- name
SKILL.md
技能檔案保留在發布者的儲存庫中。
在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add glebis/claude-skills --skill bridgework -a cursor -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add glebis/claude-skills --skill bridgework -a claude-code -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add glebis/claude-skills --skill bridgework -a codex -y在終端機中貼上複製的指令。它會將這個 SKILL.md 安裝到對應的代理中。
npx skills add glebis/claude-skills --skill bridgework -a grok -y在 Grok Bot 聊天中傳送複製的訊息。Bot 會從 GitHub 取得這個 SKILL.md,並加入你所有 Bot 共用的技能中。
Install this skill: https://github.com/glebis/claude-skills/tree/HEAD/bridgework來自發布者
Two phases: audit the person's stack into a stack file, then serve the Bridgework canvas on it. The canvas runs locally, connects to nothing and calls no model. Every step in it can produce a prompt (Sources, Ideas or Build) to paste into an agent.
Everything about the person lives in ~/.bridgework/, never in this skill folder. The skill's own demo is synthetic.
audit.py with a category the person has not agreed to in this conversation. Show the plan first.e2e-verified unless the person ran it.scripts/serve.sh demo (port 4174) in the background and open it. Skip if the person wants their own stack straight away.python3 scripts/audit.py --plan and show the person what each category reads. Then ask, with a multi-select question, which categories to allow: apps, clis, mcp, models, keys, or none (interview only). Explain that keys lists variable names such as OPENAI_API_KEY and never their values.python3 scripts/audit.py --categories <agreed> writes ~/.bridgework/audit.json and prints a summary. Without --categories it reads nothing.references/interview.md: confirm the matches, pick relevant unmatched items, then ask about what a scan cannot see (phone and watch data, hosted accounts, other machines, known dead ends). Keep it short: three or four questions per round, two rounds at most.~/.bridgework/stack.json. Catalog tools use {"use": "<id>"} and keep the audit's signals. Anything else becomes a custom part, classified with the types, domains and places in references/stack-format.md. Record known dead ends as gaps so they are drawn broken, never as working arrows.python3 scripts/build_stack.py ~/.bridgework/stack.json builds ~/.bridgework/site. It validates everything first; on errors it lists each problem and writes nothing. Fix the stack file and rerun.scripts/serve.sh serves the site on http://localhost:4175 (run it in the background). The demo uses 4174, so the two keep separate saved trails.To update later, rerun the audit (with permission again) and the interview for what changed, edit stack.json, and rebuild. The builder only replaces a folder it created.
scripts/audit.py: consent-gated, read-only scan. --plan reads nothing. --home and --root point it at a test folder.scripts/catalog.json: about 50 known tools, each with read-only detection rules and a takes/does/gives template. Add a tool here when the same unknown keeps coming up.scripts/build_stack.py: stack file to site, with validation. Keeps built-in examples and unlocks only when all their parts exist.scripts/serve.sh: local server. demo, your site, or any folder and port.references/interview.md: interview questions, consent wording, and how to read the audit.references/stack-format.md: stack file format and the allowed types, domains, places and evidence levels.assets/app/: the canvas, with the synthetic demo in data/. assets/app/INTERACTION.md explains the interaction design. Tests: npm test there, and PORT=4174 sh tests/run-browser.sh with the demo served (needs Playwright and Chrome).This skill should be used when someone wants to see what their tech stack could do in combination. It first audits the stack (an optional, consent-gated, read-only scan of this Mac plus a short interv
---name: bridgeworkdescription: This skill should be used when someone wants to see what their tech stack could do in combination. It first…---# bridgework/SKILL.md總覽
This skill should be used when someone wants to see what their tech stack could do in combination. It first audits the stack (an optional, consent-gated, read-only scan of this Mac plus a short interview), then builds and serves Bridgework, a local canvas for practising "what could these two capabilities do together?", with a prompt for an agent at every step. Triggers on "audit my stack", "what could my tools do together", "map my tech stack", "find combinations in my stack", "bridgework", "open the bridgework canvas", or "show the bridgework demo".
常見問題
從發布者下載 bridgework/SKILL.md,或複製路徑後開啟儲存庫。PlugMCP 只收錄這項技能,不代管檔案。
發布者將它存放在 https://github.com/glebis/claude-skills。
Claude、Cursor、Codex 和 Grok Build 可以讀取你從發布者儲存庫加入的 SKILL.md。在聊天中傳送技能的 GitHub 資料夾連結,Grok Bot 就會安裝它。