Individual skill
script-designer
Use when reading or modifying the script content of the exact SmartCMP script definition selected by an embedded script-editor page Context.
providers/SmartCMP-Provider/skills/script-designer/SKILL.md
Source commit db698ba4ea05891c944117a0f0cf71b81463b42a
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Network or broad shell
- Last checked
- Nov 4, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 17
- Repository last updated
- Nov 2, 2026
- License
- Apache-2.0
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- agentic-workflow Repository topic
- ai-integration Repository topic
- openclaw Repository topic
- writing Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Browse files
SKILL.mdcore · 2,986 bytesSKILL.mdcore · 2,986 bytesscripts/read_current_script.pyruns · 2,119 bytes
Read excerpt
# script-designer
Read the current saved SmartCMP script and produce user-directed replacement content.
## Workflow
1. Always call `smartcmp_read_current_script_definition` before analyzing or changing the script. Never ask the user for a script ID that is already bound by Context.
2. Use the returned script type, parameters, properties, form content, resource types, and complete current body as the source of truth. In this first phase, all fields except `content` are read-only compatibility context.
3. Apply only the requested behavior. Preserve unrelated logic, public entrypoints, parameter names, return contracts, runtime compatibility, and error semantics.
4. Return the complete updated script body in one fenced code block. Never return only a diff, partial snippet, or content containing ellipsis placeholders.
5. Do not propose replacement values for `params`, `properties`, `formContent`, or other script-definition metadata. If the requested behavior requires one of those fields to change, state that the current Skill only generates `content` and identify the unmet metadata change separately.
6. State that the result is for manual review and copying into the CMP script `content` field. Do not claim that the script was saved, published, or executed.
## Safety