Make the plugin read cleanly in public by clarifying score labels, tightening marketplace copy, and aligning the skill and agent names with the review flow.
Made-with: Cursor
Publish the Agent Compatibility plugin (CLI-backed scans, subagent prompts,
orchestration skill) to the official marketplace with marketplace listing and
README table entry.
Made-with: Cursor
Apply a full path and identifier rename for the plugin (folder, hooks, skill path, marketplace source, and docs) so installation and references consistently use continual-learning.
Co-authored-by: Cursor <cursoragent@cursor.com>
Rename the learning plugin slug to teaching across marketplace metadata and docs, and add the reused data-science avatar to continuous-learning while preserving plugin validation.
Co-authored-by: Cursor <cursoragent@cursor.com>
Keep only core plugins plus a new continuous-learning plugin with hook+skill wiring, and update marketplace listings to match the reduced set.
Co-authored-by: Cursor <cursoragent@cursor.com>
Align marketplace metadata, plugin manifest, docs, and install instructions with the new Team Kit folder and package identifier.
Co-authored-by: Cursor <cursoragent@cursor.com>
Update user-facing plugin names and marketplace copy to use the new Team Kit branding while keeping the existing slug for compatibility.
Co-authored-by: Cursor <cursoragent@cursor.com>
* Add Ralph Loop plugin
Port of the Ralph Wiggum technique from Claude Code to Cursor.
Runs Cursor in a self-referential loop, feeding the same prompt
back after every turn until a completion condition is met.
Components:
- Stop hook that intercepts session exit and re-injects the prompt
- Setup script for initializing loop state
- Skills for starting, cancelling, and explaining the loop
Co-authored-by: Cursor <cursoragent@cursor.com>
* Comply with Cursor hooks API
- Rewrite hooks.json to Cursor format (version 1, lowercase event
names, flat structure, loop_limit: null)
- Replace Claude Code stop hook output (decision/block/reason) with
Cursor's followup_message API
- Add afterAgentResponse hook to detect completion promise without
depending on transcript format
- Use CURSOR_PROJECT_DIR env var for reliable state file paths
- Remove setup script; ralph-loop skill now instructs the agent to
create the state file directly
- Update cancel-ralph skill to clean up done flag file
Co-authored-by: Cursor <cursoragent@cursor.com>
* Move state files to .cursor/ralph/ subdirectory
State file: .cursor/ralph/scratchpad.md
Done flag: .cursor/ralph/done
Cancel cleans up with rm -rf .cursor/ralph
Co-authored-by: Cursor <cursoragent@cursor.com>
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
- Convert all H1 headings to sentence case across skills, rules, agents,
commands, and READMEs (~65 headings)
- Replace em-dashes with colons in plugin.json descriptions and README
taglines to match marketplace.json convention
- Replace semicolons with periods and restructure sentences across skills,
rules, agents, and READMEs (~19 instances)
Co-authored-by: Cursor <cursoragent@cursor.com>
Introduce a dedicated meta plugin with scaffold and submission-review workflows so teams can create marketplace-ready Cursor plugins with consistent structure and metadata. Register the plugin in marketplace metadata and the root plugin index.
Co-authored-by: Cursor <cursoragent@cursor.com>
Consolidate the repo around the new domain plugins and Cursor Dev Kit workflows while removing legacy plugin content. Update manifests and README listings to reflect the current plugin reality.
Co-authored-by: Cursor <cursoragent@cursor.com>
ericzakariasson