sebastian-software
OrganizationPractice-built skills that give AI agents practical judgment for product, web, engineering, delivery, go-to-market, communication, and compliance work.
Categories
Indexed Skills (29)
codebase-improvement
Audit, diagnose, plan, and improve software codebases through repository reconnaissance, evidence-backed findings, competing-hypothesis investigation, leverage-based prioritization, executable plans, backlog reconciliation, and proportionate simplification. Use when asked why a defect or surprising behavior occurs, for a read-only root-cause report, to audit a repository, decide what to improve next, simplify code, create or review an implementation plan, reconcile stale work, plan a risky change in untested legacy code, or implement selected improvements. Do not use for PR-only review, dependency-update-only work, focused test, test-runner, or test-framework diagnosis, architecture-only decisions, or frontend-only diagnosis when a narrower skill applies.
consultant-profile
Create, audit, rewrite, localize, and improve consultant CVs, LinkedIn profiles, case studies, project lists, bios, and senior technology-consulting resumes. Use for positioning, profile completeness, career narratives, evidence-led project selection, cross-channel synchronization, and interview-driven discovery. For the profile as a customer-acquisition or pipeline surface, use linkedin-social-selling.
effective-web
Design, build, review, and improve browser-facing experiences: marketing and content sites, web apps, dashboards, React components, UI/UX, layout, typography, color, forms, tables, accessibility, motion, i18n, interface copy, states, auth UX, CSS, frontend SEO and AI search, browser performance and testing, React architecture, SVG, and HTML/CSS print. Use only when the requested outcome is the design, implementation, review, or verification of a browser experience. Do not use merely because a task mentions the web, a website, URL, browser, or HTML. Not for general browsing, internet or source research, repository or catalog evaluation, fact-finding, backend-only work, infrastructure or deployment, general writing, non-web print, or locale-specific typography.
effective-workflow
Coordinate multi-stage or mixed-domain software work from an unclear request through an authorized change, focused verification, and a review-ready handoff. Use when a task spans diagnosis, implementation, validation, review, or delivery and needs sequencing across repository-native workflows and first-party specialist skills. Prefer the matching specialist directly for an already narrow documentation, dependency, test, review, architecture, port, or frontend request.
linkedin-posts
Create LinkedIn posts, find LinkedIn content ideas, plan a LinkedIn content calendar, and tailor professional posts to an audience, voice, and goal. Use when the user mentions a LinkedIn post, LinkedIn content, LinkedIn idea, social media post for LinkedIn, post engagement, or content calendar for LinkedIn. Route engagement-to-pipeline diagnosis and acquisition strategy to linkedin-social-selling. Route non-LinkedIn, platform-unspecified, and multi-platform social content to create-social-content.
linkedin-social-selling
Plan, build, review, and improve an evidence-led B2B LinkedIn customer acquisition system. Use for LinkedIn positioning and offers, inbound profile strategy, target-account networking, welcome and outreach messages, social selling conversations, content systems, lead magnets, sales funnels, and measurement across the path from profile visit to qualified meeting. Use when the request spans multiple LinkedIn growth activities or connects content and relationships to pipeline; route a post-only writing request to linkedin-posts and field-level profile content or career evidence to consultant-profile.
metro-english
Rewrite text into relaxed US metropolitan team English: the kind of natural, direct, human voice used in Slack threads, GitHub or Linear issue comments, PR notes, async updates, and internal team communication. Use this skill whenever the user asks to make writing sound casual, less formal, less AI-generated, more human, more Slack-like, more startup/team-like, or closer to everyday New York, San Francisco, or Silicon Valley professional English. Also use it when the user provides German or stiff English and wants it turned into natural English for team communication. Do not use it for ASD-STE100, Simplified Technical English, controlled technical English, or durable technical documentation; route those tasks to tech-docs.
port-codebases
Plan, execute, review, and verify behavior-preserving codebase ports across programming languages, runtimes, frameworks, platforms, storage engines, or major APIs. Use when asked to rewrite or migrate an implementation while preserving semantics, mechanically translate a large body of code, replace a runtime or language, run a strangler or big-bang port, turn compiler and test failures into a migration queue, or organize AI-assisted porting with one or many agents. Scale the workflow to the available time, compute, and model budget without weakening correctness gates. Do not use for ordinary dependency bumps, small local refactors, or product redesigns disguised as a port.
pr-review
Review and maintain pull requests across GitHub, GitLab, Forgejo, Gitea, and other providers: inspect PRs, approve or request changes, handle feedback, fix valid findings, recover CI, keep branches current, or review caller-supplied context without taking provider action. Use when a user asks to review PRs, catch up on review work, maintain their own PRs, names a PR, requests a dry run, or delegates review analysis while retaining approval and delivery authority.
product-design
Plan, research, model, explore, prototype, and review digital product experiences. Use when turning product evidence or a provisional brief into a design brief; planning or synthesizing behavioral research to shape how the experience works; documenting a problem space, user expectations, or mental models; framing design opportunities; modeling objects, actions, relationships, journeys, and moments; creating information architecture, flows, wireframes, or prototype plans; designing or reviewing habit loops, triggers, rewards, investment, gamification, engagement, retention, or sticky experiences; or deciding how autonomy, learnability, fidelity, and visual character should shape an experience. Use for product and interaction design before or alongside implementation, especially when research, behavioral design, systems thinking, and interface craft must remain connected.
product-naming
Research, generate, screen, and shortlist names for products, software, services, companies, features, and internal initiatives. Use for naming or renaming work, multilingual name checks, spoken-name and spelling tests, domain and search-conflict research, preliminary trademark screening, naming scorecards, candidate shortlists, or a documented naming decision. Especially useful when a name must work across German and English or several European languages without sounding like a generic technology brand.
software-architecture
Assess, design, review, and evolve general software architecture with explicit system boundaries, responsibilities, data and integration contracts, quality attributes, operational concerns, and migration paths. Use when a user asks for software or system architecture, architecture options or review, service or module boundaries, monolith versus service decisions, scalability, reliability, deployability, operational readiness, performance objectives, load, soak, or stress objectives, workload scenarios, and capacity decisions, or non-frontend testing-strategy design such as the test pyramid, coverage goals, and which risks get which test types. Apply Twelve-Factor practices where they fit a long-running service; do not use for frontend-only architecture, codebase audit-only work, implementation plans, execution of an existing repository check, or recording an already-made decision when a narrower skill applies.
software-testing
Design, implement, diagnose, and verify focused non-frontend software tests for services, APIs, databases, async work, CLIs, and Rust. Use when asked to protect a behavior, invariant, regression, failure path, retry, authorization rule, migration, command-line contract, or flaky test; to diagnose test discovery, collection, runner, or framework configuration; to make a rule or state transition directly testable; to add a focused performance-regression guard; or to design, repair, or interpret a repository-native microbenchmark, comparative benchmark, or bounded end-to-end workflow benchmark. Prefer repository-native test conventions and real behavior over mock choreography. For browser, component, or React tests use effective-web. Do not use for visual, accessibility, or browser E2E testing; repository-wide coverage audits; testing-strategy design (use software-architecture); or load, soak, stress, and capacity methodology.
tech-docs
Design, write, update, and verify technical documentation for product and software users, operators, and contributors, including READMEs, setup and task guides, API and CLI references, migration notes, JSDoc, TSDoc, rustdoc, explanatory code comments, executable examples, and ASD-STE100 Simplified Technical English. Use when asked to create or improve technical docs, document a public interface or migration, write or review English technical text in STE or a controlled language, apply tekom-style rule-based writing or controlled technical German, align documentation with implementation, or validate docs against repository conventions. Do not use for general marketing copy; route repository-wide documentation audits and prioritization to codebase-improvement.
create-social-content
Create, rewrite, review, and adapt evidence-led social media content across X or Twitter, Threads, Bluesky, Instagram, Mastodon, and unspecified or multiple social platforms. Use for posts, replies, quote posts, threads, captions, resource shares, product or project updates, social content ideas, series or calendars, cross-platform repurposing, matching an authorized voice from authored examples, or checking whether an angle repeats recent content. Route LinkedIn-only post work to linkedin-posts and LinkedIn acquisition strategy to linkedin-social-selling.
data-systems
Design, review, and evolve reliable data models, datastores, transactions, consistency contracts, replication, partitioning, batch or streaming flows, and data migrations. Use for database or event-model decisions, read and write guarantees, concurrent updates, dual-write risks, replication lag, sharding or partition-key choices, data-pipeline semantics, schema evolution, backfills, cutovers, and recovery planning. Start from observed access patterns, invariants, load, failure consequences, and operational capability; do not introduce distribution, polyglot persistence, or event sourcing without a concrete driver.
market-research
Plan, conduct, analyze, and synthesize decision-led customer and market research. Use for research briefs and programs, recruitment and screeners, customer, user, buyer, win/loss, or churn interviews, contextual observation, surveys, transcript and support analysis, review and community mining, voice of customer, Jobs to Be Done, evidence-based personas, market and category landscapes, alternatives and competitor-customer evidence, market-size research, or traceable handoffs into product management, product design, product marketing, and pricing. Use when evidence must be gathered or assessed rather than invented to support a product, experience, or market decision.
marketing-writing
Plan, write, rewrite, edit, or critique persuasive marketing copy grounded in approved product and market evidence. Use for homepages, landing pages, product or service pages, pricing pages, campaign and launch copy, sales pages, emails, headlines, calls to action, value explanations, emotional resonance, objection handling, and conversion-focused copy revision. Use when the writing must help a specific reader understand a credible offer and take a proportionate next step without invented proof, pressure, or customer language.
nonfiction-writing
Plan, write, revise, or critique clear and persuasive nonfiction from supplied ideas and evidence. Use for articles, essays, newsletters, thought leadership, content marketing, engineering blog posts, technical articles, reports, case studies, professional narratives, public project pages, explanatory prose, and other factual writing; for turning notes into a draft; for improving structure, clarity, voice, rhythm, credibility, and calls to action without inventing facts; or for auditing formulaic, AI-sounding prose through observable patterns without guessing authorship.
originality-review
Audit a website, interface, campaign, document, media artifact, or code-backed experience against supplied references for originality risk, source overlap, and asset provenance. Use when asked whether work copies its inspiration; to compare text, brands, numbers, images, video, layout, motion, code, fonts, icons, or other assets; inspect current and historical files; check credits or licenses; recommend replacements; or make a release verdict. Produces evidence-backed risk findings, not a legal conclusion.
pricing-and-packaging
Research, design, review, and change pricing and packaging for software, services, and digital products. Use for willingness-to-pay research, pricing evidence, value metrics, pricing models, packages or tiers, entitlements, discounts, trials, usage allowances, price testing, or migrations for existing customers. Use when a team must connect customer value, buying behavior, product economics, and operational constraints without inventing market certainty or relying on a universal pricing formula.
product-marketing
Develop, review, and improve evidence-led product positioning, segmentation, category choices, messaging, proof, launches, sales enablement, and market learning. Use for positioning briefs, message architecture, claim and proof reviews, launch plans, sales narratives or battlecards, win/loss analysis, adoption learning, or cross-functional go-to-market alignment. Use when a team must turn stable product and customer evidence into market-facing choices without inventing customer language, differentiation, or certainty.
reference-analysis
Capture, inspect, compare, and translate supplied visual or interactive references into evidence-backed design and implementation specifications. Use for live websites, local HTML, screenshots, screen recordings, videos, prototypes, or reference packs when asked to reverse-engineer layout, visual systems, interaction, motion, responsive behavior, assets, or implementation requirements; compare several references; or turn inspiration into portable rules without copying its identity. Do not use for general internet research, product problem discovery, an originality audit, or the implementation itself.
rust-engineering
Implement, refactor, and review Rust crates and workspaces with explicit architecture, ownership, API, error, concurrency, unsafe, memory, and performance contracts. Use for Rust source changes, Cargo projects, lifetime or cloning decisions, public Rust APIs, crate/workspace boundaries, async Rust, unsafe code, FFI, allocation and data-layout choices, profiling, SIMD, atomics, parallelism, numeric conversions, or Rust-depth findings inside a code review that pr-review owns. Do not use for behavior-preserving ports, dependency-only updates, test-only work, documentation-only work, or merely running existing repository checks when a narrower skill owns the task.
typescript-engineering
Implement, refactor, and review server-side and general TypeScript with explicit type, module, async, error, and tooling contracts. Use for TypeScript source changes, type-system decisions (narrowing, assertions, discriminated unions, generics, any/unknown, runtime-boundary validation), public module and package API design, ESM/CJS and package.json exports, async and cancellation patterns, typed error handling, tsconfig and toolchain meaning, or the TypeScript-depth findings inside a code review that pr-review owns. Do not use for frontend, React, or browser work, behavior-preserving ports, dependency-only updates, test-only work, documentation-only work, or merely running existing repository checks when a narrower skill owns the task.
decision-records
Create, review, update, supersede, and audit Architecture Decision Records (ADRs) for durable project decisions. Use when a user asks for an ADR, decision log, architecture decision, design decision, communication or brand voice decision, or recorded rationale; when a cross-cutting technical, product, design, content, marketing, security, operational, or process choice must remain understandable across people, tools, and agent sessions; or when another skill identifies a decision whose undocumented rationale would otherwise drift. Preserve existing repository conventions and do not create skill-specific dot folders or private memory formats.
locale-typography
Apply and review locale-appropriate typography in visible prose for German, English, French, Dutch, Luxembourgish, European Spanish (es-ES), Italian, Danish, Norwegian, Swedish, Polish, Czech, and Croatian. Use when writing, editing, localizing, proofreading, or implementing text in Markdown, HTML, JSX, templates, UI copy, documents, or print layouts where quotation marks, punctuation spacing, dashes, apostrophes, non-breaking spaces, numbers, dates, currency, or hyphenation must match a supported language and region.
smart-dependency-updater
Research, select, introduce, group, implement, validate, and publish external dependency changes. Use when a user asks to add or choose a package, crate, action, image, SDK, or other versioned dependency; update or upgrade packages; replace Dependabot; make Renovate smarter; group dependency updates; create dependency PRs; assess changelog impact; modernize dependencies and related code; or adopt useful new APIs.
software-validation
Discover, execute, and report existing repository-native software checks. Use when asked to validate a change, run the repository's established checks against a change or package, run the applicable typecheck, static analysis, lint, format, test, benchmark, load, soak, stress, build, package, documentation, doctest, link, generated-reference, or example checks, or explain what validation evidence is still missing. Do not use to invent or install tooling, design new tests, choose architecture quality targets, prioritize repository improvements, or orchestrate delivery.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.