Latest Agent Skills

Build ultra-fast web APIs and full-stack apps with Hono — runs on Cloudflare Workers, Deno, Bun, Node.js, and any WinterCG-compatible runtime.

Head of product — orchestrate the product team, write briefs, plan initiatives, hand off to Apex.

Language-specific super-code guidelines for bash.

Records Clean Room initialization preferences, separated artifact locations, model policy, schema profile, and clean-safe rule defaults before a clean-room run starts or resumes.

Fast CLI/Python queries to 20+ bioinformatics databases. Use for quick lookups: gene info, BLAST/BLAT, viral sequence downloads, AlphaFold structures, enrichment analysis, OpenTargets, COSMIC, CELLxGENE, and 8cube mouse specificity/expression data. Best for interactive exploration and simple queries. For batch processing or advanced BLAST use biopython; for multi-database Python workflows use bioservices.

Database management, forms, reports, and data operations with LibreOffice Base.

Applies TRIZ cross-domain analogical reasoning to find solutions from adjacent fields. Use when stuck on a problem and needing inventive perspectives.

Expert tmux session, window, and pane management for terminal multiplexing, persistent remote workflows, and shell scripting automation.

Triggered by "tidy up", "clean up transactions", "categorize uncategorized", "organize my transactions"

Turn vague intent into a precise, executable spec in five phases. (gstack)

Use when all plan tasks are done and green to review, archive planning artifacts, and ask how to finish.

A playful, arcade-inspired interface for games — built on the VT323 pixel typeface, hard-edged 0px corners, chunky pill buttons that physically press into solid offset blocks

Write a markdown plan to .hermes/plans/; no execution.

Boot the session, load context from the vault, and surface what matters

Runs repeatable AI work as checked, budgeted workflow files.

Electric neon glow effects with high-contrast color pairings for bold, attention-grabbing interfaces.

Use only when the user explicitly asks to run, set up, update, re-mine, or deepen Emulo from real local AI coding-session history.

Unified math capabilities - computation, solving, and explanation. I route to the right tool.

AI-native publishing system: autonomous multi-phase workflows from ideation to export. Fiction, non-fiction, and technical books. Trigger: /velith or book-related requests.

Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now or I'm stuck or I don't know what to do

Cirq is Google Quantum AI's open-source framework for designing, simulating, and running quantum circuits on quantum computers and simulators.

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

One-shot lifecycle command that chains init → baseline → spawn → eval → merge in a single invocation. Use when the user runs /hub:run or asks to execute a full AgentHub competition end-to-end.

Language-specific super-code guidelines for php.

Run the full autonomous shipping pipeline end-to-end, hands-off with no check-ins: plan, implement, review and fix, commit, push a branch, open a PR, and watch CI to green. Use only when the user explicitly asks to build or ship something autonomously all the way to an open PR, or invokes lfg directly — it pushes and opens a PR without stopping. Not for in-the-loop work where the user reviews each step: use ce-plan to plan, ce-work to implement a plan, ce-debug to fix a bug, or ce-commit-push-pr to commit and open a PR for existing changes.

Meta-skill workflow orchestrator for bug investigation and resolution. Routes to debug, implement, test, and commit based on scope.

DAX performance optimization for semantic models. Automatically invoke when the user asks to "optimize DAX", "fix slow DAX", "DAX performance", "tune a measure", "debug a measure", "DAX anti-patterns", or mentions slow queries, server timings, or DAX authoring.

Language-specific super-code guidelines for cpp.

Bitbucket CLI for Data Center and Cloud. Use when users need to manage repositories, pull requests, branches, issues, webhooks, or pipelines in Bitbucket. Triggers include "bitbucket", "bkt", "pull request", "PR", "repo list", "branch create", "Bitbucket Data Center", "Bitbucket Cloud", "keyring timeout".

Analyze GitHub Actions failures and identify root causes

Turns a rough request into working software via a governed build loop: align first, plan, then iterate one task at a time with deterministic backpressure and holdout-scenario judging.

> 强化高能动性和高压闭环执行的行为技能。适用于连续失败、原地打转、空口完成、 把问题甩给用户、没搜就猜、修完就停等场景，也支持手动通过 /pua 进入核心模式。

Guide building a minimum viable product the minimalist entrepreneur way — manual first, then processized, then productized. Use when someone is ready to build their first product or struggling with scope.

Read-only EVM client: wallets, tokens, gas across 8 chains.

| Use when reviewing an incoming GitHub pull request — runs the multi-level (L1-L5) audit against the PR's real diff range, posts findings as one batched review (inline, summary, or local-only), offers the standard fix chain on NEEDS_FIX, and optionally merges. The maintainer-side counterpart to /hyperflow:issue. Trigger with /hyperflow:pr, "review PR #N", "review this pull request <url>", "audit the PR", "check this contribution".

Language-specific super-code guidelines for go.

Expert jq usage for JSON querying, filtering, transformation, and pipeline integration. Practical patterns for real shell workflows.

Jenkins CLI for controllers. Use when users need to manage jobs, pipelines, config.xml, runs, logs, artifacts, credentials, nodes, or queues in Jenkins. Triggers include "jenkins", "jk", "pipeline", "build", "job create", "job config", "config.xml", "run logs", "jenkins credentials", "jenkins node".

Language-specific super-code guidelines for c.

Runs an interactive command in a separate window and waits for it to close. Invoked only when another skill explicitly calls for it, never on its own.

Use when analyzing Claude Code conversation logs to find patterns in repeated user instructions that could become skills. Ask for date range first.

Use when a skill needs the user to interactively review code changes in revdiff mid-workflow — working changes, staged changes, or a specific commit — then read their annotations back. Takes a review mode.

Use when writing or editing a code comment or a documentation block, and when reviewing the comments and documentation in a diff before presenting it. Decides what stays in the source, what moves to reference documentation, and what gets deleted.

Use when a skill needs the user to interactively edit a file in Neovim mid-workflow, then read their changes back. Takes a window name and the file to edit.

Use when writing tests for TypeScript or JavaScript code in frameworks such as Jest, Vitest, Bun, etc.

Contains interactive interaction scripts. Use when another skill explicitly instructs invoking this one. Do not invoke on your own initiative.

Temporarily turn off the requirement that pending changes be reviewed before committing in the current herdr workspace.

Turn interactive commit reviews back on for the current herdr workspace.

Use when writing or editing a React component. Covers preferred patterns for functional components, prop types, and styling.

Use when working with a stack of GitHub pull requests — creating branches, keeping the stack in sync, or merging in order. Covers Git Town setup, PR targeting, rebasing, and landing the stack.

Use when creating, editing, evaluating, testing, or verifying ANY skill or skill-related file (SKILL.md, skill resources, skill scripts, or skill assets). If you're asked to evaluate or test a skill's effectiveness, use this skill.

Use when writing or modifying tests for React hooks.

Use when setting up a new personal project, or when deciding which root file a piece of documentation, configuration, environment variable, or agent instruction belongs in. Covers the standard root files and what each one owns. Does not cover source code layout.

Use when a finished, reviewed branch is committed and needs to be merged into the default branch in a repo that integrates directly to `main` (not via pull request).

Use when writing or modifying tests for Ink (terminal UI) components.

Use when writing or modifying tests in a Bun project

Use when publishing or releasing a new version of an npm/pnpm/yarn/bun package to the registry. Covers package-manager detection, semver bump selection, tagging, pushing, scoped-package access, authentication, and one-time passwords (OTP).

Use when merging a single GitHub pull request. Handles pre-flight checks, waits for CI, and executes the merge with the repo's default method or merge queue.

Invoke when the agent's conversational replies have gotten too long or wordy and the user wants shorter answers for the rest of the conversation.

Use when writing a Ruby script. Covers the template, conventions, and required patterns.