Hermes Agent Skill Authoring
NousResearch/hermes-agent
Author in-repo SKILL.md files: frontmatter and structure. An agent skill from NousResearch/hermes-agent.
Show an enrolled course and its lessons. An agent skill from madhvantyagi/Gnos.
$ npx skills add madhvantyagi/Gnos --skill course-viewer -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install madhvantyagi/Gnos course-viewer --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/madhvantyagi/Gnos.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/course-viewer .claude/skills/course-viewer && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "course-viewer" agent skill from https://github.com/madhvantyagi/Gnos/tree/main/skills/course-viewer into .claude/skills/course-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-viewer", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/madhvantyagi/Gnos/tree/main/skills/course-viewerType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add madhvantyagi/Gnos --skill course-viewer -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install madhvantyagi/Gnos course-viewer --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madhvantyagi/Gnos.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/course-viewer .agents/skills/course-viewer && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "course-viewer" agent skill from https://github.com/madhvantyagi/Gnos/tree/main/skills/course-viewer into .agents/skills/course-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-viewer", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add madhvantyagi/Gnos --skill course-viewer -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install madhvantyagi/Gnos course-viewer --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madhvantyagi/Gnos.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/course-viewer .cursor/skills/course-viewer && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "course-viewer" agent skill from https://github.com/madhvantyagi/Gnos/tree/main/skills/course-viewer into .cursor/skills/course-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-viewer", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/madhvantyagi/Gnos.git --path skills/course-viewer--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add madhvantyagi/Gnos --skill course-viewer -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install madhvantyagi/Gnos course-viewer --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madhvantyagi/Gnos.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/course-viewer .gemini/skills/course-viewer && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "course-viewer" agent skill from https://github.com/madhvantyagi/Gnos/tree/main/skills/course-viewer into .gemini/skills/course-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-viewer", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install madhvantyagi/Gnos course-viewerInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add madhvantyagi/Gnos --skill course-viewer -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/madhvantyagi/Gnos.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/course-viewer .github/skills/course-viewer && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "course-viewer" agent skill from https://github.com/madhvantyagi/Gnos/tree/main/skills/course-viewer into .github/skills/course-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-viewer", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add madhvantyagi/Gnos --skill course-viewer -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install madhvantyagi/Gnos course-viewer --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/madhvantyagi/Gnos.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/course-viewer .opencode/skills/course-viewer && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "course-viewer" agent skill from https://github.com/madhvantyagi/Gnos/tree/main/skills/course-viewer into .opencode/skills/course-viewer/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "course-viewer", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
course-viewerShow an enrolled course and its lessons. An agent skill from madhvantyagi/Gnos.
Course Viewer is an agent skill from madhvantyagi/Gnos. Show an enrolled course and its lessons. Use lesson-design to author or repair the current lesson before delivering teaching; render published content and serve the local page with saved exercises.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 39 other files, including scripts and reference files (for example `references/vendor/README.md`, `references/vendor/highlight/highlight.min.js` and `references/vendor/katex/auto-render.min.js`).
The repository describes itself as: Teaching harness , help you to learn anything , It teaches like real teacher , design curriculum , generate videos , simulations , images , pdfs , tracks your learning style etc. The licence is MIT.
Read from SKILL.md and the folder at commit 040fa15. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Ships 1 file in scripts/ (JavaScript, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
pythonFrom the folder's file list and the shell code blocks in SKILL.md.
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Course Viewer loads about 1.8k tokens when it runs, and up to ~252k if it reads all its reference files. Until then it costs about 53 tokens; SKILL.md has 967 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
The full file from madhvantyagi/Gnos at commit 040fa15, republished under its MIT licence (© madhvantyagi). 967 words, ~1,831 tokens.
.claude/skills/course-viewer/SKILL.md (or your agent's skills folder). This skill also uses 34 other files; get the full folder from GitHub.Render the enrolled course and its published lessons. The HTML page and its
neighboring assets/ directory can be read locally; the course server saves exercises to JSON and reveals
answers after submission. Math uses KaTeX. Pale peach editorial page: top bar with GNOS + tabs, hero
with giant title + field metadata, curriculum list + topic details.
Use this skill when the learner asks to see the course or answers yes after
the current lesson is ready. Re-render after a changed lesson or artifact
before giving a page link. A learner who explicitly asks for only
the outline may see its contents and sources through --outline-only.
For an explicit context load at this step, use assemble_context.py --mode viewer --subject <subject> --learner <learner> --course-id <course-id>.
Render only from the
enrolled workspace at learners/<learner>/courses/<course-id>,
never from a blueprint outputs/ file.
Read the current topic and its published lesson. Course design supplies the
outline; lesson-design supplies the teaching.
If the current topic has no ready lesson, use that skill and its
lesson design reference to
author it before delivering a lesson page. If the learner reports a shallow
lesson, set its publication back to draft, use the same reference to
repair its explanation and examples, write a new design_receipt, and
re-publish as ready — do not edit a ready file in place.
Do not write lesson content from course.json inside this viewer workflow.
The renderer does not call a model or invoke skills: the host must perform
the handoff, review the lesson, and publish it. A normal render requires a
ready lesson for the current
topic whose design_receipt.course_fingerprint equals the enrolled
course.json fingerprint and whose design_receipt.review is pass.
It fails otherwise with instructions to run lesson design first. Use
--outline-only only for an explicitly requested outline or contents preview.
If rendering fails, do not link an earlier portal/index.html or say the
course is ready to view.
The local server also checks the current lesson before starting and whenever
it serves the page, so an old page cannot be used after the course moves on.
The receipt checks a recorded handoff and course match. It cannot prove that
the host read the skill or that the explanation is good; review the lesson.
.venv/bin/python skills/course-viewer/scripts/render_viewer.py learners/alex/courses/motionThe script reads course.json, published lessons, and the artifact
manifest, then writes portal/index.html and copies the bundled KaTeX,
syntax-highlighting, and math-font assets to portal/assets/.
Open it locally:
.venv/bin/python skills/course-viewer/scripts/serve_course.py learners/alex/courses/motion --port 8080
# visit http://127.0.0.1:8080/portal/Use this server for exercise interaction. A plain file or generic static server
cannot write a learner response to the course workspace. Save answer persists
an attempt under submissions/<exercise-id>/<attempt-id>.json; only a
successful save enables Show answer. The solution is fetched on that explicit
request and the reveal is recorded separately from the learner's response.
The design lives in references/example.html. Follow that layout and the approved palette:
chip manim hooks, hidden in
curriculum rows, visible in Lessons). Older course plans still show their
planned formats. A chip turns ready
(chip manim ready) when its artifact is registered#tabs, #lesson-list,
.lesson, #prev-link / #next-link) stay intactThe viewer renders whatever is registered in the course artifact manifest, whatever made it:
<video><img><iframe>The lesson blocks show which forms were used. Older courses can still show
their planned formats. The lesson coordinator registers every artifact with
manage_artifact.py before rendering; only ready artifacts appear.
$...$, $$...$$); the renderer
preserves delimited LaTeX and equation blocks exactly. Legacy undelimited
ASCII text has a limited compatibility converter; never rely on it when
authoring. Follow the lesson contract.
Body prose is serif. Code blocks use semantic <pre><code> markup and the
bundled highlighter; the code remains readable when highlighting cannot run.© madhvantyagi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
SKILL.md and 34 other files (scripts, references) in skills/course-viewer of madhvantyagi/Gnos.
Open the folder on GitHubat commit 040fa15
Course Viewer next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Course Viewer this skillmadhvantyagi/Gnos | 339 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Hermes Agent Skill AuthoringNousResearch/hermes-agent | 252k | — | ~3.6k | Automated safety check: Pass | MIT | |
| Configuring Oauth2 Authorization Flowmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | |
| Authoring Skillsvercel/next.js | 143k | — | ~1k | Automated safety check: Pass | MIT | |
| Abp Authorizationabpframework/abp | 14k | — | ~1.3k | Automated safety check: Pass | LGPL-3.0 | |
| Lesson Memory Recorderrohitg00/agentmemory | 29k | — | ~721 | Automated safety check: Pass | Apache-2.0 |
NousResearch/hermes-agent
Author in-repo SKILL.md files: frontmatter and structure. An agent skill from NousResearch/hermes-agent.
mukul975/Anthropic-Cybersecurity-Skills
Configures secure OAuth 2.0 authorization flows, including Authorization Code with PKCE, Client Credentials, and Device Authorization Grant, covering flow selection, PKCE implementation, token…
vercel/next.js
How to create and maintain agent skills in .agents/skills/. An agent skill from vercel/next.js.
abpframework/abp
ABP permission system - PermissionDefinitionProvider, [Authorize] attribute, CheckPolicyAsync, IsGrantedAsync, ICurrentUser, IPermissionManager, multi-tenancy side.
rohitg00/agentmemory
Distills a user correction or hard-won rule into a confidence-weighted lesson that resurfaces automatically before similar future work.
mukul975/Anthropic-Cybersecurity-Skills
Implements GCP Binary Authorization end to end, including creating KMS-backed attestors, Container Analysis notes, deploy-time policies, and signing image attestations, so that only trusted…
madhvantyagi/Gnos
Design and revise a course's goal, progression, prerequisites, and sources.
madhvantyagi/Gnos
Find a Khan Academy video fast and add it only on a strong match.
madhvantyagi/Gnos
Record what the learner does and adapt the course to it in real time.
madhvantyagi/Gnos
Develop the current topic into a connected lesson. An agent skill from madhvantyagi/Gnos.
madhvantyagi/Gnos
Make Manim teaching animations with narration and subtitles when motion helps a concept.
madhvantyagi/Gnos
Turn lesson content into a PDF handout; render and check it before delivery.
Show an enrolled course and its lessons. An agent skill from madhvantyagi/Gnos. Course Viewer is an agent skill from madhvantyagi/Gnos. Show an enrolled course and its lessons.
Run `npx skills add madhvantyagi/Gnos --skill course-viewer -a claude-code`. Or copy the skill folder (skills/course-viewer in madhvantyagi/Gnos) into .claude/skills/course-viewer in your project. Claude Code loads it when a task matches its description.
Run `npx skills add madhvantyagi/Gnos --skill course-viewer -a codex`. Or copy the skill folder (skills/course-viewer in madhvantyagi/Gnos) into .agents/skills/course-viewer in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add madhvantyagi/Gnos --skill course-viewer -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/course-viewer, .gemini/skills/course-viewer, .github/skills/course-viewer and .opencode/skills/course-viewer in your project.
Going by SKILL.md and its folder, Course Viewer needs JavaScript for the scripts in its folder and the command-line tools its instructions call (python). Our summary lists: Python 3; Node.js.
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
Course Viewer is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 1.8k tokens (SKILL.md is roughly 7.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 250k tokens, read only when the agent opens those files.
Skills that share tags, products or a category with Course Viewer: Hermes Agent Skill Authoring (NousResearch/hermes-agent, 252k stars), Configuring Oauth2 Authorization Flow (mukul975/Anthropic-Cybersecurity-Skills, 34k stars), Authoring Skills (vercel/next.js, 143k stars) and Abp Authorization (abpframework/abp, 14k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
madhvantyagi (a GitHub user) maintains it in madhvantyagi/Gnos, which has 339 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 10, 2026.
Source: madhvantyagi/Gnos on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.