Packs
Start from your role or the job in front of you. Each pack installs with one command, and every role pack brings core with it. The number beside a pack is how many of that job's skills it holds. Choosing between two? Compare them side by side.
Start with your role
- Product managerProduct manager · Trackers
- Software engineerDev team · API builder
- Frontend engineerFrontend
- Solution architectSolution architect
- SRE or on-call engineerSRE / on-call
- Platform or infrastructure engineerInfrastructure as code
- DesignerExperience design · Design
- Data analystData and analytics
- ResearcherResearch
- Compliance, risk or privacy leadGovernance, risk and compliance
- AI engineerAI engineering · Skill engineering
- Writing for leaders or customersStakeholder comms · Converters
- Applying for a jobJob applications
Or start from the job
Decide what to build
Turn a direction into a committed, measurable plan: press releases, strategy frameworks, OKRs, business cases, requirements, PRDs, and the metrics that will say whether it worked.
Design the system
Commit the shape before the code: decision records, design docs, diagrams, API and data contracts, migration and threat models, and the design of any agentic parts.
Build and review software
The loop around the code itself: supervised implementation, adversarial review panels, test plans, triage, pull request descriptions, a ranked technical-debt register, accessibility and static-analysis passes, and the policy files agents read.
Build on the Claude API
Skills for teams building directly on the Anthropic API — prompt caching strategy, token budgeting, eval generation, and tool-use schema writing.
Run and recover the service
Operate what shipped: runbooks, observability design, release notes, incident communication, and the postmortem that closes the loop.
Explain it to decision makers
Get a non-technical audience to a decision: audience profiling, deck outlines and real decks, exec summaries, decision logs, and how-to guides.
Govern AI use
Adopt AI deliberately and prove what it is doing: readiness assessment, use-case triage, rollout plans, acceptable-use policy, adoption staging, and usage reporting.
Create on brand collateral
Make collateral that looks like it came from your team: capture the brand once, then build decks with your logo, colours and fonts.
Get a draft ready to ship
The passes either side of a generator: collect a messy input into a structured brief, critique the argument, and strip the machine artifacts before it leaves the building.
Design the experience
Shape what people see and read before it's built: information architecture, interface copy, content specs, component specs and service blueprints.
Research a question
Take a question to a sourced answer: a research plan with a stopping rule, a cited synthesis of the sources, and competing explanations weighed against the evidence.
Define and trust the numbers
Make the numbers a business runs on mean one thing: SQL reviewed for wrong answers, and dashboards specced before they're built, with every number on them defined.
Manage risk and compliance
Prepare the material compliance asks for: a data protection impact assessment, a SOC 2 evidence map, a risk register with owners and review dates, and answers to a customer's security questionnaire with the evidence behind each.
Build agent skills
Write and review Agent Skills for any tool: a portable SKILL.md with evals, and an audit of an existing skill before it ships.
Apply for a job
Choose which of an employer's roles to go for, then prepare one application that is tailored and true: an honest fit check against the posting, a resume reworked without adding a claim, a cover letter built only from what you supplied, and the application form's answers drafted from your resume.
Every pack
- Core
The cross-role toolkit every pack builds on: structured intake, document critique, the review council, output hygiene, and the decision graph behind a codebase, plus the ship-a-draft wrapper. Installed automatically with every role pack.
Start here: Turn rough notes into a structured brief, then get a verdict on the draft
Walk through a typical session: brief-intake → doc-critique → output-hygiene
- Solution architect
Design-phase artifacts: diagrams, decision records, design docs, contracts, schemas, threat models, and the reviews that gate them.
Start here: Record an architecture decision your team already made
Walk through a typical session: nfr-spec → design-doc → architecture-diagrams → threat-model → council-review → adr-generator
- Product manager
Direction to requirements: PR/FAQs, strategy frameworks, OKRs, business cases, interviews, PRDs, journey maps, and success measurement.
Start here: Pressure-test a product idea before anyone builds it
Walk through a typical session: requirements-interview → brief-intake → prd-draft → doc-critique → success-metrics
- Dev team
Build-and-ship: story splitting, implementation with adversarial review, test plans, triage, pull request descriptions, a ranked technical-debt register, migrations, launch readiness, release notes, agent-policy files, and code-quality gates.
Start here: Find out whether your current branch is safe to merge
Walk through a typical session: user-story-splitter → feature-implement-loop → pre-merge-review → council-review
- SRE / on-call
Operate the service: runbooks, observability design, incident communications, postmortems, and capacity/cost models.
Start here: Write the runbook an on-call engineer can follow at 3am
Walk through a typical session: observability-plan → runbook-generator → incident-comms → postmortem-generator → delivery-metrics-report
- Stakeholder comms
Non-technical audiences: audience profiling, exec summaries, decision logs, and guides. Decks live in the design pack.
Start here: Turn a long document into a one-page summary for leadership
Walk through a typical session: decision-log → audience-profile → exec-summary → doc-critique → output-hygiene
- Design
On-brand visual work: capture a brand once as a brand.json the Word and PowerPoint converters apply, and plan a deck slide by slide for its audience.
Start here: Capture your brand once, then outline a deck for it
Walk through a typical session: brand-kit → slide-outliner → doc-critique
- AI engineering
Adopt and build AI systems: readiness assessment, use-case triage, rollout and acceptable-use policy, plus agent loop design, subagent orchestration, spend budgets, agent security review, eval harnesses, and AI-usage reporting.
Start here: Find out whether a team is ready to adopt AI tools, and what blocks it first
Walk through a typical session: ai-readiness-assessment → ai-use-case-triage → ai-usage-policy → ai-adoption-rollout
- API builder
Skills for teams building on the Anthropic API — prompt caching, token budgeting, eval generation for skills, and tool-use schema writing.
Start here: Find where prompt caching will cut your input costs
Walk through a typical session: tool-use-schema-writer → token-budget-estimator → prompt-caching-advisor
- Converters
Turn Markdown into Word, Excel, PowerPoint and Confluence files that people outside engineering can open, and turn their files back into Markdown. Standard-library Python scripts, with nothing to install.
Start here: Send a Markdown report as a Word document and its tables as a spreadsheet
Walk through a typical session: file-to-markdown → output-hygiene → md-to-docx → md-to-xlsx
- Experience design
The experience around a product: the structure people navigate, the content and interface words they read, the components they use, and the service behind it all.
Start here: Restructure a menu users get lost in, and get the test that proves the new one works
Walk through a typical session: information-architecture → content-design → ux-writing → design-system-spec → service-blueprint → doc-critique
- Research
Take a question from vague to answered: plan the research around the decision it serves, synthesise the sources with every claim cited, and rank rival explanations by the evidence against them.
Start here: Turn a vague research request into a plan you can finish
Walk through a typical session: research-plan → source-synthesis → hypothesis-comparison
- Trackers
For leads and PMs who run work in Jira, Linear or GitHub Projects: load a PRD into the tracker, triage the backlog, write the weekly status report, and check the tracker still matches the doc, all from an export or an MCP tool, with the numbers computed rather than estimated.
Start here: Triage your backlog before the next refinement session
Walk through a typical session: tracker-brief-sync → backlog-triage → team-status-report → tracker-brief-sync
- Data and analytics
For analysts and the people who rely on their numbers: review SQL for the bugs that quietly inflate a figure, and spec dashboards around a decision instead of every chart that was easy to make.
Start here: Check a query before its number goes into a report
Walk through a typical session: sql-review → dashboard-spec → doc-critique
- Governance, risk and compliance
Governance, risk and compliance drafts for compliance leads, DPOs and risk owners: a risk register with a checked heat map, a GDPR data protection impact assessment, a SOC 2 control-to-evidence map, and answers to a customer security questionnaire drawn from your own evidence, each prepared for a qualified person to review.
Start here: Turn a list of worries into a scored, owned risk register
Walk through a typical session: risk-register → dpia → soc2-evidence-map → security-questionnaire-response → doc-critique
- Infrastructure as code
Terraform you can hand to another team and plans you can trust before apply: reusable modules with secure defaults, and a plan review that catches destroys, data loss, access widening and drift.
Start here: Write a module, then review its plan before the first apply
Walk through a typical session: terraform-module → terraform-plan-review → doc-critique
- Frontend
For frontend engineers and the people who review their pages: read a Lighthouse report for what actually slows the page, find what makes a JavaScript bundle heavy, and choose how each route is rendered from what it needs.
Start here: Find out what actually makes a page slow for real users
Walk through a typical session: rendering-strategy → bundle-size-review → web-performance-review
- Skill engineering
For people writing Agent Skills in their own repos: write a portable SKILL.md folder from a described task, then audit any skill for routing, portability, safety, structure and evals before you share it.
Start here: Turn a task you keep explaining into a skill, then review it
Walk through a typical session: skill-author → skill-review
- Job applications
Job applications, for any occupation: a shortlist of which of an employer's roles to go for, an honest check of your resume against the posting, a tailored resume and a cover letter that say nothing you didn't, the application form's answers drafted from your resume, and a script that lists every figure and name in a draft that your own resume doesn't contain.
Start here: Find out where you stand against a posting before you write the application
Walk through a typical session: job-fit-analysis → resume-tailor → cover-letter → application-form-answers → output-hygiene