菜单
Rebuild and republish the CR-task master tracker artifact. Use when the user says "refresh cr tracker", "update the CR task tracker", "/refresh-cr-tracker", or wants the conceptual-reasoning task master list re-pulled from live reasoning-tasks data + GitHub issues and redeployed to its claude.ai artifact.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Coordinate a two-agent planner/reviewer loop across live Emacs agent sessions. Use when the user asks to orchestrate Claude/Fable and Codex, run paired model review, converge a plan through back-and-forth review, monitor agent sessions until completion, or make a multi-agent review process unattended.
Use when a LuLu firewall alert is open on this Mac and the user asks whether to allow or block it, or asks to inspect, check, audit, or review the connection a LuLu alert is prompting about. Covers explicit $review-lulu-alert requests and questions like "should I allow this?", "what is this process connecting to?", or "is this LuLu prompt safe?".
Dotfiles and Emacs package routing context. Use when working in ~/My Drive/dotfiles, editing emacs/config.org or emacs/extras, choosing between the dotfiles repo and an elpaca source clone, or applying dotfiles documentation and commit conventions.
Dotfiles and Emacs package routing context. Use when working in ~/My Drive/dotfiles, editing emacs/config.org or emacs/extras, choosing between the dotfiles repo and an elpaca source clone, or applying dotfiles documentation and commit conventions.
Audit a macOS .app before running it or granting permissions, especially when the user asks whether a Mac app is safe, suspicious, malware, from an unknown developer, or requests screen recording, accessibility, camera, microphone, input monitoring, or other sensitive permissions.
Scan for exposed API keys and leaked credentials, audit dependency vulnerabilities, review macOS hardening settings, and evaluate Claude Code configuration risks. Use when the user wants a security review, vulnerability scan, dependency audit, secrets check, or periodic security posture assessment.
| name | refresh-cr-tracker |
| description | Rebuild and republish the CR-task master tracker artifact. Use when the user says "refresh cr tracker", "update the CR task tracker", "/refresh-cr-tracker", or wants the conceptual-reasoning task master list re-pulled from live reasoning-tasks data + GitHub issues and redeployed to its claude.ai artifact. |
Rebuilds ~/Trajectory/cr-scout-runs/cr-task-master-list.html from live sources and
redeploys it to the existing claude.ai artifact (so newly-registered GitHub issues, new
cohort tasks, and updated scores show up).
Must run in an INTERACTIVE session — the Artifact tool is not available in headless
claude -p or cloud routines. Requires the local ~/Trajectory/reasoning-tasks/main worktree and
a working gh/GitHub token (both present on Pablo's Mac).
Build. Run:
python3 ~/Trajectory/cr-scout-runs/cr-tracker/build.py
It re-derives every row from the reasoning-tasks branches (ryan/cr-collect-cohort results +
crawler pools, ryan/collect-lw-gdocs, pablo/cr-scout-batch-1), fuzzy-matches gdoc
tasks to source articles, re-queries GitHub issues via the REST API, verifies each task
dir exists before linking, dedupes, regenerates the HTML, and prints a one-line JSON
summary (rows / links / words / issues / task_links / html_sha). Takes ~1–2 min.
Redeploy (only on a successful build). Use the Artifact tool with:
file_path: /Users/pablostafforini/Trajectory/cr-scout-runs/cr-task-master-list.htmlurl: https://claude.ai/code/artifact/15852b96-f4b3-4838-b35f-e8b3fd941012favicon: 🎯label: manual-refreshReport the JSON summary (rows / article-links / word-counts / issues) and confirm the artifact URL was redeployed.
~/Trajectory/cr-scout-runs/cr-tracker/README.md.git push of the regenerated HTML is not required — the artifact is the deliverable;
pushing the repo is optional bookkeeping and stays gated on Pablo's explicit OK.