Menu
Skills neste repositório
O SkillsMP coletou 1.242 skills de Undermybelt/hermes-skills. Abra uma skill para revisar a origem e os detalhes.
Undermybelt/hermes-skillsMostrando 40 de 1.242 skills coletadas.
Use when Codex feels slow or bloated, when local sessions/logs/worktrees/config have grown over time, or when a user wants safe maintenance for Codex Desktop/CLI state. Provides a read-only report by default, backs up before applying changes, archives instead…
Idioma do texto original: inglês
Wrap an existing standalone script or replay flow into a typed app adapter/orchestrator with minimal drift. Use when a repo already has working legacy automation that must be integrated into a new architecture without rewriting the old script first.
Idioma do texto original: inglês
Use Google Magika for fast ML-based file-type detection from file bytes, not just extensions or MIME. Use when the user needs reliable file identification, suspicious upload triage, content-type validation, malware-prep filtering, or bulk file classification.
Idioma do texto original: chinês
Add and validate market-specific frame-feature label forks in ict-engine when raw pre-Bayes labels are wrong even though factor signal quality is strong.
Idioma do texto original: inglês
Use when evaluating or absorbing ideas from math-formalization agents such as MathCode into Hermes workflows. Activate when a task involves theorem proving, reusable theorem/axiom stores, subgoal decomposition, proof planning, Lean feedback loops, or…
Idioma do texto original: inglês
Route newly learned information into the right Hermes layer: repo doc, skill, memory, or session_search/L4. Use when deciding where a fact, workflow, correction, or task artifact should live after execution.
Idioma do texto original: inglês
全面清理 Hermes 记忆层 + skills 目录 + 路由引用。 当用户说"记忆太臃肿"、"清理记忆"、"优化记忆"、"skills太多"、"磁盘满了"时触发。
Idioma do texto original: chinês
Use when Hermes needs a local external memory layer via MemPalace, or when a user asks to install, isolate, validate, or MCP-connect MemPalace. Activate when you need durable verbatim searchable memory outside Hermes' small built-in memory budget.
Idioma do texto original: inglês
Debug Node.js via --inspect + Chrome DevTools Protocol CLI.
Idioma do texto original: inglês
Map an academic paper or formalization repo to concrete, implementable engineering changes in a trading/research engine. Avoid math gimmicks; focus on regime fusion, scoring, gating, and feature construction.
Idioma do texto original: inglês
Plan mode: write markdown plan to .hermes/plans/, no exec.
Idioma do texto original: inglês
Write implementation plans: bite-sized tasks, paths, code.
Idioma do texto original: inglês
对真实 Chrome + CDP 的支付/回调编排，先固化 contract 与边界，再用 probes 采证；未知站点规则不得直接升入主线。
Idioma do texto original: chinês
Fix HTTP 403 blocks from custom API providers (WAF/Cloudflare) that reject SDK User-Agent headers. Fixed UA is set in run_agent.py; no more rotation pool.
Idioma do texto original: inglês
Debug Python: pdb REPL + debugpy remote (DAP). 触发方式：Hermes 路由名 `software-development/py-debugpy`、通用 slash command `/skill software-development/py-debugpy`
Idioma do texto original: inglês
Evaluate the QMD repo/tool before adoption, install it safely on the host, and integrate it into an agent workflow without violating the repo's own automation constraints.
Idioma do texto original: inglês
Use when the user says they already cloned several repos locally and wants Hermes to inspect the newest repos, read their README/docs, then decide whether to learn from them, install them, or absorb reusable ideas. Best for local repo triage under ~ where…
Idioma do texto original: inglês
Absorb high-value patterns from OpenEvolve, RTK, Meta-Harness, and bgclick reverse-engineering into Hermes-native execution: slash-routed background loops, token-thrifty output surfaces, harness-search framing, and evidence-first reverse workflows.
Idioma do texto original: inglês
Staged workflow for clearing Rust clippy debt in large repos without thrashing — compile/API migration first, then low-risk mechanical lints in batches, then signature/type refactors, with cargo check between phases.
Idioma do texto original: chinês
Extract structs and functions from a large Rust main.rs into dedicated module files without breaking compilation. Covers the analyze.rs vs analyze/mod.rs ambiguity pitfall and bottom-up dependency ordering.
Idioma do texto original: inglês
Use when a project's agent docs, AGENTS.md, CLAUDE.md, rules, or skills are getting bloated, duplicated, or hard to route. Activate when you need to restructure agent-facing documentation into a lean skill architecture, add triggerable skill descriptions,…
Idioma do texto original: inglês
Use when Hermes skills have grown beyond a handful and need explicit routing, trigger governance, and maintenance. Activate when you want a central skill router, AGENTS.md routing table, auto-update discipline for newly created skills, and a repeatable way to…
Idioma do texto original: inglês
Use when auditing Hermes SKILL.md files for YAML/frontmatter breakage and repairing invalid frontmatter safely at scale.
Idioma do texto original: inglês
Use Slopless to review English Markdown for deterministic AI and human slop signals, including vague phrasing, formulaic prose, weak rhythm, filler, cliches, and readability issues.
Idioma do texto original: inglês
Throwaway experiments to validate an idea before build.
Idioma do texto original: inglês
Execute plans via delegate_task subagents (2-stage review).
Idioma do texto original: inglês
Use when a user rejects an agent output format, system prompt rule, memory habit, or host-agent instruction and wants Hermes, Codex, Claude Code, and OpenClaw behavior made consistent.
Idioma do texto original: inglês
Use when encountering any bug, test failure, or unexpected behavior. 4-phase root cause investigation — NO fixes without understanding the problem first.
Idioma do texto original: inglês
Use when implementing any feature or bugfix, before writing implementation code. Enforces RED-GREEN-REFACTOR cycle with test-first approach.
Idioma do texto original: inglês
用于吸收 Vibe-Skills / VCO 一类大规模 skill OS 仓的治理精华，而不直接照搬其运行时。 当用户提到 Vibe-Skills、VCO、skill sprawl、promotion gate、replay ledger、M/L/XL 路由、proof bundle、workspace memory plane 时触发。
Idioma do texto original: chinês
Patch the VS Code OpenAI Codex extension so Hermes/Codex reply completion triggers an audible macOS beep and optional VS Code toast when the shipped extension ignores desktop-notification-show.
Idioma do texto original: inglês
PUA/PIP 式 agent skill — 用企业 PUA 话术 / Performance Improvement Plan 督促 AI 不摆烂、不放弃、主动解决问题。支持 Claude Code、Codex CLI 等。
Idioma do texto original: chinês
扫描项目技术栈，自动安装最佳 AI agent skills。 用 autoskills CLI 从 skills.sh 安装匹配的 skills。 中文触发：自动技能、安装技能、技能扫描、装技能、autoskills
Idioma do texto original: chinês
Install and configure open-computer-use (macOS Computer Use via MCP) for Hermes Agent. Covers npm install, macOS permissions, hermes MCP config, and troubleshooting.
Idioma do texto original: chinês
Practical guide for using an external/shared memory system such as MemOS alongside Hermes memory and session search.
Idioma do texto original: inglês
AutoR — human-centered 研究执行框架。8阶段 pipeline，产出可复现 artifact。
Idioma do texto original: chinês
Pre-release audit for CLI tools (especially Rust/Python). Checks build, tests, help quality, output friendliness (agent + human), path leaks, dependency portability, .gitignore hygiene, and missing release artifacts.
Idioma do texto original: inglês
Use when Hermes needs a local external memory/knowledge-graph backend without remote services. Trigger when storing durable notes outside built-in memory, querying local knowledge shelves, syncing selected Hermes memory into a searchable graph, or building a…
Idioma do texto original: inglês
Apply the user's preferred model/API fallback strategy when task execution may require provider rotation, retries, failover, or token-efficient routing.
Idioma do texto original: inglês
古法编程模式。在 AI 辅助开发中强制执行问题建模、执行流模拟、复杂度分析与架构控制， 防止认知空心化，提升系统级正确性、性能与可维护性。适用于高并发、底层系统、逆向工程与复杂问题排查。
Idioma do texto original: chinês