Product & Planning

jorgemuza Skill

Manage Azure DevOps (VSTS) projects, work items, and saved queries using the orbit CLI. Use this skill whenever the user asks about Azure DevOps work items, boards, queries, WIQL, bugs, tasks, user stories, sprints, iterations, or project management on Azure DevOps / VSTS. Trigger on phrases like 'list work items', 'show bugs', 'run query', 'create a bug', 'update work item', 'ADO bugs', 'VSTS query', 'Azure DevOps tasks', 'what's assigned to me', 'list projects', 'saved queries', 'work item 12345', or any Azure DevOps-related task — even casual references like 'check the board', 'what bugs are open', 'show me the Fusion backlog', 'ADO status', 'query results', or mentions of WIQL. The orbit CLI alias is `ado`.

macmenes Bundle

TRIGGER when the user wants to PLAN their own content / content strategy — "content strategy", "content plan", "what should we write", "topic ideas", "content calendar", "pillar pages", "content briefs", "blog plan". Part of the `vantage` (Vantage.os) Content Engine pack. Builds a pillar/cluster plan, a prioritized topic backlog, full content briefs, and an editorial calendar. DO NOT trigger for ANALYZING a competitor's content (use vantage-content), live keyword DATA (use seo-dataforseo), or writing the final article (use copywriting / seo-content-writer).

microsoft Skill

How infrastructure-caused database failures are turned into messages users can act on, via ConnectionDiagnosticsService. Use when adding a discovery plugin, a connection source, a reachability provider, a new tree view or webview surface, when a user reports a confusing or raw driver error, or when asked to improve error messages for Docker, Kubernetes, Atlas, Azure or any other infrastructure-backed connection.

microsoft Skill

Patterns for cluster nodes and tree data providers in vscode-documentdb. Use when adding or changing a cluster tree item, discovery provider, Connections/Azure/Discovery tree hierarchy, tree/list mode, cluster identity, treeId/clusterId lookup, Collection View import/export resolution, reveal behavior, credentials, shell actions, or copy connection string support.

modelslab Skill

Search and discover 50,000+ AI models on ModelsLab, check usage analytics, and monitor generation history via the Agent Control Plane API.

hao-ai-lab Skill

Single source of truth protocol for Wild V2 preflight, sweep/run auditability, GPU discovery, and parallel scheduling

hao-ai-lab Skill

Protocol for GPU discovery and parallel run scheduling across local GPU and Slurm clusters

hoangsonww Bundle

Extend or audit Codex support in the EstateWise repository. Use when changing .codex config, .codex/rules, .agents/skills, AGENTS.md layering, multi-agent roles, project guidance discovery, or Codex-specific documentation and workflows.

mshadmanrahman Bundle

Product management advisor drawing from 269+ Lenny's Podcast episodes, established PM frameworks (JTBD, RICE, Opportunity Solution Trees), and practitioner wisdom. Use when asking for PM advice, product strategy, prioritization, user research, growth, roadmapping, metrics, or product decisions. Triggers on: product strategy, PM advice, prioritization, roadmap, user research, product-market fit, OKRs, metrics, growth strategy, JTBD, feature prioritization, product discovery, ask lenny, /ask-lenny.

qwedsazxc78 Bundle

Manages Helm chart version upgrades across Terraform+Helm platforms. Handles atomic 3-file updates with version discovery from ArtifactHub. Use when upgrading Helm charts, checking for outdated versions, or performing version consistency checks.

qwedsazxc78 Skill

Retire the nginx ingress controller and all nginx Ingress resources from a Kustomize + ArgoCD repo after Gateway API / Traefik migration is complete. Supports single-env (dev/stg/prd) or all-envs retirement in one command. Use this skill whenever: removing nginx after migration, cleaning up dead nginx Ingress resources from a kustomize base, decommissioning the ingress-nginx controller ArgoCD Application for an env, or retiring nginx from one environment without touching others. Safety-gated: aborts if no HTTPRoutes/Traefik Ingresses found (migration not done). Uses $patch: delete in the service overlay kustomization to exclude base nginx Ingress resources per-env — base files stay intact for other envs still using them.

qwedsazxc78 Bundle

Migrates Kustomize modules using NGINX Ingress to Gateway API resources. Dual-target: default Traefik (GatewayClass=traefik), opt-in GKE Gateway (--gateway-class gke-l7-global-external-managed). Handles master/minion topology (common.ingress/ + common.service/) as the primary case, with standalone Ingress as a fallback. Performs cluster-side preflight (CRDs, GatewayClass, policy CRDs, Traefik version probe on Traefik targets), deterministic discovery/analysis via bundled scripts, two-phase conversion with atomic rollback from full file backups, semantic diff of path and listener coverage, plus an ingress2gateway second-opinion cross-check. Renders a comprehensive report covering per-hostname mapping, TLS map, annotation inventory (translated/stubbed/unknown), risk register, cutover checklist, verification commands, and rollback procedures. Never modifies the master source; performs idempotent in-place edits only to common.service/overlays/<env>/kustomization.yaml.

fancyboi999 Bundle

在明确的发现 scope 中构建受限的 Agent Skill 目录，并在加载指令正文前报告冲突。

qualcomm Skill

Canonical PowerShell block that detects the Windows ARM64 build toolchain (host arch, Visual Studio path, ARM64-target cl.exe, MSBuild, dumpbin, vcvars script) and caches the result to .copilot/state/wos-toolchain.json for reuse across agents/phases. Load when any wos-* agent needs to build/validate ARM64 artifacts. Cached results survive across tool calls within a session; re-run only if the cache is missing or stale.

alexpialetski Skill

Close a story end-to-end — flip its status to a terminal value and reconcile every downstream artifact in one pass: the backlog Status cell, the docs/queue.md row, the parent epic table (when the project uses epics), then a queue-audit reconcile. Use whenever the user says "close", "mark done", "ship", "finish", "complete", or "resolve" a story / ticket / backlog item, or moves work to a terminal state (done, done-no-promote, abandoned, absorbed). Reach for this instead of hand-editing the story file alone — a half-applied close (status flipped but queue/backlog/epic left stale) is exactly the drift this skill exists to prevent. Works for single-root and monorepo projects.

alexpialetski Skill

Author or update product stories (a.k.a. planning docs, backlog items, tickets, specs) as Markdown under docs/stories/ with a YAML frontmatter contract (id, status, impact, urgency, depends_on, tags, openspec). Use this whenever the user is creating a story, reprioritising work, writing acceptance criteria, linking a story to OpenSpec or an ADR, or editing anything under docs/stories/ — even if they call it a spec, ticket, backlog row, or planning doc.

alexpialetski Skill

Reconcile the dependency graph, pick-next queue, and backlog status across docs/stories/, docs/queue.md, and docs/backlog.md. Use after adding or editing a story (especially one with depends_on), after reshuffling priorities, or when the user asks "what can I work on next", "what's unblocked", "sanity-check the queue", "check my story dependencies", "fix the queue order", or "what parallel work is ready". In Agent mode (the tool can write files), apply objective mechanical fixes in the same turn and report what changed; in Ask / read-only mode, emit a proposal instead. Stop and report — never guess — on directed cycles, unknown depends_on ids, duplicate ids, or ambiguous editorial reorders.

alexpialetski Skill

After a design, research, business, or prioritisation thread, evaluate whether the conversation produced durable insight worth capturing in docs/, then propose only the artifacts that are clearly justified (ADR, research note, reference doc, business update, story, backlog/queue edit). Use when the user says "wrap this session", "propose docs artifacts", "what should we capture", "summarize this into docs", "end-of-session", or similar close-out phrasing. If nothing warrants capture, say so in one sentence and stop. Never write files unless the user explicitly asks to create or update them in the same turn — propose drafts only.

morzecrew Bundle

Use when an experiment, candidate, prototype, spike, or benchmark fails and the next move is to start something else; when writing up a negative result; when triaging a backlog of dead attempts; or when a whole approach is about to be abandoned. Not when nothing was measured.

wide-moat Bundle

COSTLY: Spawns a separate sub-agent CLI session. Use ONLY for complex CODE tasks requiring 10+ iterative tool calls (multi-file refactoring with tests, code review with fixes, test-fix cycles). IMPORTANT: Always run the model discovery script first before any sub_agent call. Do NOT use for presentations, research, documentation, or any task completable in fewer than 10 tool calls.

crag666 Bundle

Citation-network literature discovery via Inciteful (incitefulmed.com/academic). Find similar papers, key papers by PageRank, reviews, top authors/institutions/journals around seed papers, and shortest citation paths between two papers. Free, no API key.

buildinternet Bundle

Create or update a releases.json manifest so registries and agents can find where a company or project publishes its release notes. Use this whenever someone wants to "list our product on Releases", "add a releases.json", "get indexed on releases.sh", "here's our website, make us a manifest", declare a changelog / updates page / RSS feed / GitHub releases / App Store listing / CHANGELOG for discovery, publish a /.well-known/releases.json, or edit an existing one — even if they don't say "releases.json" by name. The usual input is just a company website or domain (no codebase required); the manifest is a small, schema-validated file the owner hosts on their domain or repo. This skill discovers the real publish locations, models products without over-fragmenting, writes the correctly-scoped file, validates it locally, and guides publishing it.

buildinternet Skill

Coordinate bulk playbook writing using parallel sub-agents — covers org discovery, prompt templates, model selection, batch dispatch, verification, and the parent-saves pattern for working around subagent permission limits. Currently wired up for Claude Code's Agent tool; the managed-agent fleet supports sub-agents too and the pattern can be adapted, but isn't wired up there yet.

buildinternet Skill

How to find, evaluate, and recommend the best ingestion method for changelog URLs — covers feed discovery, provider detection, GitHub API, markdown sources, and scraping fallback

chenshuo2004 Bundle

Use when the user wants Codex to turn a Markdown requirements document into a Ralph PRD and run a safe Ralph/Codex build workflow against a local Git repository. Triggers include "cs-ralph-runner", "run Ralph", "generate Ralph PRD", or requests to run a Markdown PRD against a repo.

kambleakash0 Skill

Create a comprehensive Product Requirements Document from conversation and repo context. Use when the user wants a PRD, product spec, feature requirements, or similar documentation.

kambleakash0 Skill

Turn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices.

kambleakash0 Skill

Turn a PRD into a Kanban-ready backlog of vertically sliced issues, with clear dependencies and HITL/AFK flags.

kienhaminh Bundle

Use when defining product vision, agile roadmapping, prioritization (RICE/Kano), or user-centric discovery.

leongibhub Skill

Establish reliable project context from Git, repository documents, local knowledge, Redmine/RAGFlow/GitLab sources, and explicit user instructions before substantial work.

lucavb Bundle

Do discovery during planning — explore the codebase and close open questions before presenting a plan. Use when drafting implementation plans, or when a plan would defer verification or "pre-flight" checks to execution.

m0m0i Skill

Write the product requirements — who it is for, what capabilities it must have, what it deliberately is not — with stable capability ids that specs cite. Use at project inception, after northstar and before any technical design.

m0m0i Skill

Decompose capabilities into epics — chunks of work with a demonstrable outcome — each grouping the issues that specs will be written from. Use between the PRD and the backlog.

m0m0i Skill

Decompose the top of the product backlog into typed tracker issues for this iteration — each sized as one issue, one branch, one spec, one PR. Use at the start of an iteration. This is where a plan becomes committed work.

m0m0i Skill

Order the whole of the known work into a product backlog, with an explicit critical path and reasons for the order. Use after epics, and to re-groom when reality diverges. Creates no issues — sprint does that.

m0m0i Skill

Name the one metric this product moves, the levers that move it, and the quality property a defect would most damage. Use at project inception, before the PRD. Produces the anchor that every reviewer severity is judged against.