Top Agent Skills

Manage Planka Kanban projects, boards, lists, cards, and notifications through a command-line interface.

Build and maintain Raycast extensions using the Raycast API, covering UI components, data persistence, feedback, and restricted APIs like AI and Browser Extension.

Initializes, inspects, resumes, or migrates portable PWDEV Flow project state, routing requests to the appropriate workflow and creating or preserving configuration files.

Decomposes an approved specification into dependency-aware waves and atomic executable tasks with exact file scope, test-first actions, verification commands, and an execution gate.

Launches, inspects, and tears down parallel Codex phase fleets in isolated Git worktrees, with explicit approval for bypassing sandbox restrictions.

Delivers a small, bounded code change through inspection, a mini-plan, implementation, testing, review, and adversarial verification. Use for bug fixes, configuration changes, and features expected to touch no more than five files.

Designs an approval-gated feature specification from approved requirements, covering architecture decisions, component boundaries, quality constraints, and definition of done.

Diagnoses repository and PWDEV Flow health without modifying the project, producing an evidence-based scorecard and readiness report.

Curates durable project decisions, lessons, and conventions, supporting capture, listing, linking, superseding, and selection of memory entries.

Executes approved Flow plans one atomic task at a time with test-first implementation, fresh verification, blocker handling, and durable evidence.

Delegates a bounded repository task to an allowlisted external coding CLI through a guarded runner, with provider selection, timeout handling, and independent local review.

Guides a structured interview and repository research to clarify feature requirements, classify scope, and produce context artifacts for approval before design.

Inventory, archive, and summarize PWDEV Flow project history safely, without deleting artifacts or rewriting Git history.

Design precise, production-grade enterprise UI — dashboards, admin panels, SaaS interfaces, and data-heavy applications. Use this skill for professional software interfaces that need Jony Ive-level craft: clean, minimal, functional, with intentional personality. Do NOT use for creative landing pages, marketing sites.

Analyzes Claude Code session logs to report token usage, tool and skill rankings, and session search by prompt text.

Performs structured code reviews of git branches, tracking findings in a living document and optionally running deep architectural analysis with subagents.

Reviews and repairs risky or unclear code with minimal validated changes, running a fixed-point loop until the diff is clean across two consecutive review cycles.

Delivers measurement-driven performance optimization for latency, throughput, memory, and tail behavior, with correctness preservation and regression guards.

Analyzes a local codebase to infer its actual architecture from code-first evidence, producing a dominant architecture label, coexisting patterns, drift, and repo-fit advice for downstream agents.

Reviews development plans for gaps, hidden assumptions, critical misses, and XP violations, then presents prioritized findings for confirmation.

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

Routes product-discovery work into the right stage — opportunity brief, research, PRD, tickets, or outcome review — and hands off to the matching sub-skill.

Runs a structured product-discovery interview and publishes a two-page Opportunity Brief to Confluence, covering business objective, customer, problem, success metric, alternatives, assumptions, and open questions.

Audits AGENTS.md and CLAUDE.md files for bloat, redundancy, and ineffective rules, then runs A/B evals to prove which instructions are dead weight.

Loads Remotion best practices for React video creation, covering animations, composition setup, assets, audio, captions, sequencing, transitions, media metadata, Three.js, Tailwind, and rendering patterns.

Manage Hugging Face Hub resources via the `hf` CLI: download and upload models, datasets, and spaces; manage buckets, cache, collections, discussions, and inference endpoints; run SQL queries on datasets.

Creates, reads, edits, and converts Word documents (.docx) with formatting, tables, images, and tracked changes.

Creates, reads, edits, and converts PowerPoint presentations, including design guidance and quality assurance workflows.

Creates, edits, and analyzes spreadsheet files, applying professional formatting and ensuring zero formula errors.

Search the web, code, and company information using the free Exa MCP server, with no API key required.

Reference for building Tavily-powered search, extraction, crawling, and research into agentic workflows and RAG systems.

Guides the creation, iterative improvement, and evaluation of agent skills, including drafting, testing, benchmarking, and optimizing descriptions.

Applies curated color palettes and font pairings to presentation slide decks and other artifacts, with ten pre-set themes and the ability to generate custom themes on demand.

Writes internal communications such as status reports, leadership updates, 3P updates, company newsletters, FAQs, and incident reports using company-specific formats.

Applies Anthropic's official brand colors and typography to artifacts such as presentations, ensuring a consistent look and feel.

Deploys projects to Vercel as preview deployments, linking to git for automatic deploys, with fallback for unauthenticated environments.

Adds smooth, native-feeling animations to React apps using the View Transition API, covering shared elements, route changes, and list reordering with CSS-based control.

Search locally saved Codex session history stored in SQLite and session_index.jsonl, with filters for provider, time range, and archived status.

Automates Kiro CLI account onboarding with social Google or GitHub login through an HTTP proxy, including local SQLite auth cleanup, llm-access account import, proxy assignment, balance refresh, and student-tier verification.

Generates one-day Kiro credit usage reports from LanceDB usage events, with China-time windows, global totals, and account subset breakdowns.

Publishes Markdown articles and images into LanceDB via the sf-cli tool, syncs notes, infers missing metadata, and verifies results with local API checks.

Create high-quality bilingual detailed summaries for StaticFlow articles, focusing on evidence, reader value, and clear structure while allowing flexible writing style.

Writes mechanism-first technical implementation deep-dive articles that explain design intent, data flow, trade-offs, and operations, with code locations as supporting evidence.

Imports local Kiro CLI accounts into StaticFlow/llm-access by reading SQLite auth files and calling the local admin API, with proxy assignment and validation.

Batch-process pending LLM Gateway account-contribution requests through the admin API: preflight, validate, issue, patch, and refresh usage with deterministic proxy assignment.

Translates a Chinese article into English Markdown, generates bilingual detailed summaries, and writes the results back to LanceDB while preserving structure.

Safely land one or many topic branches onto main via GitHub PR: inventory, commit leftovers, push, open/update PR, wait for green CI, merge or squash (repo norm), sync local main, then delete local/remote branches only after main contains the work.

Registers an AI agent on the ClawSwarm hub, generates an identity card, and emits OADP discovery signals for cross-platform findability.

Orchestrates a full software delivery pipeline by sequentially loading and executing seven role-specific skills (BA, TechLead, PM, BE Dev, FE Dev, Tester, QA/QC), managing project configuration, task tracking, and gate checks.

Runs a structured bug-fix pipeline: scouts evidence, diagnoses root cause, applies minimal fixes, and reviews before committing.

Guides a structured planning pipeline for coding tasks, from scoping and research to plan creation, review, and handoff.

Runs and writes tests for a project, supporting unit, integration, and end-to-end scopes, plus two-pass TDD orchestration with quality-gate checks and regression sweeps.

Reads a project spec and writes one detailed plan file per SRS section, producing a complete blueprint for SRS generation.

Analyzes requirements and produces four artifact files: requirements.md, user-stories.md, acceptance-criteria.md, and business-rules.md, with optional loading from SRS workflow artifacts.

Generates frontend source code files and a PR description from BA, TechLead, PM, and BE artifacts, following a level-based implementation plan.

Reads BA and TechLead artifacts to produce a sprint plan, task breakdown, and story point estimates, creating one tracked todo per sprint task for live pipeline tracking.

Scans the projects/ directory and reports the pipeline phase completion status for each Virtual Team project, including validation errors and QA verdicts.

Derives a comprehensive test plan from user stories and acceptance criteria, then writes unit, integration, and end-to-end test cases. Flags issues in prior artifacts and declares UAT readiness.

Audits code quality against a shared contract, producing structured findings and blocking pipeline phases on critical issues without modifying code.

Generates a complete IEEE 830-compliant software requirements specification from approved plan files, producing one file per section with no word limit.