Repository
Prism-Shadow/penguin-harness agent skills
- skills
- 31
- GitHub stars
- 2.5k
GitHub description: “🐧 Unified and Stable RSI Platform”
- Stars
- 2,464 (267 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Jul 2026
- Homepage
- penguin.ooo
- agent
- agentic-ai
- ai
- claude-code
- llm
- harness
- build-tool
- desktop
- deepseek
- rsi
- self-evolving
- deepseek-harness
Install all skills
npx skills add Prism-Shadow/penguin-harnessAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in Prism-Shadow/penguin-harness, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 1.A2ui Make a reply easier to read and act on with rich blocks inside ordinary Markdown — a choice the user picks from, a form that collects several answers, a procedure as steps with warnings in place, a… | Prism-Shadow/ | 2.5k | — | ~3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 2 | A skill your agent uses when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release… | Prism-Shadow/ | 2.5k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 3 | Create and edit Bento presentations — self-contained .bento.html decks whose document is JSON. | Prism-Shadow/ | 2.5k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 4 | A skill your agent uses when standing PenguinHarness up to try a change by hand — launching the Web App, the desktop shell, the landing page, the docs site or the component gallery to click through… | Prism-Shadow/ | 2.5k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 5 | A skill your agent uses when changing the PenguinHarness Web App (packages/web) or the shared UI package — adding or restyling any UI, picking a status colour, adding an icon, laying out a row or a… | Prism-Shadow/ | 2.5k | — | ~6.4k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 6 | Drive the PenguinHarness agent browser — the desktop app's built-in browser or the user's own Chrome — from the shell with penguin browser: open pages, read them as simplified HTML or text, act with… | Prism-Shadow/ | 2.5k | — | ~2.9k | Automated safety check: Warn | Apache-2.0 | 2 days ago |
| 7 | A skill your agent uses whenever the user wants to build an agent application — their own program with an embedded agent, such as an AI app, an agentic app or a RAG app. | Prism-Shadow/ | 2.5k | — | ~11k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 8 | Run one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result. | Prism-Shadow/ | 2.5k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 9 | Initialize or extend an Agent from a user requirement - write AGENTS.md, set identity metadata, and create, install or import Skills and hook packages (scripts the harness runs on every prompt… | Prism-Shadow/ | 2.5k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 10 | Improve an Agent State through versioned scores and score-linked Traces from a frozen Benchmark. | Prism-Shadow/ | 2.5k | — | ~3.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 11 | Run finance for a PenguinHarness organization — set and adjust monthly budgets along the reporting line, audit spend daily with penguin org finance and penguin cost, explain budget alerts in the… | Prism-Shadow/ | 2.5k | — | ~2.2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 12 | 12.Company Hr Run HR for a PenguinHarness organization — guarantee every employee has an enabled calendar event, hire and offboard employees (channels included), evaluate and improve them (with the agent-tuning… | Prism-Shadow/ | 2.5k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 13 | Run a PenguinHarness organization that mirrors a real company — one digital twin per real colleague, each twin's desk bound to that colleague's chat bot, twins answering what the handbook already… | Prism-Shadow/ | 2.5k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 14 | Run experiments and papers in a PenguinHarness research organization — fix the harness and the metric first, run an autoresearch-style loop (one editable surface, the same time budget per… | Prism-Shadow/ | 2.5k | — | ~3.4k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 15 | Create a company-mode organization together with the user — collect its id, name, mission, shared workspace, model and CEO budget one question at a time, confirm the whole thing in one summary, then… | Prism-Shadow/ | 2.5k | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 16 | 16.Firecrawl Search the web and scrape pages into clean markdown with the Firecrawl API — query-based discovery, single-URL extraction including public PDFs, driven by curl with a vault-stored API key. | Prism-Shadow/ | 2.5k | — | ~902 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 17 | 17.Humanizer Rewrite or edit prose in any language so it reads like edited human writing in the register of books, newspapers and encyclopedias rather than default AI output. | Prism-Shadow/ | 2.5k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 18 | 18.Llamafactory Fine-tune LLMs with LlamaFactory — register datasets, train via YAML configs, merge LoRA adapters and serve the result. | Prism-Shadow/ | 2.5k | — | ~855 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 19 | 19.Ollama Deploy and serve local models with Ollama — pull and run them, then expose the OpenAI-compatible endpoint to apps and agents. | Prism-Shadow/ | 2.5k | — | ~839 | Automated safety check: Notes | Apache-2.0 | 2 days ago |
| 20 | Manage model API keys, default models and per-agent vault secrets with the penguin CLI. | Prism-Shadow/ | 2.5k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 21 | Drive PenguinHarness itself from a shell — list and create agents and sessions, send and steer messages mid-flight, and query costs and scheduled tasks via the penguin CLI over the local server. | Prism-Shadow/ | 2.5k | — | ~4.1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 22 | Install skills from external ecosystems into this agent's agentstate/skills/ — resolve Claude Code plugin marketplaces, the Codex plugin repo, skills.sh registry names, GitHub repos, or local… | Prism-Shadow/ | 2.5k | — | ~4.2k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 23 | 23.Vllm Deploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads. | Prism-Shadow/ | 2.5k | — | ~1k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 24 | 24.Web Design Penguin visual language for generated web pages and app UIs — GitHub-style simplicity with a single blue accent, light and pure-black dark themes, design tokens, component and chat-interface… | Prism-Shadow/ | 2.5k | — | ~4.3k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 25 | Design and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline. | Prism-Shadow/ | 2.5k | — | ~5.7k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 26 | 26.Company Ceo Run a PenguinHarness organization as its CEO — turn the mission into a ticket tree, hire HR and finance first, partition the shared workspace, schedule the calendar, open a channel per stream… | Prism-Shadow/ | 2.5k | — | ~5.5k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 27 | The protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [orgtrigger] work runs, schedule tickets from the desk session and do the work in ticket… | Prism-Shadow/ | 2.5k | — | ~7.6k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 28 | Run Claude Code on a remote host over SSH — a persistent expect-driven login session, headless claude -p with the stdin fix, the interactive TUI inside a remote tmux driven by send-keys/capture-pane… | Prism-Shadow/ | 2.5k | — | ~5.9k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 29 | Call model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client. | Prism-Shadow/ | 2.5k | — | ~6.7k | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 30 | Complete data-analysis tasks with bounded inspection, correct data semantics, native artifact handling, complete delivery, and risk-based verification. | Prism-Shadow/ | 2.5k | — | ~935 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
| 31 | Complete software-engineering tasks — investigate and review code, implement bug fixes, features and refactors with minimal scope, validate changes, and report verified outcomes. | Prism-Shadow/ | 2.5k | — | ~758 | Automated safety check: Pass | Apache-2.0 | 2 days ago |
Questions, answered from the data.
What is the best skill in Prism-Shadow/penguin-harness?
A2ui from Prism-Shadow/penguin-harness ranks first of the 31 skills in Prism-Shadow/penguin-harness listed here, with the highest score: its repository has 2.5k GitHub stars, its SKILL.md loads about 3k tokens and it passes the automated safety check with no findings. Next come Penguin Harness Dev and Bento Slides.
Are the skills in Prism-Shadow/penguin-harness official?
None yet. All 31 skills in Prism-Shadow/penguin-harness listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from Prism-Shadow/penguin-harness?
Run npx skills add Prism-Shadow/penguin-harness in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.