All authors
Claude Skills by Prism-Shadow
github.com/Prism-Shadow46 skills1 installs73 views
- Penguin Harness DevUse when developing PenguinHarness itself — changing packages/{core,server,web,cli,desktop,landing,docs,skills}, the built-in model catalog, the installers or the release workflow; writing or auditing changelog entries; writing a blog post or capturing release screenshots; running the test suite here or, when asked, on another machine; reading a prompt-cache regression out of the core suites; deciding what to do about data already on disk; auditing prose that reads like a leaked authoring ses...Votes: 0GitHub stars: 2,442
- Penguin Harness FrontendUse 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 form field, writing user-facing copy, building a popup or a hover-revealed panel, or making anything open, fold, resize or maximize. Covers the semantic tone tokens, the icon size/stroke/gap scale, the semantic-versus-formatting rule and the hover "?", the two-dictionary i18n contract, the portal-panel pattern, moti...Votes: 0GitHub stars: 2,442
- Penguin Harness Manual TestUse 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 it, screenshot it, or reproduce a report. Covers the dev entry points and their ports, which data root each writes to, and the four ways a healthy setup looks broken.Votes: 0GitHub stars: 2,442
- 0.2.1- **Date:** 2026-08-04 - **Type:** feature - **Scope:** `skills`, `docs` - **PR:** [#195](https://github.com/Prism-Shadow/penguin-harness/pull/195) [中文版](2026-08-04-skill-porting-library-skill.zh.md) New library skill `skill-porting` (agent-tuning group) teaching an agent to bring skills in from the outside world and land them correctly in `agent_state/skills/<name>/`. Its schema tables were verified by directly fetching each source on 2026-08-04 — the skill says so and treats the live JSON a...Votes: 0GitHub stars: 2,442
- 0.2.2- **Date:** 2026-08-11 - **Type:** feature - **Scope:** `skills` - **PR:** [#256](https://github.com/Prism-Shadow/penguin-harness/pull/256) [中文版](2026-08-11-humanizer-skill.zh.md) `humanizer` joins the built-in library under the Office Productivity group as a manual-install skill — `preinstall: false`, so it stays out of default_agent's preinstalled set and installs from the Skill Library on demand ([#256](https://github.com/Prism-Shadow/penguin-harness/pull/256)).Votes: 0GitHub stars: 2,442
- 0.2.4- **Date:** 2026-08-21 - **Type:** refactor - **Scope:** `skills`, `web`, `docs` - **PR:** [#400](https://github.com/Prism-Shadow/penguin-harness/pull/400) - **Breaking:** yes — the library Skill `agent-creation` no longer exists under that name [中文版](2026-08-21-agent-initialization-skill.zh.md) The Agent Tuning group's `agent-creation` Skill is now **`agent-initialization`**. The name says what it does: it initializes an Agent's settings — AGENTS.md, identity metadata, and the Skills that Ag...Votes: 0GitHub stars: 2,442
- 0.2.6- **Date:** 2026-08-23 - **Type:** process - **Scope:** `skills`, `docs` - **PR:** [#428](https://github.com/Prism-Shadow/penguin-harness/pull/428) [中文版](2026-08-23-manual-test-skill.zh.md) `.agents/skills/penguin-harness-manual-test/SKILL.md` is a new repo-development skill covering how to bring the app up on a developer machine so a change can be tried by hand: the four dev entry points (`pnpm dev`, `pnpm desktop`, `pnpm dev:landing`, `pnpm dev:docs`) with their fixed ports, and the environ...Votes: 0GitHub stars: 2,442
- 0.2.6- **Date:** 2026-08-25 - **Type:** feature - **Scope:** `skills`, `docs` - **PR:** [#463](https://github.com/Prism-Shadow/penguin-harness/pull/463) [中文版](2026-08-25-penguin-orchestration-skill.zh.md) Added `penguin-orchestration` (v1) to the skill library's AI App Development group, right after `penguin-cli`. It teaches an agent running inside PenguinHarness to drive the harness itself over the `penguin` CLI against its own local server: list and create agents, start sessions and steer them m...Votes: 0GitHub stars: 2,442
- Agent EvaluationRun one specified Test Agent on one specified Benchmark Case exactly once, privately score that execution, and return one protocol result.Votes: 0GitHub stars: 2,442
- Agent InitializationInitialize 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, before tool calls, or after a task).Votes: 0GitHub stars: 2,442
- Agent OptimizationImprove an Agent State through versioned scores and score-linked Traces from a frozen Benchmark.Votes: 0GitHub stars: 2,442
- Benchmark DesignDesign and calibrate a multi-Case capability Benchmark and establish a traceable Formal Baseline.Votes: 0GitHub stars: 2,442
- Bento SlidesCreate and edit Bento presentations — self-contained .bento.html decks whose document is JSON. Use whenever the user wants a slide deck or presentation: from scratch, from source material, or by improving an existing file.Votes: 0GitHub stars: 2,442
- Data AnalysisComplete data-analysis tasks with bounded inspection, correct data semantics, native artifact handling, complete delivery, and risk-based verification.Votes: 0GitHub stars: 2,442
- FirecrawlSearch 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.Votes: 0GitHub stars: 2,442
- HumanizerRewrite 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. A small drafting core — vary every pattern, build density from anchored facts in whole grammar, cap the quotables, put a real writer with real material behind the text, let structure serve content, write each language from inside its idiom and typography, verify what you assert, and aim for the natural distribution of edited prose ra...Votes: 0GitHub stars: 2,442
- LlamafactoryFine-tune LLMs with LlamaFactory — register datasets, train via YAML configs, merge LoRA adapters and serve the result.Votes: 0GitHub stars: 2,442
- OllamaDeploy and serve local models with Ollama — pull and run them, then expose the OpenAI-compatible endpoint to apps and agents.Votes: 0GitHub stars: 2,442
- Penguin OrchestrationDrive 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.Votes: 0GitHub stars: 2,442
- Penguin SdkUse 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. This is writing application code on the Penguin Harness SDK, not configuring an Agent State inside PenguinHarness. Covers self-contained projects, the createSession/run streaming loop with thinking and image messages, wiring the user's existing tools in as CLI commands, and a complete RAG recipe that ingests documents into a knowledge base and a...Votes: 0GitHub stars: 2,442
- Remote Claude CodeRun 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 (one keystroke at a time, capture-verified; relayed user messages go through verbatim), and multi-turn continuity via --session-id/--resume or stream-json; hosts and credentials are placeholders resolved at runtime from the user or the vault, never hardcoded.Votes: 0GitHub stars: 2,442
- Skill PortingInstall skills from external ecosystems into this agent's agent_state/skills/ — resolve Claude Code plugin marketplaces, the Codex plugin repo, skills.sh registry names, GitHub repos, or local folders to their skill directories, review every file, and normalize SKILL.md frontmatter to the Penguin format.Votes: 0GitHub stars: 2,442
- Software EngineeringComplete software-engineering tasks — investigate and review code, implement bug fixes, features and refactors with minimal scope, validate changes, and report verified outcomes.Votes: 0GitHub stars: 2,442
- VllmDeploy and serve LLMs with vLLM behind an OpenAI-compatible endpoint, with tool calling enabled for agent workloads.Votes: 0GitHub stars: 2,442
- Web DesignPenguin 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 recipes, plus an opt-in warm paper editorial theme.Votes: 0GitHub stars: 2,442
- Company CeoRun 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, review tickets and report to the board in the all-hands channel.Votes: 0GitHub stars: 2,442
- Company EmployeeThe protocol every employee of a PenguinHarness organization follows — read the handbook first, act on [org_trigger] work runs, schedule tickets from the desk session and do the work in ticket sessions, block instead of idling, ask the board in the all-hands channel before anything heavy, costly, irreversible or outside the workspace, keep channel and budget discipline, and drive it all with penguin org.Votes: 0GitHub stars: 2,442
- Company FinanceRun 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 all-hands channel with savings proposals, and handle budget pauses.Votes: 0GitHub stars: 2,442
- Company HrRun 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 plugin's agent-optimization skill), and keep the handbook's role conventions current.Votes: 0GitHub stars: 2,442
- Company MirrorRun 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 knows and relaying the rest to one another instead of hiring, scheduling and filing tickets.Votes: 0GitHub stars: 2,442
- Company ResearchRun 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 experiment, a results log, keep only improvements) inside a resource envelope the board approved in the all-hands channel, and put every claim through adversarial review by a reviewer who is not its author.Votes: 0GitHub stars: 2,442
- Company SetupCreate 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 run penguin org create and hand the user over to company mode.Votes: 0GitHub stars: 2,442
- Penguin ConfigManage model API keys, default models and per-agent vault secrets with the penguin CLI.Votes: 0GitHub stars: 2,442
- Unified Llm ApiCall model APIs through @prismshadow/mmsp (MMSP) — streaming text generation, image generation, speech synthesis, embeddings and the supported-model registry with one client.Votes: 0GitHub stars: 2,442
- Browser AutomationDrive 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 JavaScript and trusted clicks and typing, and pull structured data out of them (orders, search results, tables), signed in with the user's own accounts. Use it for any task on a website that needs a real browser or the user's sign-in, such as finding an Amazon order.Votes: 0GitHub stars: 2,442
- A2uiMake 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 callout, or a Mermaid diagram — written as fenced blocks the app renders with its own components; a pick comes back as the user's plain text. Use when a reply asks the user to decide, collects several inputs, gives a procedure, or explains a structure or flow. Includes STE-style writing rules for C...Votes: 0GitHub stars: 2,442
- 0.4.0- **Date:** 2026-07-17 - **Type:** process - **Scope:** `skills`, `llmsdk_docs`, `changelog`, `api_captures` - **PR:** [#158](https://github.com/Prism-Shadow/agenthub/pull/158) [中文版](2026-07-17-agenthub-dev-skill.zh.md)Votes: 0GitHub stars: 113
- Mmsp DevFixed workflow for developing MMSP itself — adding or updating model support, and changing its pages. Use when asked to support a new model or protocol version in this repository, sync llmsdk_docs, implement a provider client, or change the playground, the tracer or the site. Covers doc syncing, live API capture, paired Python/TypeScript implementation, model-scoped e2e testing, and the UI rules for the three pages.Votes: 0GitHub stars: 113
- Mmsp PythonGuidance for using the MMSP Python SDK (`mmsp`). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention MMSP, request `mmsp`, or already import it.Votes: 0GitHub stars: 113
- Mmsp TypescriptGuidance for using the MMSP TypeScript SDK (`@prismshadow/mmsp`). Use when developing agents that call different LLM APIs, need a unified interface for LLM providers, mention MMSP, request `@prismshadow/mmsp`, or already import it.Votes: 0GitHub stars: 113
- Code WorkflowUse for non-trivial code changes, bug fixes, and CI repairs that benefit from explicit planning, scoped implementation, verification, and lesson capture; do not use for simple questions or trivial edits.Votes: 0GitHub stars: 66
- ImplementedStatus: implementedVotes: 0GitHub stars: 66
- SrcThis document is emitted by `penguin-browser skill` for standalone CLI and MCP users. It is not the Travel Agent Desktop backend policy. Travel Agent agents use `packages/skills/skills/penguin-browser/SKILL.md`, and plain `session new` automatically follows the per-conversation Browser-menu choice (IAB by default, Chrome only when the user selects it). Do not use direct, headless, or cloud examples below to override a Desktop conversation.Votes: 0GitHub stars: 66
- Amap Lbs SkillAmap (Gaode) location services for mainland-China travel scenes over the Amap Web Service REST API: POI and nearby search, geocoding, walking/driving/transit/cycling route planning, day-trip itinerary planning, and shareable map links. Use when a request involves Chinese locations, distances, "附近/周边" nearby queries, routes, or itineraries inside mainland China; requires the user's own Amap Web Service key.Votes: 0GitHub stars: 66
- Penguin BrowserControl the browser backend selected for a Travel Agent conversation through the Penguin Browser CLI and persistent Playwright sessions. Desktop conversations default to the visible in-app browser; the user's own Chrome is an explicit alternative for reusing that profile or an existing authorized tab. Use for interactive or authenticated browser tasks that require rendered DOM, ARIA semantics, navigation, dialogs, downloads, or visual fallback.Votes: 0GitHub stars: 66
- Trip WorkspaceRead and maintain the files of the Trip a conversation belongs to. A Trip is the traveller's journey - it owns a folder on their own disk holding trip.json (its identity, written by the app) and itinerary.md (the plan, written by you). Use at the start of any conversation that belongs to a Trip, and whenever a decision, a comparison or a booking-page result should outlive the conversation that produced it.Votes: 0GitHub stars: 66