Product & Planning

vinceservidad Bundle

Plans and manages Shopify assortment, collections, sorting, product cards, bundles, cross-sells, upsells, and inventory-aware merchandising. Use for discovery and offer presentation.

yacb2 Bundle

Use when the user wants to audit, organize, clean up, or health-check their Claude Code setup — a messy or inconsistent .context/, a bloated or stale MEMORY.md, broken symlinks in .claude/skills, unused or misplaced skills, dead CLAUDE.md links, plugins inflating idle context, or "my project opens heavy / wastes context". Also fires on "audit my project", "organize my ecosystem", "what skills do I have", "check my project's health", "I think I have broken symlinks", "my .context/ is a mess", "my new project has no .context / help me start with aidex", and the /aidex command. Not for: creating .context/ docs (aidex-plan, aidex-decision, aidex-reference, aidex-research, aidex-request); project-state audits like UX or security (aidex-audit); backlog items (aidex-backlog).

yacb2 Bundle

Use when the user wants to log or draft a real communication with a person — capture an email/WhatsApp that was received, log a meeting or call that happened, or draft a message/email to send — as a written `.context/communications/` entry, kept in the communication's native language. Fires on "log this email", "save the email the client sent", "capture this WhatsApp from X", "record the call with X", "log the meeting with X", "draft an email to X", "write a reply to the client", "save this thread", and /aidex-comm commands. Not for: capturing a stakeholder/product requirement to act on (aidex-request); recording a decision/ADR (aidex-decision); planning multi-step work (aidex-plan); deferring an idea (aidex-backlog); research notes (aidex-research); references (aidex-reference); ecosystem audits (aidex); project-state audits (aidex-audit).

yacb2 Bundle

Use when the user wants an interactive HTML dashboard/render/board of `.context/` data — the backlog board, a plan's progress, an audit inventory, the coverage matrix — or says "render X as HTML", "generate the dashboard", "show this as a page". Not for: authoring content (the markdown stays canon); publishing without being asked.

yacb2 Bundle

Use when implementation work should become a written `.context/` plan before coding starts — either multi-phase work (a feature build, a migration, a refactor spanning backend/frontend/infra) or a single scoped change where only the file list and acceptance criteria need pinning down; a triage step picks which. Fires on "create a plan for X", "let's plan X", "I want to plan X", "we need to plan X", "plan the migration of X", "let's build a multi-phase plan", "implement X minimally", "a small scoped change to X", "just the minimum to ship X". Not for: fixing a bug or regression, which needs a failing test (aidex-bugfix); deferring or parking an idea for later (aidex-backlog); ADRs (aidex-decision), requests (aidex-request), research (aidex-research), or references (aidex-reference); ecosystem audits (aidex); project-state audits (aidex-audit); direct implementation with no plan doc.

yacb2 Bundle

Use when the user wants to assess the state of a feature, flow, or module — a UX, security, performance, or accessibility audit; cataloging bugs, gaps, and opportunities; retesting open findings; escalating a finding to the backlog; or updating audit methodology. Fires on "I want to do a UX / security / performance / accessibility audit", "before we ship I want to audit X", "audit the X flow or module", "catalog the state of X", "list bugs and gaps in X", "retest open findings", "register a finding under audit X", "escalate finding <id> to backlog", and /aidex-audit commands. Not for: auditing the Claude Code setup itself like skills or MEMORY.md (aidex); creating plans (aidex-plan) or decisions (aidex-decision); generic backlog items not from a finding (aidex-backlog).

yacb2 Bundle

Use when the user wants to capture or defer something for later without acting on it now, or to work the existing backlog as a board. Fires on "add to the backlog", "add to the backlog the idea of X", "park this for later", "defer this one", "shelve the X idea", "queue this for later", "track this for later", "we'll do this later", "move finding <id> to the backlog", "show me the backlog", "list open backlog items". Also owns the board itself, not just intake: "triage the backlog", "sweep the open items", "do a backlog sweep", "define these items", "which of these are already done", "what can we close quickly", "run these as a work-list", and /aidex-backlog commands. Not for: plans (aidex-plan), decisions (aidex-decision), references (aidex-reference); auditing project state (aidex-audit); ecosystem audits (aidex).

yacb2 Bundle

Use when the user relays an incoming stakeholder, client, or product request that should be captured as a written `.context/requests/` item before anyone acts on it — a feature ask, a requirement from a meeting, user feedback to formalize. Fires on "the client asked for X", "the stakeholder wants X", "capture this as a request", "log this requirement", "we got a request to add X". Not for: planning multi-step work (aidex-plan); recording a decision/ADR (aidex-decision); investigating how something works (aidex-research); documenting a settled reference (aidex-reference); deferring/parking an idea (aidex-backlog); ecosystem audits (aidex); project-state audits (aidex-audit).

yacb2 Bundle

Use when the user has made an architectural, technical, or product decision and wants it recorded as a written `.context/decisions/` ADR — what was chosen, why, the alternatives, and the consequences — so the team does not re-litigate it later. Fires on "we decided X", "document this decision", "write an ADR", "record the decision to X", "log why we chose X", "we settled on X, write it up". Not for: planning multi-step work (aidex-plan); deferring or parking an idea for later (aidex-backlog); capturing a stakeholder/client request (aidex-request), research notes (aidex-research), or a settled reference (aidex-reference); ecosystem audits (aidex); project-state audits (aidex-audit).

yacb2 Bundle

Use when the user needs to investigate, explore, or spike on how something works and the findings should land as written `.context/research/` notes before any plan or implementation. Fires on "research how X works", "investigate X", "spike on X", "look into how X is done", "I need to understand X before planning". Not for: planning multi-step work once the approach is known (aidex-plan); recording a decision/ADR (aidex-decision); capturing a stakeholder request (aidex-request); documenting a settled, stable reference (aidex-reference); deferring/parking an idea (aidex-backlog); ecosystem audits (aidex); project-state audits (aidex-audit).

yacb2 Bundle

Use when the user wants to document how an existing, settled part of the system works as an evergreen `.context/references/` module — architecture, configuration, an operational runbook, a how-it-works guide. Fires on "create a reference for X", "document how X works", "write up the X architecture", "document the X configuration", "write a runbook for X", "what is documented and what is missing". Not for: planning multi-step work (aidex-plan); recording a decision/ADR (aidex-decision); capturing a stakeholder request (aidex-request); investigating something not yet settled (aidex-research); deferring/parking an idea (aidex-backlog); ecosystem audits (aidex); project-state audits (aidex-audit).

yacb2 Bundle

NOT auto-invoked. Shared documentation-canon hub for the aidex-* family — holds the .context/ convention references (references/*.md) that the single-purpose sibling skills delegate into. Routing — plan multi-step work → aidex-plan; record a decision/ADR → aidex-decision; capture a stakeholder/client request → aidex-request; investigate/research how something works → aidex-research; document a settled system reference → aidex-reference; defer/park an idea for later → aidex-backlog; capture/draft a communication received or to send → aidex-comm; check a skill against house conventions → aidex-skill. This skill is the canon home, not an entry point; the siblings are the entry points.

zszz3 Bundle

Use when a Lark/Feishu technical document needs an editable architecture diagram, flowchart, sequence diagram, state model, data relationship, Agent workflow, development process, reliability view, learning map, roadmap, or decision visualization.

aquarius-mu Skill

Break a plan, spec, or PRD into independently-committable issues using vertical slices. Use when converting a plan into trackable work items.

avinashp Skill

Initialize project with CLAUDE.md, STATE.md, and ROADMAP.md by following the canonical init command doc.

hashintel Skill

Create or update a strategic roadmap — the outer loop that sequences invariant thresholds across an initiative. Use when direction is not concrete enough for a capsule, multiple strategic bets compete, or you need to capture long-horizon intent, decisions, risks, and verification economics. Owns docs/roadmap.md.

hashintel Skill

Create an evidence-backed frame from messy transcripts and notes before capsule/card planning. Use when discovery inputs are conversation-heavy and the problem statement is still diffuse.

kangarooking Bundle

Route viral topic discovery across platform-specific account-growth skills. Use when the user asks for 起号选题, low-follower viral references, recent viral content, cross-platform topic mining, or does not specify whether to search WeChat, X, Bilibili, or YouTube.

marian2js Bundle

Build a ranked map of the catalysts that could move a watchlist, theme, or portfolio by showing what matters, when it matters, and how those events could transmit across related names or exposures.

marian2js Bundle

Review a watchlist and rank which names deserve active attention, background monitoring, or removal based on catalysts, tradability, redundancy, and evidence quality for the user's style and timeframe.

okayus Bundle

Keep an AI coding agent oriented across sessions WITHOUT a bloated status.md. Split repository context by lifetime — a hard-capped "now" hub (docs/status.md, 40 lines / 3 KB, four fixed headings), an append-only milestone log (docs/log.md, never auto-loaded), per-topic plans deleted when done, and ADRs — then inject the hub deterministically with a Claude Code SessionStart hook, write it back with a manual /handoff skill, and gate the cap in CI. Use when status.md / PROGRESS.md / project-status.md keeps growing, when CLAUDE.md has filled up with "next actions" and strikethrough history, when a new session (or a sandboxed container session) has to rediscover where the project stands, or when asked how to carry progress, roadmap or handoff notes between Claude Code sessions. Covers why CLAUDE.md @imports and auto memory don't solve it (imports load at launch anyway; auto memory is machine-local, so host and container keep separate memories), which hook events can inject context (SessionStart stdout does, PreCom

rimagination Skill

Structured academic literature discovery and citation verification across Crossref, OpenAlex, PubMed, Europe PMC, arXiv, Semantic Scholar, and configured providers. Use for finding papers, checking DOI metadata, tracing citations, or building a source-backed search set.

janellecipriano Skill

Review a product requirements document (PRD) or spec against a quality checklist and surface gaps, ambiguities, and risks before engineering starts. Use when the user says "review this PRD", "is this spec ready", "critique my requirements", "PRD checklist", or shares a doc and wants it pressure-tested before build.

janellecipriano Skill

Draft and track OKRs — objectives with measurable key results, current values, and confidence/health. Use when the user says "write OKRs", "set objectives and key results", "track our OKRs", "quarterly goals", "are we on track for our KRs", or needs to define or check progress on measurable goals.

janellecipriano Bundle

Write a concise project or program status report with an overall RAG (red/amber/green) health rating, progress since last update, what's next, risks/blockers, and explicit asks. Use when the user says "write a status report", "weekly update", "status update", "where are we on X", or needs a stakeholder-ready progress summary.

janellecipriano Skill

Plan a sprint or iteration — sprint goal, available capacity, committed scope, and risks — from a backlog. Use when the user says "plan the sprint", "sprint planning", "what should we commit to this iteration", "groom the backlog into a sprint", or needs to turn priorities + capacity into a realistic commitment.

janellecipriano Skill

Turn goals, themes, and initiatives into a structured product roadmap — now/next/later or quarterly — with outcomes, rough sizing, dependencies, and confidence. Use when the user says "build a roadmap", "plan the quarter/half/year", "prioritize our initiatives", "what should we work on next", or needs to sequence work against objectives.

janellecipriano Skill

Build a stakeholder map and a communication plan — who needs what information, at what cadence, through which channel. Use when the user says "stakeholder map", "communication plan", "comms plan", "who do we need to keep informed", "RACI for comms", or needs to plan how to keep stakeholders aligned across a program.

jiahao-shao1 Bundle

Academic paper discovery / filtering / reading via Scholar Inbox API + notebooklm-py CLI. Use for browsing today's papers, recommendations, rate/collect, deep-read via NotebookLM, ask questions about papers, trending. Triggers: 'scholar inbox', 'paper digest', '看论文', '读论文', '论文推荐', 'rate papers', '今天有什么论文', 'deep read paper', '帮我筛选论文'. Not for PDF reading, lit reviews, or general notes.

jiahao-shao1 Bundle

Deep critical analysis of one specific paper — dissect experimental setup, extract numbers, evaluate claims against a hypothesis. Triggers: 'analyze this paper', 'deep dive into', '分析这篇论文', '论文深度分析', 'what does this paper really show', '这篇论文说明了什么', arXiv ID with analysis intent. Not for paper discovery (use scholar-agent), quick summaries, or literature surveys.

jiahao-shao1 Bundle

Strategic project review — auto-discovers strategy docs (vision, roadmap, decisions, notes), produces five-dimension snapshot. Use for direction review, alignment check, milestone status, pre-meeting overview. Triggers: 'project review', 'strategic review', 'where is the project at', '项目全景', '审视战略', '项目现在什么状态'. Not for code/PR review.

jmagly Bundle

AUTO-INVOKE when user mentions ops, runbook, inventory, audit trail, ops repo, sysops, devops, itops, infrastructure operations, fleet management. Ops framework quick reference — capability domains, extension model, and discovery phrases for runbooks, inventory, audit trail, verification.

jmagly Bundle

AUTO-INVOKE when user mentions SDLC, requirements, architecture, ADR, use case, user story, test plan, phase gate, inception, elaboration, construction, transition, intake, deploy. SDLC framework quick reference — phase model, capability domains, and curated discovery phrases for aiwg discover.

jmagly Bundle

AUTO-INVOKE when user mentions research, paper, citation, GRADE, corpus, provenance, literature review, induct paper, evidence, bibliography. Research framework quick reference — discovery phrases for corpus inception, paper acquisition, GRADE quality, citation graphs, provenance-tracked synthesis.

jmagly Bundle

AUTO-INVOKE when user mentions forensics, incident response, IOC, log analysis, evidence preservation, breach investigation, threat hunting, attack timeline. Forensics framework quick reference — discovery phrases for incident response, log analysis, evidence preservation, IOC extraction.

jmagly Bundle

AUTO-INVOKE when user mentions marketing, campaign, brand, content production, audience persona, copy, social media, marketing intake, approval workflow. Marketing framework quick reference — discovery phrases for campaign intake, brand compliance, content production, audience synthesis, approval workflows.