hermes-core-skills

Use when Hermes Agent needs X/Twitter search, public signal research, monitoring, or approval-gated account actions through the Hermes Tweet plugin.

Router Learning System — 越用越聰明嘅任務路由引擎。 每個 task 有最佳 path，Router 自動記錄經驗、動態調整、跳過爛 path。

Use when signaling work status across autonomous sessions.

Use when needing to standardize descriptions across many skill files at once — change format, fix wording, or enforce a convention like 'Use when...' prefix.

Use before making irreversible changes (deleting files, destructive git operations, large refactors). Use when you need the ability to roll back if something goes wrong. Use at the start of any task that modifies multiple files.

Use when the context window is getting full and tasks need breaking down.

Use when verifying that tool commands actually executed after compaction.

Use when managing a long-term project across multiple Hermes sessions.

Use when setting up or extending Hermes Agent.

Structured multi-phase plan for improving Hermes Agent — IDE docs, release frequency, plugin marketplace, desktop app, and Rust performance.

Use delegate_task with multiple browser-equipped sub-agents to extract verbatim text from Chinese academic/religious websites with JavaScript-heavy tree navigation. Covers coordination patterns, site-specific navigation, error recovery, and QA verification.

Use when Chris wants multiple perspectives on a design/feature decision and then a final integrated verdict. 多角色各自俾建議 → 終極角色做篩選整合，避免單一角度的盲點。

Use when evaluating whether an open-source project fits our needs.

Use when understanding the relationship between OpenClaw Gateway and Hermes Agent.

Use when the user asks for a plan instead of executing work.

Use when requesting a code review before pushing changes. Pre-commit verification pipeline — static security scan, baseline-aware quality gates, independent reviewer subagent, and auto-fix loop. Use after code changes and before committing, pushing, or opening a PR.

Use when handling user input, authentication, data storage, or external integrations. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services.

Brake system that auto-stops the agent after N repeated failures, prevents token burning on loops.

Use when a skill SKILL.md is over 2000 words and needs trimming to the Superpowers standard of under 500 words.

Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.

Use when executing implementation plans with independent tasks in the current session

Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.

Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.

Use when facing a complex decision, multiple possible approaches, or before making irreversible changes. Use when the best course of action is not obvious and requires reasoning before acting. Use before running destructive operations, before large refactors, or when you catch yourself rushing.

Use when context is getting large, when working on long sessions, or when you notice token consumption is high. Use before dispatching subagents, before reading large files, and during context compaction.

Use when the user asks for a plan instead of executing work.