Claude Skills by eugenelim

Enumerate the named camps on a contested topic before research begins. Builds the perspective scaffold that `/source-map` and `/compare-hypotheses` consume downstream in the decision pipeline. Grounded in Wikipedia NPOV (neutral point of view — fairly represent significant views) and ACH (competing hypotheses — surface all explanations before evaluating). Produces `<topic-slug>-perspectives.md` listing each camp's name, its core claim, and representative voices, plus a tension map recording w...

Curate the authoritative sources for a topic before research begins. Surveys adjacent material to discover voices rather than asking the LLM directly who's authoritative — STORM's finding is that direct question-asking does not work well for source discovery. Produces `<topic-slug>-sources.md` grouping candidates by primacy (`primary` / `secondary` / `tertiary`). When invoked downstream of `/identify-perspectives`, groups sources by camp; in standalone invocations, skips the camp-grouping ste...

Use when someone asks how a dashboard, report, or monitoring view should help a user understand data and act. Produces domain-model-first information architecture and a widget hierarchy for the analytical surface, not individual chart implementations. Use `interaction-design` for component behavior, `conversion-design` for marketing surfaces, and `workspace-design` for sustained-work tools. Metric and outcome strategy belongs upstream; shaping the analytics product belongs to `frame-intent`; ...

Use when someone asks what a surface should communicate, to whom, in what form, and in what order before wireframes or final copy. Produces a content brief for acquisition, product, or reference surfaces. It owns message and narrative structure; `tone-of-voice` owns the brand register, `copy-direction` owns acquisition-surface copy goals, and `ux-writing` owns product UI strings. Organization-level content strategy belongs to `define-content-strategy`; feature framing belongs to `frame-intent...

Use when someone asks how to structure a landing page, product homepage, pricing page, or acquisition flow so a qualified visitor understands the offer and can act. Produces information architecture and structural specifications for a conversion surface. Use `content-design` for its message hierarchy and `copy-direction` for its copy goals; use `user-flow` and `interaction-design` for product UI. Go-to-market strategy belongs upstream; shaping the acquisition initiative belongs to `frame-inte...

Use when someone asks what the copy on one marketing or acquisition surface should feel like before the lines are written. Produces ranked, grounded copy goals and a `copy-direction.md` record for that surface. `tone-of-voice` owns the cross-surface brand register, `content-design` runs first to decide message and narrative structure, and `ux-writing` owns product UI strings. Product or growth strategy belongs to product strategy; framing the acquisition bet belongs to `frame-intent`; impleme...

Use when someone says a digital surface should feel premium, calm, playful, or otherwise has a vibe but no shared visual direction. Produces ranked aesthetic goals and a `creative-direction.md` record grounded in referents and arbitration rules. Use `design-system` after the direction to derive tokens, `information-architecture` for page hierarchy, and `design-review` to critique existing work. Product positioning belongs to product strategy; framing or scoping the bet belongs to `frame-inten...

Use when a design team asks for durable rules that turn journey evidence and opportunity pains into consistent decisions across sprints. Produces 3–5 named design principles, each with rationale and an arbitration test. Use `creative-direction` for visual goals, `design-system` for token taxonomy, and `design-review` to evaluate existing work. Target segments and product positioning belong to product strategy; choosing and scoping a bet belongs to product engineering; encoding rules in compon...

Use when someone asks to critique an existing rendered screen, flow, or mockup for usability, quality-floor, clarity, and aesthetic-fit problems. Produces a severity-rated findings list grounded in the actual artifact. Use `creative-direction` to name a new visual direction, `information-architecture` to design hierarchy, and `design-system` to derive tokens. Reviewing product strategy or choosing a bet is upstream strategy work; framing the work belongs to `frame-intent`; reviewing code defe...

Use when an approved aesthetic direction exists and someone asks how to name and organize semantic tokens, spacing, type, or color scales. Produces a token taxonomy and rationale; it does not implement token values. Use `creative-direction` to establish the vibe, `information-architecture` for page hierarchy, and `design-review` to evaluate an existing surface. Product differentiation belongs to product strategy; framing a design-system initiative belongs to `frame-intent`; implementing token...

Use when someone asks how a documentation site, help center, API reference, or guide set should be organized so readers reach first value. Produces content-type, information-architecture, and navigation specifications that scale with the corpus. Use `conversion-design` for marketing surfaces and `informational-design` for editorial reading surfaces. Organization-level documentation strategy is upstream; shaping a docs-platform initiative belongs to product engineering; authoring the technical...

Use when someone asks where the current experience-design thread stands, which design artifacts exist, what is missing, or which design skill comes next. Reads the configured design output and returns a read-only orientation; it never writes files or performs the missing design work. Product or portfolio status belongs to product strategy, prioritizing and shaping the next feature belongs to product engineering, and implementation or build status belongs to frontend engineering.

Use when someone asks what goes where on a screen or flow, in what order, and how users stay oriented. Produces an information-architecture and layout-reasoning document covering hierarchy, reading flow, progressive disclosure, navigation, and wayfinding. Use `creative-direction` for visual mood, `interaction-design` for within-screen behavior, `user-flow` for screen sequence, and `design-review` for critique. Product direction belongs to product strategy; scoping the feature belongs to `fram...

Use when someone asks how an article, news page, editorial feature, or other long-form informational surface should support sustained reading. Produces typography, hierarchy, and reading-flow specifications for the surface. Use `documentation-design` for task/reference systems, `conversion-design` for acquisition pages, and `workspace-design` for tools. Editorial or product strategy is upstream; shaping a publishing-product bet belongs to product engineering; writing the article or building i...

Use when someone asks how one screen or component should respond to actions, validate input, transition, recover, or feel in use. Produces behavioral and state specifications for the interaction. Use `information-architecture` for hierarchy, `user-flow` for cross-screen routes, and `creative-direction` for visual mood; `ux-writing` owns the strings shown in those states. Product strategy is upstream; framing and scoping the feature belongs to `frame-intent`; implementing the state machine, mo...

Use when a team asks what an end user goes through across an experience, from one meaningful outcome to the next. Produces a customer journey map of stages, actions, touchpoints, emotions, pains, and opportunities, adjusted for the relevant platform. Use `service-blueprint` for backing services, `user-flow` to turn the journey into screens, and `process-mapping` for internal operations. Adoption strategy belongs to product strategy; selecting and scoping a bet belongs to product-engineering s...

Use when someone asks how a catalogue, listing grid, comparison view, detail page, or transaction bridge should help participants discover and choose in a marketplace. Produces information-architecture specifications for search, filters, listings, comparison, and the path to transaction. Use `conversion-design` for a single-product marketing page and `workspace-design` for an internal management tool. Marketplace strategy is upstream; framing and sizing the marketplace bet belongs to product ...

Use when a team asks how an internal business operation works today or should work tomorrow across actors and handoffs. Produces a SIPOC scope, swimlane map, as-is/to-be flow, and pain-and-waste register. Use `journey-mapping` for the customer's experience, `service-blueprint` to connect a journey to backstage support, and `user-flow` for screens. Operating or product strategy belongs upstream; shaping an automation bet belongs to `frame-intent`; implementing workflow software belongs to engi...

Use when someone asks what people, services, and systems support each step of an existing customer journey. Produces a service blueprint across frontstage, line of visibility, backstage, and support. Use `journey-mapping` to discover the customer path first, `user-flow` for screen transitions, and `process-mapping` for an internal operation without the customer lens. Service strategy belongs upstream; framing the initiative belongs to `frame-intent`; implementing service calls or frontend beh...

Use when a team asks how the brand should sound consistently across channels and surfaces. Produces a brand-register document with named, ranked voice goals and arbitration rules. It is the upstream anchor: `content-design` owns a surface's message and structure, `copy-direction` owns acquisition-surface copy goals, and `ux-writing` owns product UI strings. Organization-level product or content strategy belongs to the strategy packs; shaping a product initiative belongs to `frame-intent`; imp...

Use when an approved customer journey needs to become screens, transitions, failure paths, and navigation routes. Produces a complete screen sequence plus one self-contained brief per screen and a whole-flow walk-through. Use `journey-mapping` to understand the journey first, `interaction-design` for behavior within one screen, and `service-blueprint` for backing services. Adoption strategy belongs upstream; appetite and scope belong to `frame-intent`; implementing routes and screens belongs ...

Use when someone asks how a productivity, collaboration, or agentic workspace should support sustained professional work across sessions. Produces a workspace-surface specification covering context persistence, collaboration state, ambient attention, interruptions, and session arcs. Use `analytical-design` for dashboards and monitoring views and `marketplace-design` for exchange surfaces. Product strategy is upstream; choosing the appetite and scope belongs to product engineering; implementin...

Read and inspect Figma files (Cloud) via the REST API. Supports fetching files / specific nodes / file metadata / version history / comments, rendering frames to PNG/SVG/JPG/PDF, posting comments (file-level or pinned to a node), converting FigJam connector graphs to Mermaid, and best-effort reads of design tokens (variables) and dev resources where the token's plan allows. Use when the user wants to read, render, comment on, or extract structure from a Figma file. Does NOT modify design cont...

Deep accessibility engineering beyond automated tooling — focus management architecture, ARIA role correctness under dynamic mutation, live-region discipline, keyboard contract specification, and manual WCAG 2.2 AA verification for the two criteria automated tools miss.

Design a UI component's public interface — props/slots/events, controlled vs. uncontrolled ownership, composition patterns, lifecycle contract, and usage documentation — before writing any implementation.

Organize CSS at scale using cascade layers, scoping strategies, and specificity budgets — preventing specificity wars, enabling safe deletion, and making CSS that other engineers can reason about.

Measure, diagnose, and remediate Core Web Vitals and asset budget violations using structured profiling, causality analysis, and repeatable remediation patterns.

Orient skill — read the current surface's evidence manifest, known exceptions, and gate history to return a surface-state summary against the frontend engineering quality floor.

Load when a task's primary output is HTML, CSS, or JS. Provides design pre-flight, codified craft rules, GATES verification commands, and an evidence manifest for that surface. Four modes — create (new surface), retrofit (improving existing), audit (review only), verify (run gates and manifest).

Select and implement the correct rendering model (CSR/SSR/SSG/ISR/RSC) for each route based on data-access patterns, performance targets, and personalization requirements.

Design and implement adaptive layouts using CSS Grid, Flexbox, container queries, and fluid typography/spacing — the craft layer for layouts that work correctly across all viewport sizes without JavaScript.

Design and govern a three-tier CSS custom property token system (primitive → semantic → component), including semantic alias layers, light/dark theming, and DTCG-compatible source generation.

Use when GitHub work should enter the repository work-intake route, including an Issue, Milestone, view, or cross-repository selection.

Reviewed refresh and confirmed GitHub coordination write-back processor for tracker-origin artifacts.

Use this skill when the user asks to create, write, draft, or open a new ADR (architecture decision record). Triggers on phrases like "new ADR", "write an ADR for...", "record this decision", "let's ADR this". Do NOT use for RFCs (use `new-rfc`) or feature specs (use `new-spec`).

Use this skill when the user asks to propose, draft, or open an RFC, update the rules, amend the charter, change our principles, or change the convention for something; also use it for follow-on RFC artifacts after acceptance. Triggers on "RFC", "propose a change to...", "let's get input on...", "draft a proposal", "create the follow-on specs for RFC-NNNN", "generate ADRs for the accepted RFC", and "implement the follow-on work from an RFC". Do NOT use for a settled architectural decision (us...

Surface the current RFC landscape at a glance — how many RFCs are in each lifecycle state, which are active, and how many findings are waiting in the candidate register. Triggers on 'rfc status', 'show rfcs', 'what rfcs are open', 'rfc dashboard', 'how many rfcs', 'rfc candidates', 'rfc report', or any request for an overview of the RFC landscape. Read-only: never creates or modifies RFC files.

Use this skill to author governed, best-practice Terraform/OpenTofu infrastructure from a plain-language intent. Triggers on "provision X", "create Terraform for", "generate IaC for", "set up cloud resources", "write Terraform for", "scaffold infrastructure". Stops at a digest-pinned `terraform plan` (G4 handoff); never runs `apply`. Governance-first — resolves the decision-record surface before any code.

Use this skill to audit Terraform/OpenTofu drift, reconcile state, run a pre-change preflight, or check an incoming IaC diff for ADR compliance. Triggers on "reconcile my infrastructure", "check for drift", "drift audit", "what drifted", "before I change X check drift", "is my infra in sync", "adr-check", "does this change comply", "check this diff against our ADRs", "compliance check this IaC change". Never autonomously applies. Shares generate-iac's references and reviewers.

Use when Linear work should enter the repository work-intake route, including an Issue, sub-issues, a Project, Cycle, view, or cross-repository selection.

Use this compatibility skill when you want to catch up an existing product brief with changes in the linked Linear Issue — "sync the brief with LIN-123", "the Linear issue has been updated, update the brief". It delegates refresh authority, lifecycle checks, and write-back confirmations to the configured `work-intake` Linear refresh processor while preserving the old trigger language.

Read Linear Issues and Projects via the GraphQL API. Supports fetching individual issues (title, description, identifier, sub-issues, owning project), fetching all issues in a project, verifying credentials, and executing confirmed refresh write-back actions through work-intake. Use when you want to read Linear work items to create briefs or catch up a brief with changes.

Use this skill when the user wants to scaffold a new package in the monorepo's `packages/` directory. Triggers on "new package", "create a package called...", "add a library for...". Don't use for new top-level directories (those need an RFC) or for new apps (which go in `apps/`, not `packages/`).

Create, revise, retrofit, audit, or verify product documentation — pack READMEs, journeys, tutorials, how-to guides, reference pages, and explanations. Use when asked to write, improve, restructure, audit, or verify user-facing documentation, fix a pack README, create a guide for a feature, update a journey page, or check whether docs match shipped behavior. Infers the mode from the request. Do NOT use for feature specifications (use new-spec), cross-cutting proposals (use new-rfc), decisions...

Use at business-unit scale to stand up and keep current a value-stream meta-repo — a coordinating repo with no app code that holds the cross-component artifacts a polyrepo has nowhere else to put (the federated Backstage catalog, the shared-contract authority, the C4/bounded-context architecture, and the cross-component delivery rollup). Triggers on "set up a value-stream meta-repo", "coordinate across component repos", "stand up the cross-component catalog", "where does the shared contract l...

Use when an intent is framed and you need to test whether the bet holds before building it out — naming the riskiest assumption, predeclaring a kill condition, and running it under a chosen prototype-approach. Triggers on "de-risk this", "is this assumption true", "what would have to be true", "should we validate or just build it", "test the bet". Routes by reversibility (one-way vs two-way door) and ends in a survive/kill verdict. Do NOT use to author the intent (use `frame-intent`) or to br...

Use when a de-risked intent needs breaking into the next level down — child intents, or a shippable delivery contract at the leaf — and optionally projecting onto a tracker. Triggers on "decompose this", "break this down", "slice this", "what specs come out of this", "push this to Linear/Jira". Recursive (one level at a time); one independently shippable feature becomes a delivery contract, while multi-spec or cross-repository work becomes a delivery brief. Do NOT use to author an intent (use...

Use to turn a raw product idea into a ratified, build-ready decision brief — the upstream discovery loop run by the discovery-lead agent. Triggers on "scaffold the product vision for X", "run a discovery for X", "diverge on the product shape then converge to a brief", "take this idea to a decision brief", "resume the X discovery". It diverges across candidate product shapes, converges the chosen one through a research/product/UX/architecture/safety lens roster, pauses at the consent gates (G0...

Use at step 3 of the PE shaping sequence when you hold an initiative- or capability-scope opportunity and need ≥3 structured comparable solution options that place-bet can reason against. Emits solution-options.md with an options array and a recommendation. Do NOT use for freeform brainstorm (use explore-options), feature-scope divergence (use explore-options), or committing a bet (use place-bet).

Use to generate multiple candidate product shapes before the discovery loop converges on one — the divergence stage that guards against myopic-greedy commitment. Triggers on "give me candidate product shapes", "diverge on the product shape", "what are the options before we commit", "explore alternatives for X", "don't converge yet". Generates N candidates across altitude × mechanic, each with its riskiest assumption, then frames an explicit compare-and-choose. Do NOT use to break down a chose...