R
rofyray/agent-skill-kit
A curated collection of portable Agent Skills for Codex, Claude, Cursor, Gemini, and ChatGPT, with reusable…
★ 1·updated 2026-11-16
View on GitHub ↗Link checked 2026-11-17 · HTTP 200 · opens the vendor's own site
After install: how to tell it works
- What you see after install — The command exits 0 and the terminal shows no "command not found" or "permission denied".
- One-line self-check — Run the smallest usage example from that repository's README. If the output matches what the README describes, it is working.
- If that does not work — This project has no troubleshooting notes. Search its issues for "install".
The install command comes from the repository; these checks describe observable results only and do not replace the project's own docs.
- Star count
- 1 ★ · rofyray/agent-skill-kit · read from the GitHub search API · (checked 2026-11-19 20:00:48)
- Source
- read directly from its GitHub page · type: open-source project
- Harvest history
- first seen 2026-11-15 · last seen 2026-11-20 · seen 6× · listed by 1 sources
- Score
- score 103 · 1 ★ · 1 sources · repo
- Install
- see Install & config above
FAQ (answers come from our records)
Who is it for?
We filed it under these tags: Open Source. The tags come from the entry itself, not a taxonomy we imposed.
Who maintains it?
repository
rofyray/agent-skill-kit;first catalogued 2026-11-15;last seen 2026-11-20。There is no official certification or quality rating here — we record sources and dates only.README excerpt (English, untranslated) · Read the full README on GitHub →
# Agent Skill Kit
Excerpted from the repository README (abridged)
Portable Agent Skills for Codex, Claude Code, Cursor, Gemini CLI, Claude Web/Desktop/Cowork, and ChatGPT.
## Skills
| Skill | Description |
| ai-film-image-direction | Design, generate, edit, and audit continuity-safe visual assets for films and animation. |
| ai-film-performance-direction | Develop, direct, test, and audit acting, dialogue, voice, and ensemble performance. |
| ai-film-screenwriting | Develop, draft, revise, and evaluate feature-length screenplays through production handoff. |
| ai-film-video-direction | Plan, prompt, generate, revise, and audit continuity-safe film and animation shots. |
| ai-motion-graphics-direction | Direct launch films, footage overlays, product motion, architectural reveals, and 2D or editorial explainers across models. |
| audit-code-slop | Measure verbosity and structural erosion across 12 languages, compare baselines, and verify refactoring progress. |
| build-agent-prds | Create, revise, and audit phased coding-agent PRDs with reusable assets, parallel delivery, testing matched to scope, and complete ZIP handoffs. |
| build-and-maintain-a-second-brain | Build, maintain, and visualize a source-grounded wiki with an interactive 3D brain, ingestion, querying, health checks, and reviews. |
| build-cinematic-sites | Plan, build, revise, and audit complete cinematic websites with purposeful motion in the user's chosen tools. |
| create-and-edit-images | Create photorealistic images or make precise edits while preserving unrequested details. |
| craft-goal-driven-prompts | Turn a goal into a structured prompt with completion criteria and an optional improvement loop. |
| curate-with-taste | Review or create distinctive prose, critique creative options, and keep human taste in the decision loop. |
| design-beyond-defaults | Design, redesign, critique, polish, and audit distinctive interfaces with preserved behavior and rendered evidence. |
| interview-coach | Coach role research, applications, interview prep, practice, debriefs, progress, and negotiation. |
| refine-prompts | Audit, polish, refactor, and compare existing prompts while preserving requirements and exposing behavior changes. |
| review-code-changes | Review changes with an adaptive committee, independently verified findings, and bounded re-review. |
| understand-before-coding | Understand, plan, implement, review, verify, and document code changes using repository evidence. |
| write-agent-briefs | Create, improve, or audit executable agent briefs with clear constraints, verification, and deliverables. |
## Install
### Claude Web/Desktop/Cowork
1. Enable Code execution and file creation in Settings > Capabilities. Team and Enterprise owners must also enable Skills. See Anthropic's setup guide.
2. Download an individual skill ZIP from GitHub Releases.
3. Open Customize > Skills, click +, choose Create skill > Upload a skill, and select the ZIP. Ensure the skill is enabled.
### ChatGPT Web
1. Download an individual skill ZIP from GitHub Releases.
2. Open Plugins > Skills, click +, and choose Upload from your computer.
## Skills
| Skill | Description |
| ai-film-image-direction | Design, generate, edit, and audit continuity-safe visual assets for films and animation. |
| ai-film-performance-direction | Develop, direct, test, and audit acting, dialogue, voice, and ensemble performance. |
| ai-film-screenwriting | Develop, draft, revise, and evaluate feature-length screenplays through production handoff. |
| ai-film-video-direction | Plan, prompt, generate, revise, and audit continuity-safe film and animation shots. |
| ai-motion-graphics-direction | Direct launch films, footage overlays, product motion, architectural reveals, and 2D or editorial explainers across models. |
| audit-code-slop | Measure verbosity and structural erosion across 12 languages, compare baselines, and verify refactoring progress. |
| build-agent-prds | Create, revise, and audit phased coding-agent PRDs with reusable assets, parallel delivery, testing matched to scope, and complete ZIP handoffs. |
| build-and-maintain-a-second-brain | Build, maintain, and visualize a source-grounded wiki with an interactive 3D brain, ingestion, querying, health checks, and reviews. |
| build-cinematic-sites | Plan, build, revise, and audit complete cinematic websites with purposeful motion in the user's chosen tools. |
| create-and-edit-images | Create photorealistic images or make precise edits while preserving unrequested details. |
| craft-goal-driven-prompts | Turn a goal into a structured prompt with completion criteria and an optional improvement loop. |
| curate-with-taste | Review or create distinctive prose, critique creative options, and keep human taste in the decision loop. |
| design-beyond-defaults | Design, redesign, critique, polish, and audit distinctive interfaces with preserved behavior and rendered evidence. |
| interview-coach | Coach role research, applications, interview prep, practice, debriefs, progress, and negotiation. |
| refine-prompts | Audit, polish, refactor, and compare existing prompts while preserving requirements and exposing behavior changes. |
| review-code-changes | Review changes with an adaptive committee, independently verified findings, and bounded re-review. |
| understand-before-coding | Understand, plan, implement, review, verify, and document code changes using repository evidence. |
| write-agent-briefs | Create, improve, or audit executable agent briefs with clear constraints, verification, and deliverables. |
## Install
### Claude Web/Desktop/Cowork
1. Enable Code execution and file creation in Settings > Capabilities. Team and Enterprise owners must also enable Skills. See Anthropic's setup guide.
2. Download an individual skill ZIP from GitHub Releases.
3. Open Customize > Skills, click +, choose Create skill > Upload a skill, and select the ZIP. Ensure the skill is enabled.
### ChatGPT Web
1. Download an individual skill ZIP from GitHub Releases.
2. Open Plugins > Skills, click +, and choose Upload from your computer.
Listed badge (optional)
Copy this line into the README if you want the listing mark. Optional, and it does not affect being listed.
[](https://anclum.com/en/s/rofyray-agent-skill-kit/)
- Source
- github · https://github.com/rofyray/agent-skill-kit
- Browse by field
- Open source
- Traction
- 1 ★
- added
- today
More entries
Filed under
Every tag opens the full list for that filter. Counts are the live catalogue figures.