algal/sparky/solveit-tools
Claude Code and agent skill by algal/sparky
- community
Checking that the SKILL.md file is still in the repository.
Read, edit, and execute SolveIt dialogs (notebooks) via CLI. Add code/note/prompt cells, run them, and inspect outputs.
Install
npx vskill@latest install algal/sparky/solveit-toolsSKILL.md
SolveIt Dialog Tools
Manipulate SolveIt dialogs (similar to Jupyter notebooks) via CLI. A dialog contains messages (cells) of type code, note (markdown), prompt (AI prompt/response), or raw.
Every command takes a dialog URL as its first argument and returns JSON to stdout.
Invocation
Commands
read_dialog — Read all messages
Returns:
Use id values to reference messages in other commands. The output field is omitted when empty.
add_message — Add a new message
| Flag | Values | Default | Notes | |
|---|---|---|---|---|
--type | code, note, prompt, raw | code | ||
--placement | at_end, at_start, after, before | at_end | ||
--ref-id | message ID | — | Required when placement is after or before |
Returns the new message: {"id": "_abc123", "type": "code", "content": "print('hello')"}.
exec_message — Execute a single message
Executes the message and waits for the result (default timeout: 60s). Returns the message with its output:
update_message — Change content or type
Provide --content, --type, or both. Returns the updated message.
delete_message — Remove a message
Returns {"id": "_ea386899", "deleted": true}.
run_dialog — Execute the entire dialog
Runs all cells front-to-back using SolveIt's intelligent defaults: code cells are executed, prompt cells and cells with existing output are skipped. Default timeout: 120s.
Returns a summary:
Use read_dialog afterward to inspect the full results.
Typical workflow
- Read the dialog to understand its current state
- Add or update messages as needed
- Execute individual messages with
exec_message, or run everything withrun_dialog - Read again to inspect outputs
Message types
| Type | Content | Output | Execution | |
|---|---|---|---|---|
code | Python source | Execution result | Runs in SolveIt kernel | |
note | Markdown text | — (never has output) | Not executable | |
prompt | Natural language prompt | AI-generated response | Sends to SolveIt AI | |
raw | Raw text/HTML | — | Not executable |
Rules
- Always quote the URL in shell commands — it contains special characters (
?,&,%). - Message IDs look like
_ea386899(underscore + 8 hex chars). Always use the exact ID fromread_dialog. - After
run_dialog, check results withread_dialog— the summary only shows counts. - Errors from the tool are JSON on stderr:
{"error": "..."}.
Security
- Security scanPassed, 100 of 100Pattern checks on the skill's files.
- Model reviewNot runA model review is scheduled for the next rescan.
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingopenclaw_configs/workspace/skills/solveit-tools/SKILL.md
Popularity
- Repository stars
- 75
- Repository forks
- 9
- 7-day trend score
- 22
Stars and forks are for the whole GitHub repository, not this skill alone. Refreshed 5 Apr 2026, 7 months ago.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/algal/sparky/solveit-tools)