Product & Planning

silviobeer Bundle

Run a human checkpoint as a structured reconcile loop: present a compact review package, collect feedback point by point (adopt/change/reject/defer), write the decision log, cascade every change through all affected planning artifacts, and seal the result in state.json. Use when: (1) architecture + wave plans are ready for Checkpoint 1 approval before any execution, (2) PR review comments need reconciling at Checkpoint 2 (invoked via delivery), (3) intake bootstrap drafts need validation (via the intake skill, 0b). Not for: producing the plans themselves (use writing-plans), resolving PRD reviews on the discovery track (use review-reconcile), P0 setup (use setup).

silviobeer Skill

Design PM-friendly technical architecture for a PROJ (covers all its PRDs). No code, only high-level design decisions. Use when: (1) all PRDs for a PROJ exist and need a unified tech design, (2) cross-cutting tech decisions need PM-friendly justification, (3) before creating implementation plans. Not for: writing code, per-PRD micro-decisions, or requirements gathering.

silviobeer Skill

Design PM-friendly technical architecture for a PROJ (covers all its PRDs). No code, only high-level design decisions. Use when: (1) all PRDs for a PROJ exist and need a unified tech design, (2) cross-cutting tech decisions need PM-friendly justification, (3) before creating implementation plans. Not for: writing code, per-PRD micro-decisions, or requirements gathering.

silviobeer Skill

Use as Step 1 of the PROJ workflow before creating or changing any feature, component, workflow, or behavior. Turns a feature idea into one or more approved buildable concepts through project discovery, scope decomposition, structured intake, bounded exploration, assumption playback, and risk review. Produces specs/PROJ-<X>-<theme>/1_brainstorm/PROJ-<X>-concept.md, then hands off to visual-companion for UI features or requirements-engineer for backend/API features.

silviobeer Skill

Reconcile mockup iteration changes back into the concept before requirements. Use after ui-mockup when stakeholders have iterated on the mockups (changes prompted directly into the HTML) and the agreed result must flow back into the concept. Reads the mockup iteration log, updates the concept doc, marks abandoned decisions, and signals handoff-ready for requirements-engineer. Primary step of the Product Discovery track, but also usable in the full 0-to-8 chain.

silviobeer Skill

Use as Step 1 of the PROJ workflow before creating or changing any feature, component, workflow, or behavior. Turns a feature idea into one or more approved buildable concepts through project discovery, scope decomposition, structured intake, bounded exploration, assumption playback, and risk review. Produces specs/PROJ-<X>-<theme>/1_brainstorm/PROJ-<X>-concept.md, then hands off to visual-companion for UI features or requirements-engineer for backend/API features.

silviobeer Skill

Run a long-form, parallel architecture drift and refactor discovery pass over the current codebase. Use when the user wants an overnight/deep exploration that sends subagents through the repo to identify larger refactor opportunities, architecture mismatches caused by feature growth, simplification targets, technical debt themes, and chain-ready inputs for later brainstorming, architecture, or implementation planning. Produces evidence-backed reports and handoff artifacts only; it does not change code and is not part of the 0-7 feature chain.

silviobeer Skill

Run a long-form, parallel architecture drift and refactor discovery pass over the current codebase. Use when the user wants an overnight/deep exploration that sends subagents through the repo to identify larger refactor opportunities, architecture mismatches caused by feature growth, simplification targets, technical debt themes, and chain-ready inputs for later brainstorming, architecture, or implementation planning. Produces evidence-backed reports and handoff artifacts only; it does not change code and is not part of the 0-7 feature chain.

silviobeer Skill

Establish what a product IS before any feature is designed: interview the product owner into docs/PRODUCT.md (purpose, audience, non-goals, success) and cut the product into a numbered PROJ map in specs/product-roadmap.md. Use when: (1) a new product/project starts and no docs/PRODUCT.md exists, (2) the product direction changed and the map needs a revision round. Not for: a single feature in an existing product (use brainstorming), extracting the baseline from an existing codebase (use intake), stack or scaffold decisions, feature detail.

silviobeer Skill

Establish what a product IS before any feature is designed: interview the product owner into docs/PRODUCT.md (purpose, audience, non-goals, success) and cut the product into a numbered PROJ map in specs/product-roadmap.md. Use when: (1) a new product/project starts and no docs/PRODUCT.md exists, (2) the product direction changed and the map needs a revision round. Not for: a single feature in an existing product (use brainstorming), extracting the baseline from an existing codebase (use intake), stack or scaffold decisions, feature detail.

silviobeer Skill

Assemble a standalone, distributable handoff package from discovery artifacts for downstream UI/UX experts and developers. Use after requirements-engineer on the product discovery track when the concept, mockups, and PRDs must be packaged into one self-contained dated run folder (and ZIP) that external readers can consume without access to the rest of the repo. Produces a delta since the previous handoff, README index, manifest, single-source-of-truth scope/decisions doc, role-split UI and developer handoffs, copied mockups, and a paste-ready Linear import.

silviobeer Skill

Explore interactive UI structure before requirements. Use when a concept exists and the team needs to discuss and decide the rough shape of the interface: sidepanel vs modal vs drawer vs split view vs wizard vs dedicated page, navigation model, screen flow, and interaction container. Starts with conversational discovery questions, then produces multiple clickable low-fidelity HTML approaches grounded in the existing app, then returns to conversation for selection and iteration. Not for polished visual design, final mockups, colors/typography, or detailed acceptance criteria.

silviobeer Skill

Resolve a developer or stakeholder review of finished PRDs by going through the raised gaps point by point, deciding each with the product owner or deferring it to a developer meeting, then reconciling the agreed outcomes back into the PRDs, concept, and mockups. Use after requirements-engineer (and any handoff) when a review comes back with gaps, ambiguities, or open questions on the PRDs. Records a decision log, keeps unresolved items as an explicit developer-meeting agenda, and maintains a handoff-facing changelog so external teams (UI/UX, devs) can follow what changed since the version they reviewed. Sibling of concept-sync on the Product Discovery track.

dangtran1003 Bundle

Tạo tài liệu Issue Discovery Report (.docx) khi phát hiện bug, missing case, hoặc vấn đề nằm ngoài scope trong quá trình phát triển phần mềm. Sử dụng skill này khi user muốn tạo report cho bug/issue/lỗi mới phát hiện, viết báo cáo phát hiện lỗi, tạo BDR (Bug Discovery Report), document missing case hoặc edge case, tạo report để BA/Dev review, hoặc bất kỳ khi nào user đề cập "tạo report lỗi", "phát hiện bug", "missing case", "issue report", "BDR", "discovery report". Cũng trigger khi user nói "tạo report như template", "report theo format cũ", hoặc muốn document vấn đề kỹ thuật để team review.

franky47 Skill

Create a PRD through user interview, codebase exploration, and module design. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.

franky47 Skill

Break a PRD into independently-grabbable beans issues using tracer-bullet vertical slices. Use when user wants to convert a PRD to issues, create implementation tickets, or break down a PRD into work items.

shwsgithub Skill

PRD(제품 요구사항 문서) 작성 스킬. JTBD·유저스토리 기반 15섹션 구조로 사람 팀과 AI 프로토타이핑 툴(Cursor/v0/Lovable/bolt.new) 양쪽이 바로 쓸 수 있는 PRD를 만들고, 산문 섹션은 번역투·AI 관용구를 걷어낸 자연스러운 한글로 자체 윤문한다. "PRD 작성해줘", "요구사항 문서 만들어줘", "기획서 써줘", "/prd" 같은 요청에 사용.

specsnl Skill

Use this skill to prepare the environment and run the PHP/Laravel quality tools of a Specs project locally — PHP_CodeSniffer, PHPStan/Larastan, PHPUnit, Rector and the markdown linter — all through the Taskfile. It is the PHP/Laravel layer of the `ci-green-check` skill, which invokes it whenever a repository has a `composer.json`; that skill owns check discovery, the fix loop, and the final report. Also triggers directly when the user says "run checkall", "run phpstan", "run phpcs" or "run the tests" in a Laravel/PHP repository.

mister2d Bundle

Comprehensive Nomad cluster operations and administration via the HTTP API. Use when asked to: deploy/run/submit/update/stop/restart/scale Nomad jobs; manage CSI volumes, dynamic host volumes, or storage; inspect allocations, evaluations, deployments, or nodes; configure ACLs, namespaces, quotas, node pools, or sentinel policies; stream logs or exec into tasks; manage variables/secrets, scaling policies, service discovery, or operator tasks (raft, autopilot, snapshots, keyring). Works against any Nomad cluster without hardcoded addresses. First-class support for full job spec (HCL/JSON), CSI volumes, templates, artifacts, and Consul service discovery.

erzatiam Skill

Initialize a root CLAUDE.md plus a structured .claude/ directory for any new project. Use this skill whenever the user says 'init project', '初始化项目', 'setup .claude', 'create project config', 'help me set up Claude for this project', or similar. Also triggers when the user asks to generate CLAUDE.md, rules.md, faults.md, project-statements.md, environment.md, or an adaptive research roadmap. Works for any project type: research, software engineering, data science, web dev, systems, etc.

erzatiam Skill

Initialize durable project context for a new repository. Use when the user says 'init project', '初始化项目', 'setup AGENTS.md', 'create project context', or asks to generate project statements, environment, rules, faults, references, or an adaptive research roadmap. Works for research, software engineering, data science, web, systems, and mobile projects.

aswinr3 Bundle

Document-driven QA for a web platform — read the PRD, slice specs, permissions matrix, workflows, user flows and design system in full, derive precise traceable test cases from them, and verify the running platform with Playwright plus Jest/Vitest. Covers unit, integration, mock, smoke, sanity, functional, regression, exploratory and non-functional testing; compares the built UI against the design file and design system; runs a deterministic UI defect sweep; emits test cases as TSV for Google Sheets; and writes per-module and per-type result files after every run. Gathers every testing dependency up front (per-role credentials, disposable-data status, spec location) and waits for them — a missing critical dependency gates the run unless the user says to proceed without it — then runs the agreed scope end to end and reports a single verdict. Use when asked to test a platform against a PRD/spec/requirements doc, write or review tests, plan QA, build Playwright e2e coverage, check design conformance, hunt UI iss

bosmark Bundle

Operate your BoS OS day to day. The coordination layer that runs after Bootstrap and Workshop: it shapes a rough idea into a measurable Mission Brief, staffs the mission by casting and speccing the agent team, then drives delivery from goal to running system. Three bounded agents — Mission Shaper, Agent Planner, Delivery Manager — plus mission state templates. Use when someone wants to run a mission, shape a goal into a brief, staff or plan a mission, manage delivery, run the backlog, or operate their agent team. Triggers: "run a mission", "run the BoS OS", "run agent run skill", "shape a mission", "mission brief", "staff this mission", "plan the mission", "delivery manager", "run my backlog", "operate my agents", "stand-up", "what's next on the mission". MANDATORY TRIGGERS: BoS OS, agent OS run, run a mission, run agent run skill, mission shaper, agent planner, delivery manager, mission brief, backlog, stand-up.

clickzetta Bundle

End-to-end data science workflow guide for ClickZetta Lakehouse, covering environment setup, data discovery, feature engineering (SQL + ZettaPark), and model inference deployment. Details: Python 3.10+/Jupyter/ZettaPark setup, project structure, data quality assessment, and inference (BITMAP profiling, UDF batch inference, vector search). Trigger when the user wants to do data science, ML, or analytical work using ClickZetta Lakehouse — connecting Jupyter to Lakehouse, doing EDA, building features, running ML inference, user profiling, audience segmentation, or batch scoring. Keywords: data science, ML, ZettaPark, Jupyter, feature engineering, EDA, profiling, inference

clickzetta Bundle

Comprehensive review and diagnosis of ClickZetta Lakehouse data pipelines. Starting from any entry point (task name / schema / table name / business domain keyword), autonomously discovers all pipeline objects (Studio tasks, Lakehouse tables, pipeline objects, run records), identifies missing scheduling dependencies, DDL idempotency issues, layer skipping, Dynamic Table anti-patterns, and other common problems. Delivers prioritized fix recommendations and executes them. Trigger when the user says: "review pipeline", "check data pipeline", "pipeline diagnosis", "pipeline has issues", "task failed", "data is wrong", "pipeline review", "check ETL", "pipeline health check", "data lineage check", "pipeline overview", "pipeline audit", "task dependency check", "DT refresh failing", "data inconsistency", "pipeline not working". Keywords: pipeline review, diagnosis, task dependency, data lineage, DT health, pipeline discovery

clickzetta Bundle

Build Kafka-to-Lakehouse ingestion pipelines using READ_KAFKA Pipe or Kafka External Table + Table Stream. Covers: connection validation, JSON/CSV parsing, Pipe DDL, SASL auth, VCluster sizing, latency monitoring, tuning. Trigger when the user says: "Kafka ingestion", "Kafka Pipe", "read_kafka", "Kafka external table", "Kafka consumer", "message queue import", "Kafka backlog", "ingest from Kafka", "stream data to Lakehouse", "real-time Kafka pipeline", "Kafka to ODS". Keywords: Kafka, Pipe, read_kafka, message queue, streaming ingestion, real-time ETL

rocketwill Bundle

Explicitly invoked human-led software development: orchestrate discovery, decisions, specs, tickets, read-only review, and verification while the human owns implementation and commits.

nana7536 Bundle

RITFIT品牌知识库检索技能。当用户进行以下操作时必须触发本技能： (1) 策划RITFIT任何campaign活动方案时（包括但不限于节日营销、新品推广、季节性活动等），先读取知识库中相关的历史方案和复盘作为参考； (2) 复盘或总结已有活动时，读取知识库中的历史数据和复盘记录； (3) 查询RITFIT品牌运营知识（TikTok、红人营销、品牌PR、社媒运营等岗位知识）时； (4) 询问RITFIT品牌部OKR、年度硬仗、部门架构、行业资料等内容时。 用户通常会用中文提出需求，但知识库中包含中英文内容。 只要用户的请求与RITFIT品牌活动策划、运营知识、部门信息相关，就应触发此技能读取知识库。

serialexperimentslainnnn Skill

Running the security operations function as an operation, not a product. Use when choosing between an in-house SOC, an MSSP or MDR provider and a hybrid model, sizing 24x7 shift coverage and follow-the-sun rotations, writing shift handover notes, managing the alert queue and its backlog, automated enrichment before triage, triage and escalation criteria, structured close codes and case management (TheHive, Cortex, IRIS, Shuffle, Tines, n8n, SOAR playbooks and what must never be automated), analyst tiering and why the tier model ages badly, alert fatigue and analyst burnout, actionable-alert ratio as a service-level indicator, the rule-retirement process, SOC metrics that survive scrutiny (time to detect, time to contain, telemetry coverage) versus vanity counts of closed alerts, SIEM ingest volume as the dominant cost driver and what to keep hot, warm or cold, scheduled threat hunting with a written hypothesis and a hunt report (PEAK, hunting maturity model), purple-team scheduling and deconfliction, SOC-CMM

serialexperimentslainnnn Skill

Use when IT runs as a service with a customer on the other side — writing or reviewing a service catalogue entry with a named service owner, separating request fulfilment from incident from problem records in a ticket tool, defining request categories and a request catalogue, standard pre-approved changes versus a CAB and the change record that satisfies an auditor, change freeze and blackout windows, writing an SLA, OLA or underpinning contract with service hours, response and resolution targets, credits and exclusions, distinguishing a contractual SLA from an engineering SLO, service desk tiering, escalation matrices and follow-the-sun coverage, CMDB and CI relationships, discovery versus manual maintenance, configuration item ownership and drift, known error database and workarounds, ITIL 4 practices and ITIL Version 5, PeopleCert and AXELOS licensing of ITIL material, ISO/IEC 20000-1 certification scope, FitSM, YaSM or VeriSM as license-free alternatives, service reporting and first-contact resolution, or

serialexperimentslainnnn Skill

Reducing the risk of building something nobody needs, before it is built. Use when deciding how much discovery a decision deserves and whether it is reversible, addressing the four product risks (value, usability, feasibility, business viability) from Marty Cagan and SVPG, running customer interviews about past behaviour instead of future intent, building an opportunity solution tree (Teresa Torres, Continuous Discovery Habits) to trace a solution back to an outcome, writing a problem statement behind a requested feature, choosing an experiment (paper or clickable prototype, smoke test, fake door, concierge, Wizard of Oz) and its ethical and privacy limits, designing an A/B or online controlled experiment with a minimum detectable effect, power and sample-size calculation and duration fixed in advance, one primary metric plus guardrails, sample ratio mismatch checks, the peeking problem and always-valid or sequential inference, multiple-comparison correction, deciding when an A/B test is impossible (low traff

serialexperimentslainnnn Skill

Use when work is organized as a project or delivery programme — choosing predictive, agile or hybrid delivery for a given piece of work, writing a project charter, statement of work or product backlog, declaring which of scope, time, cost, quality and risk is fixed and which floats, estimating with ranges instead of single dates, relative estimation and story points, Monte Carlo forecasting over throughput data, planning fallacy and reference class forecasting, WIP limits, lead time and cycle time, cumulative flow and burnup charts, a RAID or risk-and-assumption log with owner and trigger, cross-team dependency tracking and critical path, a RACI and stakeholder communication plan, RAG status reports and watermelon reporting, milestone versus incremental delivery, change-request and scope-change control, decision records for management decisions, project closure with acceptance criteria and handover to operations, retrospectives with owned actions, PMBOK Guide Eighth Edition, PRINCE2 7, the Scrum Guide, SAFe,

serialexperimentslainnnn Skill

Use when running or designing the incident process itself — declaring an incident, severity matrix (SEV1-SEV4, impact x urgency), Incident Commander, operations lead, communications lead and scribe roles, incident channel and status page cadence, stakeholder and customer update templates, mitigate-before-diagnose calls, rollback decisions, command handover in long incidents, incident closure, blameless postmortem with owned action items, time-to-declare and time-to-mitigate metrics and MTTR pitfalls, ITIL major incident and problem management, game days and tabletop exercises, vendor outage and third-party or data-breach incidents.

serialexperimentslainnnn Skill

Use when privacy must be built into the system rather than written in a policy — PII discovery in source and columns, minimization and purpose limitation by design, automated deletion that actually deletes everywhere, LINDDUN privacy threat modelling (GO/PRO/MAESTRO), NIST Privacy Framework, DPIA/EIPD triggers, k-anonymity, l-diversity, t-closeness and differential privacy budgets (OpenDP, SmartNoise, Tumult, Google DP), tokenization, masking, synthetic test data, Presidio, crypto-shredding with per-data-subject keys, GDPR data subject rights (access, portability, rectification, erasure) implemented as software across every copy, consent as versioned auditable state, PII leaking into logs, traces and metrics, EU-US Data Privacy Framework and international transfer design, personal data in AI training, model memorization and the AI Act, and personal data breach impact assessment.

boxlogodev Bundle

This skill handles all SAP Analytics Cloud (SAC) tasks including Story design, Analytic Applications, Smart Insights, Predictive scenarios, Planning models, data connectivity (live vs. import), HANA Cloud connection, BW Bridge, BTP destination configuration, Datasphere integration, R visualizations, Smart Discovery, allocation, value driver tree, Time-series forecasting, Calculated Measures, Hierarchies, SAC Mobile, embedding (SAP Build Apps, Fiori), and performance optimization. Use whenever the user mentions SAC, Analytics Cloud, SAC Story, Analytic Application, BW Bridge, SAC Planning, Smart Insights, Predictive, or BTP analytics.

serialexperimentslainnnn Skill

Knowing what you actually own — asset inventory and CMDB as engineering artifacts, not audit paperwork. Use when choosing or operating NetBox (DCIM racks/devices/interfaces, IPAM prefixes/IP ranges, cables, virtual machines, custom fields, Diode ingestion, Orb discovery agent, NetBox Assurance drift), Nautobot, GLPI and the GLPI Agent, Snipe-IT, Ralph, i-doit, OCS Inventory or a ServiceNow CMDB aligned to CSDM, populating records by automated discovery (Nmap sweeps, LLDP/CDP neighbours, SNMP, osquery, cloud provider APIs, hypervisor and Kubernetes APIs, agent check-ins) versus manual entry, reconciling conflicting data from several sources and deciding which wins per attribute, picking a stable unique asset identifier that is not the hostname or the IP, modelling service dependency and CI relationships so an incident can answer "what breaks if this dies", tracking hardware and software asset lifecycle from purchase to disposal, finding the running server nobody can explain or switch off, stale record detectio