How-to

I have a goal — what are the steps?

Per pack (19)

• Use the AI engineering pack — Install the AI engineering pack, run its first task, and follow a typical session step by step.
• Use the API builder pack — Install the API builder pack, run its first task, and follow a typical session step by step.
• Use the Job applications pack — Install the Job applications pack, run its first task, and follow a typical session step by step.
• Use the Converters pack — Install the Converters pack, run its first task, and follow a typical session step by step.
• Use the Core pack — Install the Core pack, run its first task, and follow a typical session step by step.
• Use the Data and analytics pack — Install the Data and analytics pack, run its first task, and follow a typical session step by step.
• Use the Design pack — Install the Design pack, run its first task, and follow a typical session step by step.
• Use the Dev team pack — Install the Dev team pack, run its first task, and follow a typical session step by step.
• Use the Experience design pack — Install the Experience design pack, run its first task, and follow a typical session step by step.
• Use the Frontend pack — Install the Frontend pack, run its first task, and follow a typical session step by step.
• Use the Governance, risk and compliance pack — Install the Governance, risk and compliance pack, run its first task, and follow a typical session step by step.
• Use the Infrastructure as code pack — Install the Infrastructure as code pack, run its first task, and follow a typical session step by step.
• Use the Product manager pack — Install the Product manager pack, run its first task, and follow a typical session step by step.
• Use the Research pack — Install the Research pack, run its first task, and follow a typical session step by step.
• Use the Skill engineering pack — Install the Skill engineering pack, run its first task, and follow a typical session step by step.
• Use the Solution architect pack — Install the Solution architect pack, run its first task, and follow a typical session step by step.
• Use the SRE / on-call pack — Install the SRE / on-call pack, run its first task, and follow a typical session step by step.
• Use the Stakeholder comms pack — Install the Stakeholder comms pack, run its first task, and follow a typical session step by step.
• Use the Trackers pack — Install the Trackers pack, run its first task, and follow a typical session step by step.

Per skill (113)

• Use accessibility-audit — Adversarially audit a UI (component code, page markup, screenshot, or flow) against WCAG 2.2 AA
• Use adr-generator — Generate an Architecture Decision Record (ADR) from a context-decision-consequences brief
• Use agent-adoption-stage — Place an engineering team on the agentic-coding adoption ladder (0 gated → 4 intent-steered) using observables like agents-in-flight per engineer and who writes the…
• Use agent-budget — Write the spend spec for an agentic workflow
• Use agent-config-review — Review a coding agent's configuration for access broader than the work needs and give a verdict
• Use agent-incident-response — Plan the first hour after something went wrong with an AI coding agent or its tooling
• Use agent-loop-design — Design a supervised agent loop
• Use agent-threat-model — Threat-model an AI agent deployment against the lethal trifecta
• Use agents-md-generator — Generate or audit a repository's AGENTS.md
• Use ai-adoption-rollout — Plan the human rollout of an AI tool or workflow to an organisation
• Use ai-readiness-assessment — Score an organisation's or team's readiness to adopt AI tooling across six gating dimensions
• Use ai-usage-policy — Draft an organisation's AI use policy or staff guidance from what it has told you about its people, tools, data and worries
• Use ai-usage-report — Generate a per-user or team-level report on how AI tools are being used
• Use ai-use-case-triage — Turn a pile of candidate AI use cases into a ranked portfolio
• Use api-contract-draft — Draft an OpenAPI 3.1 contract from a feature brief or story
• Use application-form-answers — Prepare the answers to a job application form from the person's resume
• Use architecture-diagrams — Generate architecture diagrams (Mermaid, PlantUML, C4) from a written description of a system
• Use audience-profile — Translate an audience type (exec, board, technical, sales, investor, internal, partner, customer) into structural rules
• Use backlog-triage — Triage a whole backlog export from Jira, Linear or GitHub Projects (CSV, JSON or an MCP tool)
• Use behaviour-equivalence — Prove that a rewritten, migrated or refactored component behaves the same as the old one with a golden-master comparison
• Use brand-kit — Capture a brand once as a reusable brand.json
• Use brief-intake — Turn raw mess
• Use bug-triage — Turn a vague bug report (Slack message, support ticket, "it's broken on mobile sometimes") into an actionable ticket
• Use bundle-size-review — Find what makes a JavaScript bundle heavy and what can safely come out, from the bundler's stats file (webpack stats.json, an esbuild metafile, or the…
• Use business-case — Build a business case for a build/buy/defer investment decision
• Use capacity-cost-model — Build a capacity and cost model for a service or feature
• Use cloud-cost-review — Review actual cloud spend from a cost export (AWS CUR or Data Exports, GCP billing export, Azure cost details) and produce a ranked savings report
• Use codebase-tour — Get a newcomer (a new engineer, or the agent itself) oriented in an unfamiliar repository before they make one specific change, with a short tour scoped to that change
• Use content-design — Write a content spec for a page or journey from user needs
• Use context-graph — Map the decisions behind a codebase from its ADRs, RFCs and design records
• Use council-review — Convene a council of distinct senior-engineer personas (Architect, Security, Operator/SRE, Pragmatist, User-Advocate, plus optional bench seats) to deliberate a…
• Use cover-letter — Write a cover letter for one job from the person's resume and the posting
• Use dashboard-spec — Spec a dashboard before anyone builds it
• Use data-contract — Draft a data contract for a dataset, table, or event stream consumed by others
• Use decision-log — Extract decisions, action items, owners, and due dates from meeting notes, Slack threads, design-review transcripts, or any unstructured discussion
• Use delivery-metrics-report — Produce a delivery metrics report for one service from deployment, incident and pull-request exports
• Use dependency-upgrade-review — Give a merge verdict on a dependency-upgrade pull request (Dependabot, Renovate or a hand-made bump) across npm, pip, Go, Cargo and Maven lockfiles and GitHub Actions…
• Use design-doc — Generate a Google-style engineering design doc (problem, goals/non-goals, options considered, recommended approach, risks, rollout) from a feature brief or short…
• Use design-system-spec — Write a design system component spec
• Use devils-advocate — Adversarial review of a code change before it merges
• Use doc-critique — Review an existing document
• Use dpia — Draft a data protection impact assessment (DPIA) for one processing activity in the structure GDPR Article 35(7) requires
• Use eval-harness-generator — Takes a skill's SKILL.md and generates a set of eval cases
• Use event-contract-draft — Draft the contract for an event or message interface (Kafka topics, SNS/SQS, EventBridge, Pub/Sub, RabbitMQ, webhooks) as an AsyncAPI 3.0 document plus a short decisions…
• Use exec-summary — Compress a long technical document, design doc, or proposal into a one-page executive summary aimed at non-technical or time-poor stakeholders
• Use feature-implement-loop — Implement a feature or story so it ends up *verified*, not just generated
• Use feedback-synthesis — Turn raw customer feedback
• Use figma-diagrams — Work with Figma and FigJam files via the Figma REST API
• Use file-to-markdown — Convert a Word document, PowerPoint deck, Excel workbook, web page, CSV, JSON, text file, email (.eml or Outlook .msg) or PDF into clean Markdown
• Use guide-builder — Turn raw notes, a spec, a thread or a messy procedure into a guide someone else can follow
• Use hypothesis-comparison — Compare rival explanations for an observation with analysis of competing hypotheses (ACH)
• Use incident-comms — Draft audience-segmented updates during a live incident
• Use information-architecture — Design the information architecture for a product or site
• Use interactive-diagram — Turn a codebase, a system description, a process or a database schema into one self-contained interactive HTML diagram (architecture, workflow, data flow, lifecycle…
• Use job-fit-analysis — Compare a job posting with a resume and say honestly whether to apply
• Use judge-audit — Audit whether an LLM-as-judge, or a panel of judges, can be trusted for the decision its scores drive, before anyone acts on them
• Use launch-readiness — Produce a go/no-go launch readiness report for a merged change before it goes live
• Use lean-canvas — Turn a startup or internal-product idea into a lean canvas that finds what could kill it
• Use llm-eval-harness — Design an evaluation harness for an LLM-powered feature
• Use mcp-pairing — Recommend which MCP servers to connect for a loop, workflow or task, stage by stage, with the narrowest access that works
• Use md-to-confluence — Turn a Markdown runbook, design note or guide into a Confluence page
• Use md-to-docx — Turn a Markdown draft into a Word document (.docx) that someone outside engineering can open, edit and track changes in, with real Heading styles so the navigation pane…
• Use md-to-pptx — Turn an existing Markdown document (a status report, runbook, review or notes) into a PowerPoint deck (.pptx) that opens without a repair prompt, with nothing to install
• Use md-to-xlsx — Turn the tables in a Markdown file, a CSV or a JSON array into an Excel workbook (.xlsx) that finance, ops or a client can sort, filter and sum, with one sheet per table…
• Use migration-plan — Generate a phased migration or rollout plan (schema change, API version, datastore swap, platform move, auth-provider switch)
• Use nfr-spec — Sweep a feature or system through the full non-functional requirements catalog
• Use observability-plan — Design an observability plan for a service
• Use okr-cascade — Cascade company OKRs to team-level OKRs
• Use output-hygiene — Review agent-written text before it ships and strip the machine artifacts it carries
• Use postmortem-generator — Write a blameless incident postmortem from the raw material (chat scrollback, alert history, timeline, notes) for the audience and length the user names
• Use pr-description-writer — Write the pull request title and description for one change, from the actual diff and commits
• Use prd-draft — Draft a Product Requirements Document from a feature idea or brief
• Use pre-merge-review — Gate an existing change for merge
• Use prfaq — Write an Amazon-style PR/FAQ
• Use prompt-caching-advisor — Analyzes a prompt or conversation structure and identifies the highest-value cache breakpoints
• Use refactor-plan — Plan paying down one piece of technical debt as a refactor that serves the goal it is blocking
• Use release-notes — Write release notes from a git log, a list of merged PRs or rough notes about what changed
• Use rendering-strategy — Decide route by route how each page of a web app is rendered
• Use requirements-interview — Generate per-stakeholder interview kits for feature discovery
• Use research-plan — Turn a vague research question into a research plan
• Use resume-tailor — Tailor a resume or CV to one job posting without adding anything that isn't true
• Use reverse-architecture — Reverse-engineer a system's architecture from what already exists
• Use risk-register — Build or update an enterprise or project risk register
• Use role-shortlist — Read every open role on an employer's careers page, a job-board export or a folder of saved postings, and say which ones one person should apply for
• Use rollout-plan — Plan the progressive release of a code change behind a feature flag or canary
• Use runbook-generator — Generate an operational runbook for a service
• Use security-questionnaire-response — Answer a customer's security questionnaire from your own evidence
• Use service-blueprint — Build a service blueprint
• Use skill-author — Write a new portable Agent Skill (a SKILL.md folder) from a described task, for Claude Code, Codex, Copilot, Cursor, Kiro or Antigravity in any repo
• Use skill-review — Audit an existing Agent Skill folder (SKILL.md plus its scripts, references and evals) for Claude Code, Codex, Copilot, Cursor, Kiro or Antigravity, and return a READY /…
• Use slide-outliner — Outline an architecture review or technical pitch deck
• Use slo-spec — Define service level objectives for a service from its critical user journeys
• Use soc2-evidence-map — Map an organisation's controls to the SOC 2 Trust Services Criteria in scope (Security always, plus Availability, Confidentiality, Processing Integrity or Privacy if…
• Use sonar-onboard — Scaffold a repo for Sonar compliance
• Use sonar-review — Run a Sonar scan against the just-changed code on the current branch and produce a structured compliance report
• Use source-synthesis — Answer a question from a set of sources the user supplied
• Use sql-review — Review a SQL query for correctness first and performance second
• Use strategy-analysis — Run a strategy framework
• Use subagent-design — Decompose a task into an orchestrator and subagents
• Use success-metrics — Define how a feature's success will be measured before it's built
• Use team-status-report — Write a weekly team status report from tracker data (Jira, Linear or GitHub Projects, via CSV, JSON or an MCP tool)
• Use tech-debt-register — Turn a pile of technical-debt complaints, TODOs and incident notes into a ranked register
• Use terraform-module — Generate a Terraform module from a described need, with main.tf, variables.tf, outputs.tf and versions.tf, typed and validated variables, secure defaults (encryption on…
• Use terraform-plan-review — Review a terraform plan before apply, from the plan text or terraform show -json output
• Use test-plan-generator — Generate a risk-based test plan for a feature, PR, or release
• Use threat-model — Produce a STRIDE threat model from a design doc, architecture description, or feature spec
• Use token-budget-estimator — Estimates input and output token usage for a described agentic workflow, surfaces the dominant cost drivers, and suggests max_tokens budget controls per component
• Use tool-use-schema-writer — Takes a function description (name, purpose, parameters) and writes a valid Anthropic tool_use JSON schema, with type annotations, required fields, and a description for…
• Use tracker-brief-sync — Turn a brief or PRD (such as prd-draft output) into tracker-ready epics and issues
• Use user-journey-map — Map a customer's end-to-end journey toward an outcome
• Use user-story-splitter — Split an epic, feature request, or PRD chunk into independently shippable user stories with testable Gherkin acceptance criteria and a recommended build order
• Use ux-writing — Write the interface copy for a flow or component
• Use web-performance-review — Read a Lighthouse report or PageSpeed Insights result, with field data when there is any (CrUX, PSI loadingExperience or RUM p75), and say what makes the page slow for…