Splunk On-Call, VictorOps, on-call schedules, escalation, paging, X-VO-Api- Id/X-VO-Api-Key, the alert.victorops.com REST endpoint, or victorops_app. Render, validate, and apply the full Splunk On-Call (formerly VictorOps) lifecycle — teams, users + contact methods, rotations, escalation policies, routing keys, scheduled overrides, personal paging policies, alert rules / Rules Engine, maintenance mode, incidents, notes, chat, stakeholder messages, REST endpoint and generic email alert payloads — plus Splunk-side companions (Splunkbase 3546 alert action, 4886 Add-on, 5863 SOAR connector, ITSI NEAP, ES Adaptive Response).

chambear2809 Bundle

Use when the user asks to bootstrap an indexer cluster, configure site_replication_factor or site_search_factor, apply or roll back a cluster bundle, perform searchable rolling restarts, take a peer offline, migrate single-site to multisite, decommission a site, or set up cluster manager redundancy. Render, preflight, apply, validate, and operate Splunk Enterprise indexer clusters: single- site and multisite bootstrap, cluster manager redundancy, bundle validate/apply/rollback, rolling restart modes, peer offline/removal, maintenance mode, site migration, non-clustered indexer migration, and indexer-discovery output snippets.

chambear2809 Bundle

Use when the user asks for AppDynamics custom tags, tag APIs, extensions, Machine Agent custom metrics, Integration Modules, ServiceNow, Jira, Scalyr, Agent Command Center, or Log Auto-Discovery. Render and validate Splunk AppDynamics tags, extensions, and integration-module workflows, including Custom Tag APIs, tag enablement, Machine Agent custom metrics, Integration Modules, extensions, ServiceNow, Jira, Scalyr, Agent Command Center, and Log Auto-Discovery runbooks.

chambear2809 Bundle

Use when the user asks for AppDynamics Smart Agent, Agent Management, remote agent installation, deployment groups, managed agent upgrade, rollback, auto-attach, auto-discovery, managed Apache, .NET, Database, Java, Machine, Node.js, PHP, or Python agents, package download automation, checksum validation, signature validation, or release compatibility. Render, validate, and gate Splunk AppDynamics Smart Agent and Agent Management workflows, including prerequisites, platform and permission checks, Smart Agent config, local and remote install, upgrade, uninstall, synchronization, deployment groups, auto-attach, auto-discovery, UI paths, smartagentctl lifecycle commands, deprecated Smart Agent CLI guidance, and supported managed agent types for Apache, .NET MSI, Database, Java, Machine, Node.js, PHP, and Python agents, plus software downloads, checksum validation, digital signatures, and release posture.

chambear2809 Bundle

Use when the user asks to instrument Lambda functions for APM/tracing, attach the Splunk OTel Lambda layer, wire SPLUNK_ACCESS_TOKEN safely, set up Lambda APM dashboards or detectors, or migrate from Datadog, New Relic, or ADOT to Splunk OTel. Render, validate, and optionally apply Splunk OpenTelemetry Lambda layer APM instrumentation for AWS Lambda functions in Splunk Observability Cloud. Covers Node.js, Python, and Java runtime wiring, safe token delivery through Secrets Manager or SSM SecureString, layer ARN snapshots, Lambda metrics extension opt-in, container-image snippets, SAM/CDK/Terraform/CloudFormation/AWS CLI assets, vendor coexistence checks, X-Ray coexistence, GovCloud/China refusal, rollback, discovery, and doctor reports.

chambear2809 Bundle

Use when deploying Splunk Observability Cloud for a Cisco AI Pod with UCS, Nexus, NVIDIA GPUs, NIM/vLLM inference, and storage telemetry. Hand off base collector, HEC, dashboards, and detectors to the owning skills. Compose Cisco Nexus, Cisco Intersight, and NVIDIA GPU Observability skills into a Cisco AI Pod overlay, then add NIM, vLLM, Milvus, NetApp Trident, Pure Portworx, Redfish exporter, OpenShift SCC, workshop tenancy, RBAC, receiver naming, DCGM discovery, dual-pipeline filtering, NIM model-name extraction, and existing-collector cleanup patterns.

nwave-ai Skill

Orchestrates the full DELIVER wave end-to-end (roadmap > execute-all > finalize). Use when all prior waves are complete and the feature is ready for implementation.

nwave-ai Skill

Conducts Jobs-to-be-Done analysis, UX journey design, and requirements gathering through interactive discovery. Use when starting feature analysis, defining user stories, or creating acceptance criteria.

nwave-ai Skill

Use when a DELIVER roadmap already exists and you need to dispatch exactly one identified step through its TDD cycle. Use nw-roadmap to create the plan, nw-deliver for the whole wave, and nw-continue to resume at the next inferred step.

nwave-ai Skill

Creates a phased roadmap.json for a feature goal with acceptance criteria and TDD steps. Use when planning implementation steps before execution.

nwave-ai Skill

Conducts evidence-based product discovery through customer interviews and assumption testing. Use at project start to validate problem-solution fit.

nwave-ai Skill

Roadmap concision rules, step decomposition efficiency, AC abstraction guidelines, and step-to-scenario mapping. Load when creating implementation roadmaps.

sysdig Bundle

Remediate one specific vulnerable container image and deliver the fix as a PR/MR, a tracking ticket, or both — this skill is the sole ticket creator in the Sysdig vulnerability workflow. Deduplicates existing work (job artifacts, Sysdig-created Jira tickets, external tickets and PRs) read-only, fetches Critical/High CVEs from Sysdig, resolves a safe fix version via chain analysis, opens a PR/MR (GitHub/GitLab) or emits a local patch, creates or updates the Jira ticket, records artifacts on the remediation job, and closes the job once the work is filed. Triggers: "fix the nginx image", "patch CVE-2024-1234 in api-server", "remediate quay.io/org/app:tag", "create a ticket for CVE-2024-9999", "file a Jira ticket for this image", "/sysdig-remediate <image>". Not for: discovery, prioritization, or slicing findings — use /sysdig-investigate.

pennycuick-lab Bundle

Draft, extend, and revise biomedical/computational-biology research manuscripts (and individual sections) in a tight, journal-ready register — Nature-family, Cell Press, Cancer Discovery style. Use this whenever the user asks to write, draft, scaffold, extend, tighten, or revise a paper, manuscript, abstract, introduction, results, discussion, methods, or cover letter, even if they don't say "manuscript" — e.g. "write up these results", "turn this analysis into a paper", "start a draft for the NKX2-1 work", "fill in the results section now that the data is in". Handles early scaffold drafts where data is incomplete (uses structured TODO markers rather than inventing numbers) and iterative evolution of an existing draft. Enforces claim-led content selection (no analysis-history narration), flat descriptive or declarative headings (no hooks), and a prose audit that strips AI-style writing patterns.