Undermybelt/hermes-skills - 第 30 页

fanqie-male-reader-prof

用 headless 采样番茄书库不同字数段热榜，在字体混淆下仍归纳男频读者侧写、爽点偏好与写作策略。

follow-builders

AI builders digest — monitors top AI builders on X and YouTube podcasts, remixes their content into digestible summaries. Use when the user wants AI industry insights, builder updates, or invokes /ai. No API keys or dependencies required — all content is…

原文语言：英语

github-trending-spider

Operate or review the AI Daily Frontier / github-trending-spider project: a Python + Vue app that aggregates GitHub Trending, Hacker News, TLDR AI, V2EX, Linux.do, OpenAI, Anthropic, and InfoQ AI sources into Chinese AI/frontier summaries, JSON snapshots, a…

原文语言：英语

gread

Provide the ability to search, inspect, and read source code from all public GitHub repositories and their associated documentation.

原文语言：英语

openalex-paper-search

Query OpenAlex for scholarly works, DOI lookups, citation metadata, author/source/topic filters, and API quota status. Use when the user asks to search papers, find literature, lookup DOI/OpenAlex IDs, query OpenAlex, 查论文, 搜论文, or inspect paper metadata with…

原文语言：英语

paper-search

Search, download, and read academic papers from 20+ sources (arXiv, PubMed, Semantic Scholar, CrossRef, OpenAlex, etc). Use when the user asks to find papers, search academic literature, look up research papers, download a paper PDF, or extract text from a…

原文语言：英语

qmd

使用 QMD 作为 Hermes 的外部记忆检索层。面向本机 notes/docs/projects/skills/sessions 的本地混合检索，优先走向量或 hybrid 搜索，而不是只靠 session_search。

research-innvtn-explorer

Explore literature-grounded research innovation ideas and paper framing in a host-neutral way. Use when an AI agent needs to collect a recent paper pool, run broad and deep literature search, decompose methods into reusable capabilities, generate A+B or…

原文语言：英语

research-knowledge-ops

Use when doing research or knowledge-work from Hermes: arXiv discovery, prediction-market data, wiki/markdown knowledge bases, Obsidian notes, or DSPy-style research/prototyping of LM programs.

原文语言：英语

research-paper-write

Write ML papers for NeurIPS/ICML/ICLR: design→submit.

原文语言：英语

skillopt

Use when the user asks about Microsoft SkillOpt, optimizing or training agent skill documents with reflective loops, evaluating skill changes with validation gates, or running SkillOpt experiments. This is a wrapper around the local reviewed source checkout…

原文语言：英语

xurl

X/Twitter via xurl CLI: post, search, DM, media, v2 API.

原文语言：英语

agent-brain-thin-harness

Use when improving Hermes or a repo's agent docs around memory boundaries, external knowledge routing, thin-harness-fat-skills structure, or short AGENTS/CLAUDE map design. Activate when you want to absorb good ideas from systems like GBrain without…

原文语言：英语

agent-harness-evltn

Evaluate external agent learning and memory harnesses from code before installing; verify host coupling, enforcement reality, forgetting semantics, and safe adopt-vs-adapt recommendation.

原文语言：英语

arch-drift-guard

Use when a repo is suffering architecture drift, API drift, main-file bloat, boundary erosion, or repeated breakage from cross-layer edits. Enforces artifact-first anti-drift governance: classify drift type, declare allowed change surface, write durable repo…

原文语言：英语

claude-code-harness

Plan-work-review harness for Claude Code.

原文语言：英语

code-review

Pre-commit review: security scan, quality gates, auto-fix.

原文语言：英语

codex-session-patcher

Codex/Claude/OpenCode session patcher review.

原文语言：英语

dbggng-hermes-tui-comman

Debug Hermes TUI slash commands: Python, gateway, Ink UI.

原文语言：英语

ddd-project-grdrls

Use when a user asks Hermes to design, scaffold, refactor, or implement a non-trivial software project, service, platform, or architecture. Enforces slow-is-smooth DDD discipline: strategic design first, tactical design second, implementation last; prevents…

原文语言：英语

decision-surface-layer

Hermes 中文优先的决策面技能：把“主目标、偏好权重、硬约束、取舍规则”单独落成用户可改文件， 不再埋在提示词里。适用于方案很多、取舍复杂、用户偏好稳定、执行前必须先定方向的任务。

原文语言：多语言混合

evo-exprmn-optmzr

Convert evo's experiment-tree optimization model into a Hermes-native workflow for benchmark-driven code evolution using git worktrees, scored experiments, gates, traces, and iterative branching.

原文语言：英语

fres-cont-loop-runn

Hermes 中文优先的轻量自主循环技能：每轮新上下文、状态写文件、Git 留痕、小任务推进、测试/构建/验收作为回压门禁。 当用户说一直跑、循环做、分小步、断点续跑、跑到完成、像 Ralph 那样、别塞爆上下文时使用。

原文语言：多语言混合

gap-driven-repo-implmn

Identify project gaps, search GitHub for reference implementations, translate/adapt to target language, integrate with tests

原文语言：英语

graphify-flow

Install and use graphify from Hermes to build knowledge graphs for codebases, docs, papers, or mixed folders, then inspect GRAPH_REPORT.md and graph outputs.

原文语言：英语

herm-feis-gate-dbgg

Debug Hermes gateway when Feishu/Lark credentials appear configured but the bot does not reply. Covers stale launchd env, platform-not-enabled states, websocket startup failure, and duplicate local gateway conflicts.

hermes-agent-sec-review

Use when Hermes is asked to install, trust, review, clone, or rely on an external skill, MCP server, repository, URL, document, on-chain address, or product integration. Activate when untrusted external input could lead to prompt injection, supply-chain…

原文语言：英语

hermes-agent-skill-athrn

Author in-repo SKILL.md: frontmatter, validator, structure.

原文语言：英语

hermes-config-optmzr

Hermes配置优化 - 精简路由文件、添加中文触发词、压缩memory，减少token消耗

hermes-mcp-self-heal

Use when Hermes MCP servers show failed or disconnected behavior and need structured self-heal: test each server, verify the backing listener or command, repair launchd persistence, and retest from Hermes.

原文语言：英语

hermes-mcp-server-extnsn

Extend Hermes MCP server (mcp_serve.py) to expose internal capabilities to external agents. Use when adding tools to Hermes's MCP interface so Codex, Windsurf, Claude Code, and other MCP clients can access skills, routing, or other Hermes features.

原文语言：英语

hermes-skill-gov

Use when Hermes skills are accumulating, getting stale, or producing mixed results. Activate when you need to classify skills by observed quality, decide whether to auto-fix, iteratively improve, or freeze a skill, and keep the skill set reliable without…

原文语言：英语

host-disk-cleanup

Use when the local machine is out of disk space or the user asks to delete unused, untagged, old, cache, log, snapshot, Codex, or Hermes local state without touching important personal files.

原文语言：英语

hypa-loca-memo-brid-fts

Use when turning Hypatia into a local external memory layer for Hermes or another agent, especially when you need a thin CLI bridge and must verify that FTS search actually indexes newly inserted knowledge. Also use when Hypatia search returns no results…

原文语言：英语

ict-engi-fact-rese-muta

Class-level umbrella for ict-engine factor-research, mutation scoring, parameter sweeps, autoresearch scripting, and structural interpretation of optimization bottlenecks. Use when working on factor-research experiments, mutation evaluation, scoring anatomy,…

原文语言：英语

ict-engine-maintenance-loop

Use when committing ict-engine work, repairing provider/runtime readiness, changing shell/env setup, or turning repeated repo maintenance lessons into durable skills and routing entries.

原文语言：英语

ict-engine-release-mirror-ci

Use when publishing ict-engine to the private release mirror, when GitHub Actions fails after publication, when a published tag needs correction, or when source repo and release mirror targets may be confused.

原文语言：英语

ict-engine-surface-intgr

Class-level umbrella for ict-engine feature/surface integration work: extending FrameFeatures, wiring timed PDA and BBN evidence, safely integrating new output surfaces into main.rs, and staged extraction/triage of monolithic integration paths.

原文语言：英语

json-firs-fnnc-cli-patt

Absorb agent-facing patterns from trading/financial CLIs such as kraken-cli without blindly integrating live execution. Use when evaluating exchange CLIs, paper-trading shells, MCP-enabled finance tools, or when porting their JSON-first subprocess contracts,…

karpathy-coding-dscpln

Compact coding-discipline overlay for Hermes based on Karpathy-inspired guidelines: think before coding, simplicity first, surgical changes, and goal-driven verification. Use when doing non-trivial code edits, reviews, refactors, or debugging where…