hermes-s6-container-supervision
Modify, debug, or extend the s6-overlay supervision tree inside the Hermes Agent Docker image — adding new services, debugging profile gateways, understanding the Architecture B main-program pattern.
plan
Plan mode: write an actionable markdown plan to .hermes/plans/, no execution. Bite-sized tasks, exact paths, complete code.
spike
Throwaway experiments to validate an idea before build.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
code-liveness-and-refactoring
Use when deciding whether code, columns, or pipeline stages are live, dormant, or stale; assessing deserialized config-schema changes; proving refactor parity; finding duplicated taxonomies; or reviewing package and infrastructure complexity. Covers data-flow and execution evidence, compatibility states, semantic parity, and risks of overclaiming dead code or harmless cleanup.
code-review
Guidelines for performing thorough code reviews with security and quality focus
dogfood
Exploratory QA of web apps: find bugs, evidence, reports.
simplify-code
Parallel 3-agent cleanup of recent code changes.
verification-and-evidence
Use when judging whether a fix, gate, test, deployment, durability claim, partitioning change, transfer, or monitor truly works. Covers false greens and mutation evidence, committed-tree and deployed-runtime proof, destructive-path and persistence checks, automation coverage, enforcement layers, and independent truth oracles.
nix-flake-dotfiles-maintenance
Use when modifying a multi-host Nix flake or dotfiles repo, especially host-specific inputs, overlays, lockfile scope, and evaluation checks.
rust-engineering
Use for Rust workspace engineering: dependency adoption and feature unification, replacing in-house layers with crates, borrowed/zero-copy decoding and honest benchmarks, uv-built Rust extensions, CI gates, deletion refactors, and multi-crate commit boundaries.
terminal-multiplexer-workflows
Use when answering, configuring, or troubleshooting terminal multiplexer workflows such as Zellij/tmux pane, tab, floating pane, grouping, keybinding, and CLI-action behavior.
workstation-and-agent-tooling
Use for personal workstation and agent-runtime tooling: Hermes profiles and Nix/Home Manager daemon configuration, native desktop popups, Waybar and Neovim runtime issues, interactive TUI and agent-harness testing, notebook kernels and FIM completions, skill packaging, and secure remote secret installation.
safe-git-rebase-with-guards
Perform a git rebase safely when the branch may have uncommitted WIP, poisoned rerere cache, or a concurrent actor. Use for any non-trivial rebase/linearization in a shared repo or git worktree where conflict markers, WIP loss, or baked-in corruption are risks.
stacked-issues
Implement multiple GitHub issues sequentially as stacked branches in separate worktrees, with an implementer sub-agent and an independent reviewer sub-agent per issue. Use when the user gives you two or more dependent issues and asks for them to be implemented in order, or says "stacked branches", "sequential issues", "issue chain", "do these in worktrees", or describes a parent epic with child issues that build on each other. Also reach for this whenever the user wants implementation and verification done by separate agents.
stacked-prs
Push local branches and create stacked PRs. Analyzes branch topology, pushes, creates PRs with correct base branches, and resolves merge conflicts. Use when you have a chain of local branches to turn into stacked PRs.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
using-superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
requesting-code-review
Use when completing tasks, implementing major features, or before merging to verify work meets requirements
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
codex
Delegate coding to OpenAI Codex CLI (features, PRs).
manage-dotfiles
Manage dotfiles and keep synced with external directories. Use on Linux / macOS systemswhen thetre are external connfigs which are being imported into the dotfiles, or when stored dotfiles need to be brought outside to the XDG environment.
analyzing-backtests
Analyzes algorithmic trading backtest results from Jupyter notebooks and generates summary reports. Use when the user wants to analyze or summarize backtest notebooks.
data-juicer
Primer for using the data-juicer Python library (also written `datajuicer` or `DJ`) — a YAML-driven, OP-based system for cleaning, filtering, deduplicating, transforming, and synthesizing text and multimodal data for foundation models. Use this skill whenever the user mentions data-juicer, DJ, dj-process, dj-analyze, "DJ format", building data recipes / YAML pipelines for LLM training data, or writing custom Filter / Mapper / Deduplicator / Selector / Aggregator / Grouper operators ("OPs"). Also reach for it when the user is putting together a data preprocessing pipeline for LLM pre-training, post-tuning, or multimodal datasets and DJ would be a natural fit, even if they haven't named the library yet — flagging DJ as an option is often the most helpful move.
package-skill
Package a Claude Code skill directory into a distributable .skill file. Use when the user wants to export, package, bundle, zip, or distribute a skill. Triggers on mentions of .skill files, packaging skills, exporting skills, or sharing skills.
brainstorm
>-
feature-brainstorm
Multi-phase brainstorming for complex feature implementations using parallel sub-tasks. Use when the user asks to brainstorm, design, or plan a complex feature, wants to explore implementation approaches, or needs architectural analysis before coding. Triggers on phrases like "brainstorm feature", "design implementation", "explore approaches", "plan architecture", or "how should we implement".
conventional-commits
Commit changes in a git workspace using the Conventional Commits specification. Use when the user asks to commit, stage, or save changes to git, or mentions "conventional commits". Analyzes staged/unstaged changes, groups related modifications, generates properly formatted commit messages, and commits files separately or together as appropriate. Confirms with user when commit ordering is ambiguous.
spotify
Spotify: play, search, queue, manage playlists and devices.
manage-dotfiles
Manage dotfiles and keep synced with external directories. Use on Linux / macOS systemswhen thetre are external connfigs which are being imported into the dotfiles, or when stored dotfiles need to be brought outside to the XDG environment.
media-transfer-to-te-amo
Use when copying TV media onto /mnt/Te_Amo and the imported show must be reshaped to match the nested TV Shows library layout on Te_Amo.
te-amo-tv-show-layout
Canonical folder and filename shape for TV shows stored under /mnt/Te_Amo/TV Shows.
apple-notes
Manage Apple Notes via memo CLI: create, search, edit.
apple-reminders
Apple Reminders via remindctl: add, list, complete.
findmy
Track Apple devices/AirTags via FindMy.app on macOS.
imessage
Send and receive iMessages/SMS via the imsg CLI on macOS.
macos-computer-use
|
agent-skill-library-governance
Use when inventorying, deduplicating, categorizing, centralizing, or migrating skills across Claude Code, Codex, Pi/shared agents, OMP, Hermes, or similar agent runtimes. Distinguishes authoritative user-managed skills from system bundles, plugin caches, memories, backups, and symlink aliases; selects canonical full bundles and produces a collision-aware migration map.
claude-code-internals-inspection
Inspect installed Claude Code internals and official plugin recreations to locate prompts, output styles, built-in strings, and migration hooks.
claude-code
Delegate coding to Claude Code CLI (features, PRs).
codex
Delegate coding to OpenAI Codex CLI (features, PRs).
coding-agent-output-styles
Find, extract, and port coding-agent output style prompts across Claude Code, Pi, and OMP.
Page 4 of 8 · 357 results