全部 Skills

Design and build an official Apify integration for a company's product - workflow-automation apps (Zapier/n8n-style), AI agent plugins (coding-agent skills+MCP bundles or OpenClaw/Hermes-style harnesses), AI framework packages (LangChain/LlamaIndex-style), or direct application clients via apify-client. Use when planning, creating, or reviewing an integration that exposes Apify Actors, runs, datasets, or key-value stores inside another product.

Preview conservative tool-name translations and copy complete local skill bundles for manual adaptation to Google Antigravity.

Stop ineffective AI coding repair loops with stable failure fingerprints, a three-attempt budget, real-path proof, negative controls, and tested rollback.

Prepare required media inputs within an existing OD Next plan. Reuse capability evidence, acquire and measure assets efficiently, and resolve asynchronous jobs without removing required content or weakening quality standards.

Check whether the hub docs kept up with the four SDK repositories (tesseron-typescript, tesseron-rust, tesseron-python, tesseron-cpp) and the published hub packages. Use before or after an SDK release, when asked "are the docs stale", "did the docs keep up with the release", "which docs pin an old version", or as the release gate that backs the AGENTS.md rule that an SDK release PR is complete only after its hub docs PR merged.

Generate an approval-gated improvement PRD from a report and baseline, with evidence-backed what/why/value changes and measurable targets. Use for rebuild proposals. Don't use for task breakdown, coding, implementation, or unapproved persistence.

Generate phased tasks.md from an approved website PRD, with landing page first, measurable tasks, and collect/create asset tracking. Use for implementation planning. Don't use for coding, design review, unapproved PRDs, or direct deployment.

Generate a plain-language report from website-analyzer JSON and save it only after explicit approval. Use for non-technical summaries. Don't use for developer audits, raw SEO analysis, penetration testing, or unapproved persistence.

Generate a website-clone closure report comparing baseline analysis, builder metadata, planned tasks, and implemented results. Use after a completed rebuild. Don't use for live audits, ongoing monitoring, implementation, or speculative metrics.

Build an approved Vite/React/Tailwind plan, collect assets, verify static output, deploy to GitHub Pages, and emit metadata. Use for implementing tasks.md. Don't use for design review, planning, backend services, or unapproved specs.

Analyze a website's UI/UX, category, style, performance, surface security, and SEO; emit structured JSON. Use for URL audits or website-cloner input. Don't use for penetration tests, full SEO audits, or App Store ASO.

Build an improved website clone from a URL via 6-phase gated workflow (Vite/React/shadcn/Tailwind + GitHub Pages). Use for end-to-end site rebuilds. Don't use for single-phase work.

Scan a live site with isitagentready.com, then approve each step: triage the 0-5 agent-readiness score, write agent-ready-plan.md, file issues via /plan-to-issues. Don't use for applying llms.txt/SEO fixes (seo-ai-optimizer) or app-store ASO.

Review a product codebase and landing page against 32 viral principles and produce a Virality Score plus ranked fixes. Use to audit virality or prioritize growth. Don't use for SEO, ASO, copywriting, or code review.

Manage AI agents in tmux: spawn sessions, send messages, wait, capture replies, inspect fleets, and tear down safely. Use for tmux-hosted CLI agents. Don't use for SSH, GNU screen, or GUI apps.

Generate unit tests for untested branches and edge cases. Use when coverage is low, CI flags gaps, or a release needs hardening. Not for integration/E2E suites, framework migrations, or fixing production bugs.

Generate sprint-based development tasks from a PRD. Use when asked to create tasks or break down requirements. Don't use for PRD/TAD authoring or task execution.

Generate a Technical Architecture Document (TAD) from a PRD. Use when asked to design system architecture or define how a product is built. Updates tad.md and reports GitHub links. Don't use for PRD authoring, sprint tasks, or code implementation.

Create, evaluate, or improve Claude Code subagent files (.claude/agents/*.md) — the frontmatter + system prompt defining a delegatable specialist. Don't use for skills (skill-creator), CLAUDE.md/AGENTS.md (agent-config), or running an agent.

Audit and optimize websites for technical SEO, content SEO, and AI bot accessibility. Fixes meta tags, sitemaps, robots.txt, structured data, llms.txt, and GPTBot/ClaudeBot directives. Not for App Store ASO, paid search, or blog writing.

Install local-first security hardening: pre-commit secret detection, offline dependency scans, static analysis, reports, and gated free CI. Use when hardening repos or adding security hooks. Don't use for incident response or cloud security reviews.

Manage software releases end-to-end: bump version, generate changelog, tag, push, GitHub release, publish to PyPI/npm. Use when asked to ship, cut a release, or tag a version. Don't use for routine commits or marketplace publishing.

Generate Product Requirements Documents from `idea.md` and `validate.md` files. Use when asked to create or update a PRD. Don't use for TAD, sprint tasks, or raw idea validation.

Convert any phased plan file, or a conversation about what to build, into labelled GitHub issues under one tracking epic mapping each issue to its source task. No plan file required. Don't use for writing plans, resolving issues, or triage.

Transform a project into a professional open-source repository by adding LICENSE, README, CONTRIBUTING, CODE_OF_CONDUCT, SECURITY, and GitHub issue/PR templates. Don't use for documentation overhauls, landing-page generation, or registry publishing.

Run OpenCode in a docker-dev sandbox (SSH/gh on by default; --no-ssh/--no-github to isolate). Prints docker exec attach; kept until you confirm rm. Don't use for opencode.ai (opencode-runner), Herdr, or the app.

Run coding tasks via opencode using free cloud models. Use when asked to offload work to opencode.ai or run a free model. Don't use for local models (Ollama, LM Studio), Claude/OpenAI calls, or when Claude should do the work itself.

Resume a limit-blocked OpenCode session in a fresh sandbox: same project and agent setup, no host OpenCode config/token/key, attached in a tmux panel. Don't use for one-shot sandbox tasks (opencode-sandbox), opencode.ai (opencode-runner), or Herdr.

Optimize Ollama configuration for the current machine's hardware. Use when asked to speed up Ollama, tune local LLM performance, or pick models that fit available GPU/RAM. Don't use for LM Studio, llama.cpp, vLLM, or hosted-API LLM providers.

Generate professional SVG logos from project context: 7 brand variants plus a showcase HTML page. Use for product marks, wordmarks, icons, and favicons. Don't use for raster-only logos, illustrations, or full brand guidelines.

Generate landing pages with PAS, AIDA, or StoryBrand from a product brief or existing README. Use for sales copy, hero sections, CTAs, or README rewrites. Don't use for blog posts, UX audits, or HTML builds.

Run Herdr loops for one open GitHub issue (resolve→review→fix) or an existing PR (review→lazy fixer) until CLEAN. Don't use for plain resolution without review, review-only/no-fix requests, backlog automation, or merging.

Generate cross-platform install scripts for any software or library — a standalone install.sh runnable via a curl/wget one-liner with OS, arch, and package manager detection. Don't use for Dockerfiles, CI/CD pipelines, or one-off shell scripts.

Validate app/startup ideas with market, feasibility, commercial, and open-source competitor analysis. Use when asked to evaluate, validate, or score a product idea. Don't use for PRDs, go-to-market plans, or investor decks.

Manage AI agent fleets in Herdr: tile root + sub-agents in one tab, start/prompt/wait/read/monitor via the herdr agent CLI, steer any pane; `help` lists every operation. Use for Herdr fleets. Don't use for tmux, screen, or non-Herdr terminals.

Build production-grade frontend interfaces with distinctive aesthetics and working code. Use for UI components, pages, or frontend features. Don't use for backend/API work or usability-only audits.

Sync a GitHub fork with upstream while keeping unmerged feature branches and open PRs mergeable. Use for rebase on upstream, PR conflicts, integration main. Don't use for git init, releases, or non-fork repos.

Review UI usability using Steve Krug's principles and produce a scannable report. Use for UX audits of screenshots, URLs, or code. Don't use for brand critique, WCAG audits, or backend/API review.

Generate or update docs to match the code, citing each claim to path:line and asking on ambiguity; runbook docs also get a check-only validation script. Don't use for API-reference autogen (JSDoc/Sphinx), landing pages, or CLAUDE.md/AGENTS.md.

Generate diagrams as valid Excalidraw JSON — flowcharts, architecture, ER diagrams, mind maps, sequence diagrams, wireframes, C4 models, and more. Don't use for draw.io/Mermaid output, slide decks, or pixel-perfect brand graphics.

Generate professional diagrams as valid draw.io XML — flowcharts, architecture, C4 models, ER diagrams, sequence diagrams, mind maps, and swimlanes. Don't use for Excalidraw or Mermaid output, hand-drawn sketch styles, or slide decks/presentations.

Generate a diagram and route to the right engine — draw.io XML (precise, editable, C4, swimlanes) or Excalidraw JSON (hand-drawn, sketch, wireframes). One entry for flowcharts, architecture, ER, sequence, mind maps. Don't use for Mermaid or slides.

Configure pre-commit hooks and lean GitHub Actions for shift-left quality assurance. Use when adding or auditing CI/CD to maximize local test coverage and minimize CI cost. Skip for Terraform/K8s, deployment pipelines, or non-GitHub CI providers.

Set up or tune any dev machine, fresh or drifted, on macOS, Linux, or Windows: report what's missing, install only that, then fix PATH, duplicate runtimes, and shell config. Don't use for Dockerfiles, CI images, or single package installs.

Audit a stale, inherited, or messy codebase — deps, bugs, security, tests, CI, docs, UI/UX — then emit a phased, testable modernization plan. Read-only: plans upgrades, never applies them. Not for single-PR review, PRD-to-tasks, or UX-only audits.

Review or improve code — one skill, four modes: bug/security review (default), performance, clean-code audit, slop cleanup. Pass mode:review|perf|clean|cleanup or infer. Don't use for writing features or generating tests (use test-coverage).

Build production-quality CLIs with language detection and a five-step approval-gated workflow. Use when wrapping an existing module or app. Don't use for GUI/TUI apps, web APIs, or one-off shell scripts.

Check product and brand names for conflicts across trademarks, domains, social handles, and package registries. Returns a risk level and Proceed/Modify/Abandon recommendation. Skip for name brainstorming, logo design, or trademark filings.

Generate a commit message, stage all changes, and push to remote after scanning for secrets, large files, and protected-branch risks. Skip for opening PRs, code review, or cutting releases/tags.

Optimize App Store and Google Play listings via a 7-phase, plan-approval-gated ASO workflow (keyword strategy, metadata, localization). Don't use for web SEO, paid UA campaigns, or pre-submission compliance audits.