JasonxzWen
UserRelease-oriented agent skill hub and CLI for analyzing repos, installing high-signal Codex/Claude Code/OpenCode skill profiles, and safely tracking managed files.
Categories
Indexed Skills (43)
clone-website
Load when the user explicitly asks to clone, reverse-engineer, or rebuild a website they own or are authorized to reproduce; do not load for generic redesign, inspiration, scraping, phishing, impersonation, or copying third-party brands.
design-taste-frontend
Load when a workflow-router-selected owner workflow needs anti-template frontend visual direction, design-read calibration, or pre-flight critique for landing pages, portfolios, marketing pages, or redesigns; do not load for dashboards, data tables, multi-step product UI, routine frontend logic, HTML reports, slide decks, or generic code explanation.
stop-slop
Load when the user asks to draft, edit, or review English prose for AI-writing tells; do not load for code explanation, Chinese output, technical specs, or routine status reports.
source-to-insight-blog
Load when turning an external article, blog, release note, interview, or report into a source-backed insight blog with Chinese fidelity, media references, an effective-interact summary layer, and project-iteration review; do not load for ordinary summaries, full copyrighted reposts, or production site design.
agent-introspection-debugging
Load when a workflow-router-selected owner workflow needs agent run, tool loop, context drift, or recoverable harness/tool failure debugging; use diagnose for product/runtime bugs.
coding-standards
Load when a workflow-router-selected owner workflow needs cross-project code quality conventions; use frontend-patterns or security-review for narrower framework or risk guidance.
compound-code-review
Load when a workflow-router-selected owner workflow needs Compound Engineering-inspired code review for deep pre-PR, CE-style, or multi-perspective review with structured findings, lenses, confidence, and fix routing; skip ordinary verification.
diagnose
Load when a workflow-router-selected owner workflow needs hard bugs and performance regressions, failing commands, hard-to-reproduce behavior, or unknown root causes diagnosed; use agent-introspection-debugging instead for agent/tool harness failures.
documentation-lookup
Load when a workflow-router-selected owner workflow needs current library, framework, SDK, API, CLI, or cloud-service documentation; fetch docs instead of relying on training data or ordinary repo evidence.
e2e-testing
Load when a workflow-router-selected owner workflow needs durable Playwright E2E suites, Page Object Models, fixtures, CI browser tests, or flaky-test strategy; use webapp-testing for one-off local inspection.
feynman-learning-coach
Load when a workflow-router-selected owner workflow needs cases where the user explicitly wants to learn, study, prepare for an exam/interview, build a syllabus, or use Feynman teach-back checks; do not load for routine implementation or one-off facts.
frontend-design
Load when a workflow-router-selected owner workflow needs polished product UI, web pages, landing pages, dashboards, React components, HTML/CSS layouts, or styling; skip routine frontend logic and reports.
frontend-patterns
Load when a workflow-router-selected owner workflow needs React or Next.js frontend logic, component patterns, state, forms, routing, accessibility, or responsive behavior; use frontend-design for visual direction.
frontend-slides
Load when a workflow-router-selected owner workflow needs an HTML presentation, slide deck, talk/pitch slides, or PPT/PPTX-to-web conversion; use effective-interact for findings or handoff reports.
grill-me
Load when a workflow-router-selected owner workflow needs cases where the user says grill me, asks to be challenged, or wants assumptions surfaced through a one-question-at-a-time interview; do not use for routine implementation.
mcp-builder
Load when a workflow-router-selected owner workflow needs MCP server design, build, review, testing, tool schema, resource, or prompt work; skip ordinary REST clients and non-MCP integrations.
openspec-apply-change
Load when a workflow-router-selected owner workflow needs to implement or continue an existing OpenSpec change; use sdd-workflow for default non-OpenSpec implementation.
openspec-archive-change
Load when a workflow-router-selected owner workflow needs to archive a completed OpenSpec change after implementation and spec sync decisions are resolved.
openspec-explore
Load when a workflow-router-selected owner workflow needs explicit OpenSpec exploration, discovery, or requirement clarification; use sdd-workflow for default change alignment.
openspec-propose
Load when a workflow-router-selected owner workflow needs an explicit OpenSpec proposal with design, spec deltas, and tasks; use product-capability for ordinary implementation contracts.
prototype
Load when a workflow-router-selected owner workflow needs a throwaway prototype, state-model sanity check, UI variant, mock interaction, or playable design; do not use for production feature work.
security-review
Load when a workflow-router-selected owner workflow needs security-sensitive code, auth, user input, secrets, API endpoints, payments, injection risk, or unsafe IO reviewed; use compound-code-review for broader review.
slack-gif-creator
Load when a workflow-router-selected owner workflow needs to create, optimize, or validate an animated GIF for Slack emoji or messages; skip static images, video editing, and non-Slack animation.
tdd-workflow
Load when a workflow-router-selected owner workflow needs implementing features, fixing confirmed bugs, or refactoring production code with tests through red-green-refactor; diagnose first for unknown root causes and prototype for throwaway exploration.
theme-factory
Load when a workflow-router-selected owner workflow needs a coherent visual theme for slides, docs, reports, HTML artifacts, or landing pages; skip product UI implementation and accessibility review.
verification-loop
Load when a workflow-router-selected owner workflow needs final build, typecheck, lint, test, diff, smoke, and artifact checks before declaring completion; use diagnose while root cause is unknown.
web-artifacts-builder
Load when a workflow-router-selected owner workflow needs complex standalone React/Tailwind/shadcn browser artifacts with state, routing, or bundled components; use effective-interact for reports and frontend-design for production UI.
webapp-testing
Load when a workflow-router-selected owner workflow needs one-off local web app inspection with Playwright, screenshots, console logs, or UI issue reproduction against a dev server; use e2e-testing for durable suites.
claude-api
Load when a workflow-router-selected owner workflow needs Claude API or Anthropic SDK build, debug, migration, or tuning work; skip provider-neutral, OpenAI, or non-Anthropic model work.
doc-coauthoring
Load when a workflow-router-selected owner workflow needs to collaboratively draft, restructure, or reader-test docs, PRDs, RFCs, proposals, specs, or decision records; skip implementation itself.
handoff
Load when a workflow-router-selected owner workflow needs to hand off current work, compact a conversation for another agent/session, or create restart notes; do not load for visual HTML repo reports.
internal-comms
Load when a workflow-router-selected owner workflow needs internal communications such as status reports, leadership updates, 3P updates, newsletters, FAQs, incident reports, or project updates; skip public marketing copy.
skill-creator
Load when creating, updating, adapting, or evaluating a standard agent skill; do not load for ordinary documentation edits or one-off prompt advice.
web-design-guidelines
Load when a workflow-router-selected owner workflow needs UI, UX, accessibility, or web interface guideline compliance review; use frontend-design when creating or changing production UI.
hub-maintenance-workflow
Load when workflow-router selects the harness-hub-maintenance state for Harness Hub source evaluation, personal workflow distribution, routing overlay, capabilities, npm lifecycle, or managed update/remove behavior; preserve local adaptations and upstream skill bodies.
sdd-workflow
Load when workflow-router selects the sdd-change state for feature, bug fix, refactor, product/spec change, or implementation work; run SDD-first lifecycle with embedded TDD.
effective-interact
Load when agent pauses to report relatively complex information needing Chinese-first clear complex communication, alignment, multi-option choice, status/incident, long-task fact ledgers, implementation plans, reviews, maps, explainers, evidence, risks, validation, or handoff; choose plain text/Markdown/visual Markdown/HTML by decision cost; do not load merely because answer is long; skip trivial chat/bundled apps.
product-capability
Load when a workflow-router-selected owner workflow needs an implementation-ready capability plan with product constraints, invariants, interfaces, unresolved decisions, and acceptance boundaries before coding.
workflow-router
Load when a non-trivial request needs intent recognition before work starts; classify it into exactly one workflow owner, or ask a clarification; do not load for explicit owner-skill invocations, trivial chat, or execution steps already routed.
answer-workflow
Load when workflow-router selects the question state for read-only explanation, evidence lookup, feasibility, or comparison; answer from evidence and do not edit files unless rerouted.
delivery-workflow
Load when workflow-router selects the delivery state for accepted validation closeout, cleanup, handoff, release notes, environment reset, or reporting; do not start new scope.
diagnosis-workflow
Load when workflow-router selects the diagnosis state for a failing command, runtime bug, flaky behavior, performance regression, or agent/tool failure; reproduce or bound the symptom before fixing.
review-workflow
Load when workflow-router selects the review state for code, plan, release, UI, or security review; produce findings first and do not implement fixes unless the user explicitly redirects.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.