Archify Diagrams
tt-a1i/archify
Creates interactive architecture, workflow, sequence, data-flow and lifecycle diagrams as standalone HTML with inline SVG, themes and image or video export.
Explains how LobeHub records Works, durable records of what an agent produced, covering registration, deduplication, versions, cards, type adapters and share-visitor access scopes.
Install LobeHub Agent Work Registry
$ npx skills add lobehub/lobehub --skill agent-work -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install lobehub/lobehub agent-work --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/lobehub/lobehub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/agent-work .claude/skills/agent-work && 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 "agent-work" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-work into .claude/skills/agent-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-work", 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/lobehub/lobehub/tree/canary/.agents/skills/agent-workType 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 lobehub/lobehub --skill agent-work -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install lobehub/lobehub agent-work --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/agent-work .agents/skills/agent-work && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "agent-work" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-work into .agents/skills/agent-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-work", 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 lobehub/lobehub --skill agent-work -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install lobehub/lobehub agent-work --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/agent-work .cursor/skills/agent-work && 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 "agent-work" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-work into .cursor/skills/agent-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-work", 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/lobehub/lobehub.git --path .agents/skills/agent-work--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 lobehub/lobehub --skill agent-work -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install lobehub/lobehub agent-work --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/agent-work .gemini/skills/agent-work && 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 "agent-work" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-work into .gemini/skills/agent-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-work", 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 lobehub/lobehub agent-workInstalls 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 lobehub/lobehub --skill agent-work -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/agent-work .github/skills/agent-work && 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 "agent-work" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-work into .github/skills/agent-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-work", 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 lobehub/lobehub --skill agent-work -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install lobehub/lobehub agent-work --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/lobehub/lobehub.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/agent-work .opencode/skills/agent-work && 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 "agent-work" agent skill from https://github.com/lobehub/lobehub/tree/canary/.agents/skills/agent-work into .opencode/skills/agent-work/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-work", 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.
Facts
- Skill name
agent-work- GitHub stars
- 83k
- Token cost
- ~3.6k tokens
- SKILL.md length
- 1,367 words
- Files
- 1
- Skills in repo
- 50
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Explains how LobeHub records Works, durable records of what an agent produced, covering registration, deduplication, versions, cards, type adapters and share-visitor access scopes.
- Works in 4 steps: packages/types/src/work.ts — extend… → packages/database/src/models/work/ToolRes… → packages/database/src/models/work/index.t… → …
- Adding a new Work type to the registry
- SKILL.md covers Type registry, Access scope (Agent Share…, Registration write paths and Display anchor & completion…, plus 3 more sections
- Calls gh and vercel
What it does
The skill is a maintainer guide to the Agent Work registry in LobeHub. A Work is a durable record of something an agent produced or touched, such as a GitHub PR or issue, a Linear issue, an office file, a document or a task. It appears as a card under the assistant message and accumulates versions, so one PR edited twice gives one card with history. Two tables hold the data: works, deduplicated by resource type and resource ID within a scope, and work_versions, which ignores retried registrations that reuse a tool call ID and carries provenance and cumulative cost and usage.
A single type registry lists the Work types (document, external, file and task) with an adapter for each, so a type added without an adapter fails to compile. Newer types are hidden behind a client opt-in, because released Electron clients lag and crash on unknown descriptors. For Agent Share visitors, every read and write carries an access scope that separates ordinary rows from share-stamped ones, and registration paths reachable from a visitor run must fail closed when no topic exists. Skill providers and CLI scanners fall under the same registry.
When your agent uses it
- Adding a new Work type to the registry
- Changing how Works are registered or deduplicated
- Making sure share-visitor runs cannot see or write the creator's Works
Example prompts
- “Add a new Work type for generated images and make sure it ships behind the opt-in.”
- “A retried registration created a duplicate card. Find out why deduplication did not catch it.”
- “Check that this new registration path uses the visitor run's access scope.”
Requirements
- A checkout of the LobeHub repository
Workflow steps
4 steps, taken from the first numbered list in SKILL.md.
- packages/types/src/work.ts — extend WORK_SKILL_PROVIDERS + WORK_PROVIDER_RESOURCE_TYPES (+ resource-type unions).
- packages/database/src/models/work/ToolResult.ts — write the normalizer; mirror linearToolResult.ts.
- packages/database/src/models/work/index.ts — add it to SKILL_TOOL_RESULT_NORMALIZERS (the satisfies forces this).
- Pick a stable cross-surface resourceId (the github lesson: choose the identity every surface can produce).
What it can do on your machine
Read from SKILL.md and the folder at commit 1863542. It shows what the files ask for, not the result of running them.
Tool permissions
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.
Runs code
Shell commands in SKILL.md call:
ghvercel
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use gh and vercel, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
LobeHub Agent Work Registry loads about 3.6k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 1,367 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.
Safety
Auto-check passed
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); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,367 words (~3,578 tokens).
“A Work is a durable record of something an agent produced or touched — a GitHub PR/issue, a Linear issue, an entity file (pptx/xlsx/docx/pdf), a document, a task. Works render as cards under the assistant message that produced them and…”
- name
- agent-work
- user-invocable
- false
Files
Just SKILL.md in .agents/skills/agent-work of lobehub/lobehub.
Open the folder on GitHubat commit 1863542
Compare with similar skills
LobeHub Agent Work Registry 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 |
|---|---|---|---|---|---|---|
| LobeHub Agent Work Registry this skilllobehub/lobehub | 83k | — | ~3.6k | Automated safety check: Pass | Custom licence | |
| Archify Diagramstt-a1i/archify | 79k | — | ~2.9k | Automated safety check: Pass | MIT | |
| Electron Multi-Process ArchitectureiOfficeAI/AionUi | 33k | 1 repos | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Backend Code Reviewlanggenius/dify | 158k | — | ~676 | Automated safety check: Pass | Custom licence | |
| Dark Architecture Diagram BuilderCocoon-AI/architecture-diagram-generator | 7.4k | 1 repos | ~2.1k | Automated safety check: Pass | MIT | |
| SVG Diagram GeneratorJimLiu/baoyu-skills | 26k | 1 repos | ~3.1k | Automated safety check: Pass | MIT |
Similar skills
Electron Multi-Process Architecture
iOfficeAI/AionUi
Tells the agent where new code belongs in an Electron multi-process project and which APIs each process may use, with rules for new bridges, services, agents and workers.
Backend Code Review
langgenius/dify
Reviews backend code under api/ for concrete, reproducible defects, routes to rule packs for architecture, schema, repositories and SQLAlchemy, and ranks findings from P0 to P3.
Dark Architecture Diagram Builder
Cocoon-AI/architecture-diagram-generator
Creates dark-themed system, cloud, security and network architecture diagrams as self-contained HTML files with inline SVG and CSS.
SVG Diagram Generator
JimLiu/baoyu-skills
Creates standalone dark-themed SVG diagrams, including architecture, flowchart, sequence, structural, mind map, timeline and state machine types.
Senior Architect Toolkit
maslennikov-ig/claude-code-orchestrator-kit
Comprehensive software architecture skill for designing scalable, maintainable systems using ReactJS, NextJS, NodeJS, Express, React Native, Swift, Kotlin…
More from lobehub/lobehub
All 50 skills in this repoLobeHub Interactive Prototype
lobehub/lobehub
Builds single-file interactive HTML prototypes rendered with the real LobeHub UI components and written as production-style React, so they can later be split into files.
Acceptance Evidence for Deliveries
lobehub/lobehub
Verifies a delivery end to end by driving the real product on a CLI, web, desktop or iOS Simulator surface, capturing evidence and publishing a round with the lh CLI.
Git Worktree Cleanup
lobehub/lobehub
Audits stale Git worktrees and branches with a bundled script, classifies each one, and deletes only after you approve the exact candidates.
LobeHub Alint Rule Set Maintenance
lobehub/lobehub
Maintains LobeHub's model-backed alint rule set: writing rules, removing false positives against real code, deciding warn versus error and tracking token cost.
LobeHub Builtin Tool Authoring
lobehub/lobehub
Guides building LobeHub builtin agent tools, from the manifest and execution runtime to executors, chat UI renders and registry wiring.
LobeHub Data Fetching Layers
lobehub/lobehub
Explains how LobeHub client code fetches data through services, SWR store hooks and cache keys, and when to avoid useEffect fetching or duplicated state.
Related
Categories
Questions about LobeHub Agent Work Registry
What does LobeHub Agent Work Registry do?
Explains how LobeHub records Works, durable records of what an agent produced, covering registration, deduplication, versions, cards, type adapters and share-visitor access scopes. The skill is a maintainer guide to the Agent Work registry in LobeHub. A Work is a durable record of something an agent produced or touched, such as a GitHub PR or issue, a Linear issue, an office file, a document or a task.
When should I use LobeHub Agent Work Registry?
LobeHub Agent Work Registry fits situations like: adding a new Work type to the registry; changing how Works are registered or deduplicated; making sure share-visitor runs cannot see or write the creator's Works.
How do I install LobeHub Agent Work Registry in Claude Code?
Run `npx skills add lobehub/lobehub --skill agent-work -a claude-code`. Or copy the skill folder (.agents/skills/agent-work in lobehub/lobehub) into .claude/skills/agent-work in your project. Claude Code loads it when a task matches its description.
How do I install LobeHub Agent Work Registry in Codex?
Run `npx skills add lobehub/lobehub --skill agent-work -a codex`. Or copy the skill folder (.agents/skills/agent-work in lobehub/lobehub) into .agents/skills/agent-work in your project. Codex loads it when a task matches its description.
Can I use LobeHub Agent Work Registry in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add lobehub/lobehub --skill agent-work -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-work, .gemini/skills/agent-work, .github/skills/agent-work and .opencode/skills/agent-work in your project.
What does LobeHub Agent Work Registry need to run?
Going by SKILL.md and its folder, LobeHub Agent Work Registry needs the command-line tools its instructions call (gh and vercel). Our summary lists: A checkout of the LobeHub repository.
Does LobeHub Agent Work Registry access the network?
SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is LobeHub Agent Work Registry safe to install?
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. Review the folder before installing.
What licence does LobeHub Agent Work Registry use?
LobeHub Agent Work Registry has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does LobeHub Agent Work Registry use?
About 3.6k tokens (SKILL.md is roughly 14k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to LobeHub Agent Work Registry?
Skills that share tags, products or a category with LobeHub Agent Work Registry: Archify Diagrams (tt-a1i/archify, 79k stars), Electron Multi-Process Architecture (iOfficeAI/AionUi, 33k stars), Backend Code Review (langgenius/dify, 158k stars) and Dark Architecture Diagram Builder (Cocoon-AI/architecture-diagram-generator, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains LobeHub Agent Work Registry?
lobehub (a GitHub organization) maintains it in lobehub/lobehub, which has 83,023 GitHub stars. The repository holds 50 skills in this directory. The repository was last updated on October 7, 2026.
Source: lobehub/lobehub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.