sporkwace/monkey-thought-translator
translate claude skills into chatgpt or codex skills only after auditing purpose, target host, capability parity, resource portability, tool assumptions, and unrealizable behavior. use when the user uploads or points to a claude skill, asks to port a claude skill to chatgpt, codex, or openai skills, or wants a compatibility review before translation. requires a compatibility report, risk score, capability matrix, and user approval before packaging when behavior cannot be preserved faithfully.
83
90%
Does it follow best practices?
Impact
89%
2.34xAverage score across 2 eval scenarios
Passed
No known issues
Evaluation results
78%
39%Port the Notion Task Dashboard to ChatGPT
Approval gate on connector-dependent skill
Compatibility report produced
100%
100%
Capability matrix present
100%
100%
Connector classified host-dependent
0%
100%
Credential assumption documented
40%
100%
Risk score high or blocked
0%
100%
Approval gate triggered
0%
0%
Direct approval wording used
0%
0%
No overbroadening
100%
100%
Translation mode named
0%
100%
Host-specific assumptions listed
50%
100%
100%
63%Translate Our Meeting Summarizer Skill to ChatGPT
Clean port with kebab naming and OpenAI metadata
Name normalized to kebab-case
0%
100%
agents/openai.yaml created
0%
100%
openai.yaml has display name
25%
100%
openai.yaml has icon field
0%
100%
openai.yaml has accent color
0%
100%
Frontmatter description is lower-case
0%
100%
Frontmatter includes trigger conditions
50%
100%
Claude runtime references replaced
100%
100%
skill.zip produced
100%
100%
Round-trip review present
50%
100%
- Evaluated
- Agent
- Claude
- Model
- Claude Sonnet 4.6