25 executable AI agent skills for debugging, planning, token efficiency, and security
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
A method for comparing the abilities of two AI agents or developer tools using documentation, source code, and hands-on tests. An AI agent is software that can carry out tasks through tools.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when signaling work status across autonomous sessions.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when needing to standardize descriptions across many skill files at once — change format, fix wording, or enforce a convention like 'Use when...' prefix.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
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.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when the context window is getting full and tasks need breaking down.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when verifying that tool commands actually executed after compaction.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when managing a long-term project across multiple Hermes sessions.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when setting up or extending Hermes Agent.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Structured multi-phase plan for improving Hermes Agent — IDE docs, release frequency, plugin marketplace, desktop app, and Rust performance.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when Hermes Agent needs X/Twitter search, public signal research, monitoring, or approval-gated account actions through the Hermes Tweet plugin.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use delegatetask 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.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
A decision framework that gathers advice from several roles and combines it into one recommendation. It supports both parallel opinions for a decision and a step-by-step pipeline for applying feedback.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when evaluating whether an open-source project fits our needs.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when understanding the relationship between OpenClaw Gateway and Hermes Agent.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when the user asks for a plan instead of executing work.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
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.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
A task-routing engine that chooses among several ways to perform an action and learns from the results over time using a local SQLite database.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
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.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Brake system that auto-stops the agent after N repeated failures, prevents token burning on loops.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when a skill SKILL.md is over 2000 words and needs trimming to the Superpowers standard of under 500 words.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
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.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when executing implementation plans with independent tasks in the current session.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
ChrisLamDev/hermes-core-skills
Skill Claude CodeCodex
Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: