Design and architecture skill for ADRs, RFCs, design reviews, and ripple-effect analysis. Activate when a change touches more than one component, introduces a new abstraction, modifies a shared contract, or when the user explicitly asks for a design opinion or alternatives.
Implementation skill for writing, modifying, and refactoring code. Activate by default for any coding task that does not warrant the architect skill. Optimized for parallelisable execution, fast feedback loops, and minimal surface area per change.
Documentation skill for ADRs, READMEs, in-code docstrings, and reference material. Activate when the user asks for documentation, when a public contract changes without docs, or when an ADR is needed per the architect skill's output. Optimized for documents that age well.
Practitioner-grade reference knowledge for modern frontend development. Covers HTML semantics, CSS custom properties and design tokens, Tailwind CSS, WCAG 2.1 AA accessibility baseline, Core Web Vitals, asset optimization, and framework-agnostic JavaScript baseline. Activate when authoring or reviewing HTML, CSS…
Deep, practitioner-grade knowledge of GitHub Actions for authoring, reviewing, hardening, and debugging workflows. Activate when reading or writing any file under .github/workflows/, when diagnosing a failing pipeline, when reviewing a CI change in a pull request, or when designing reusable / composite actions. Covers…
Deep, practitioner-grade knowledge of GitLab CI/CD for authoring, reviewing, hardening, and debugging pipelines. Activate when reading or writing a .gitlab-ci.yml, when reviewing a CI change in a merge request, when designing runners/executors or reusable CI/CD Components, or when migrating to GitLab CI from another…
IDEA stage lifecycle skill for structured idea-convergence. Activate before a SPECS session whenever multiple competing, overlapping, or complementary proposals must be resolved first. Supports three governance modes (solo, unanimity, vote) and produces one or more SPECS issues as output.
Create and populate a new expertise (role) file under config/expertise/ through a guided interview. Activate when an adopter wants to add a domain-expertise context profile for a role the catalog does not yet cover. Collects the role's responsibilities and key practices and writes a conformant config/expertise/ .md…
Build your personal profile (config/PROFILE.md) through a guided interview. Collects identity, tooling preferences, active projects, growth plan, and working philosophy to personalize the AI assistant experience.
Customize the agent identity file (config/SOUL.md) through guided conversation. Walk the user through each section of the SOUL-E framework (Stance, Origin, Understanding, Lineage, Error Handling) to craft a personalized agent personality.
Create and populate a new team file under config/teams/ through a guided interview. Activate when an adopter wants to add a per-team context and configuration profile. Collects the team's mission, technology stack, and development practices and writes a conformant config/teams/ .md, refusing to silently overwrite an…
Pull request and logbook composer. Activate when opening a PR, updating a PR description, or appending to a logbook issue. Produces titles, bodies, test plans, and logbook entries that conform to the project's AGENTS.md conventions.
Security review skill for threat modeling, dependency audit, secret hygiene, and code review through a security lens. Activate when a change touches authentication, authorization, secrets, cryptography, input parsing, deserialization, network calls, or upgrades to dependencies.
Specification authoring skill for the SPECS stage of the ADR-0010 lifecycle. Activate as step 0 of any non-trivial ticket — before any architect, developer, or tester — to qualify the user intent and emit exactly one Markdown spec file under /specs/ conforming to docs/spec-format.md. Mode-aware (FULL / INTERMEDIATE /…
Test authoring and test-strategy skill. Activate when writing new tests, planning a test strategy, enumerating edge cases for a feature, or reviewing whether a change has adequate coverage. Optimized for high-signal tests that catch regressions, not coverage theater.
Web test automation skill. Activate when writing Playwright or RobotFramework tests, auditing page conformity or accessibility, authoring test scenarios, or running regression passes on a web application.
WCAG 2.1 Level AA compliance auditor. Runs an automated baseline scan, then manually verifies keyboard navigation, color contrast, interactive element accessibility, image alt text quality, ARIA correctness, and motion preferences. Produces a structured findings report (violation → warning → informational). Does not…
Runs WCAG 2.1/2.2 (AA/AAA) compliance checks on a page or user flow using axe-core. Reports violations by impact level with remediation guidance and outputs a CI-ready test suite.
Specialist implementer for Astro projects. Scaffolds and configures Astro projects, implements pages/layouts/components, wires Content Collections, configures integrations, handles deployment, and diagnoses build failures. Receives tokens from designer, copy from copywriter, and hands off to seo-specialist and…