ChrisLamDev/hermes-core-skills

hermes-tweet

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

原文语言：英语

router-learning-system

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。

autonomous-work-signaling

Use when signaling work status across autonomous sessions.

原文语言：英语

batch-skill-description-standardization

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

原文语言：英语

checkpoints-and-rewind

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.

原文语言：英语

context-aware-task-decomposition

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

原文语言：英语

context-compaction-verification-and-recovery

Use when verifying that tool commands actually executed after compaction.

原文语言：英语

cross-session-execution-framework

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

hermes-agent

Use when setting up or extending Hermes Agent.

原文语言：英语

hermes-improvement-multiphase-plan

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

原文语言：英语

multi-agent-browser-text-extraction

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.

原文语言：英语

multi-role-synthesis-framework

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。

open-source-adaptation-pattern

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

openclaw-hermes-arch

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

原文语言：英语

plan

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

原文语言：英语

requesting-code-review

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…

原文语言：英语

security-hardening-checklist

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.

原文语言：英语

self-regulation-brake-system

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

原文语言：多语言混合

skill-slimming-strategy

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

原文语言：英语

spec-driven-development

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.

原文语言：英语

subagent-driven-development

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

原文语言：多语言混合

systematic-debugging

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

原文语言：英语

test-driven-development

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

原文语言：英语

think-tool

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,…

原文语言：英语

token-efficiency

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.

原文语言：英语

writing-plans

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

原文语言：英语