Independent adversarial review of plan.md before task generation. Prefer an opposite-runtime CLI reviewer that writes reviews/planreview.md directly; fall back to Caspar subagents only when unavailable. Trigger after createplan and before createtasks. Do NOT review generated tasks, finished code, or apply scope changes.
EnglishLightweight scope→research→plan workflow for small/medium tasks (bug fixes, small features). Confirms functional scope with the user, runs parallel read-only research, then writes a quicktaskplan.md with phased parent/sub-task structure. Trigger when the user wants a quick plan for a bounded change and full /caspar:plan task-generation would be overkill. Do NOT trigger for large/multi-area features (route to /caspar:plan + /caspar:createtasks) or for pure execution with a plan already in hand.
EnglishUse when the user wants to search the project's captured knowledge, recall a specific past learning, or discover what learnings already exist (e.g. \"/caspar:recall\", \"what do we know about X\", \"is there a learning for Y\"). Do NOT trigger to capture or write new knowledge — that is /caspar:learn.
EnglishRun the lightweight Caspar release flow: commit pending Caspar changes, sync Codex assets, run tests, bump marketplace/plugin/package versions, commit and push, refresh the user-level Codex install, and print the Claude Code marketplace update command. Use when the user asks to release, ship a Caspar version, bump Caspar, or update local installs after Caspar prompt/plugin changes.
EnglishLight pre-commit cleanup pass — diff sanity, log/dead-code hygiene on changed files, strict lint, run related + broad tests, then conventional-commit. Use when wrapping up uncommitted or just-finished work before check-in (\"sweep\", \"clean up and commit\", \"tidy this diff\"), standalone or as the final phase of caspar-clean. Do NOT use for forensic dead-code removal across the codebase (use caspar-prune), for authoring new tests (use caspar-test), or as a full validation gate — this is a fast hygiene+commit pass, not deep review.
English
AGENT SKILLS ATLASIncludes Caspar Plan Review, Caspar Quick Dev, Caspar Recall, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Caspar Plan Review
Independent adversarial review of plan.md before task generation. Prefer an opposite-runtime CLI reviewer that writes reviews/planreview.md directly; fall back to Caspar subagents only when unavailable. Trigger after createplan and before createtasks. Do NOT review generated tasks, finished code, or apply scope changes.
Caspar Quick Dev
Lightweight scope→research→plan workflow for small/medium tasks (bug fixes, small features). Confirms functional scope with the user, runs parallel read-only research, then writes a quicktaskplan.md with phased parent/sub-task structure. Trigger when the user wants a quick plan for a bounded change and full /caspar:plan task-generation would be overkill. Do NOT trigger for large/multi-area features (route to /caspar:plan + /caspar:createtasks) or for pure execution with a plan already in hand.
Caspar Recall
Use when the user wants to search the project's captured knowledge, recall a specific past learning, or discover what learnings already exist (e.g. \"/caspar:recall\", \"what do we know about X\", \"is there a learning for Y\"). Do NOT trigger to capture or write new knowledge — that is /caspar:learn.
Caspar Release
Run the lightweight Caspar release flow: commit pending Caspar changes, sync Codex assets, run tests, bump marketplace/plugin/package versions, commit and push, refresh the user-level Codex install, and print the Claude Code marketplace update command. Use when the user asks to release, ship a Caspar version, bump Caspar, or update local installs after Caspar prompt/plugin changes.
Caspar Sweep
Light pre-commit cleanup pass — diff sanity, log/dead-code hygiene on changed files, strict lint, run related + broad tests, then conventional-commit. Use when wrapping up uncommitted or just-finished work before check-in (\"sweep\", \"clean up and commit\", \"tidy this diff\"), standalone or as the final phase of caspar-clean. Do NOT use for forensic dead-code removal across the codebase (use caspar-prune), for authoring new tests (use caspar-test), or as a full validation gate — this is a fast hygiene+commit pass, not deep review.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Caspar Plan Review skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.