gaia-research/gaia-skill-tree / .agents/skills/fuse
fuse
FlaggedCombine two AI agent skills into one. Trigger phrases: /fuse, "fuse these skills", "combine skills", "merge these two skills", "create a fusion skill"
| File | Kind | Size |
|---|---|---|
| .gitignore | other | 41 B |
| CITATION.cff | other | 818 B |
| LICENSE | other | 1.0 KB |
| README.md | markdown | 11.0 KB |
| SKILL.md | skill md | 1.3 KB |
| install.sh | script | 651 B |
| powered-by-gaia.svg | other | 1.2 KB |
| reference/compose.md | markdown | 2.1 KB |
| reference/detect.md | markdown | 1.0 KB |
| reference/name.md | markdown | 772 B |
| reference/register.md | markdown | 1.4 KB |
| scripts/candidates.sh | script | 1.7 KB |
| scripts/validate.sh | script | 1.0 KB |
reference/detect.md
View on GitHub# Step 1: Detect
Identify the two source skills to be fused.
## Input Resolution
- If the user provided two explicit skill names (e.g., `/fuse shape + audit` or `/fuse shape and audit`), use those directly.
- Otherwise, locate the skills directory and scan it for installed skills.
## Scanning Installed Skills
1. Scan directories under the detected skills directory (`.agents/skills/`, `.claude/skills/`, or `.cursor/rules/`).
2. For each directory:
- Verify if a `SKILL.md` (or relevant `.md` rule/definition) exists.
- Read the file and extract the skill `name` and the first line of the description from the YAML frontmatter.
3. Present the list of detected skills to the user as a numbered list.
4. Prompt the user to select two skills (e.g., `1 and 3` or `shape and audit`) or confirm a suggested pair.
## Script Automation
To get a quick machine-readable list of available candidates, run:
```bash
bash scripts/candidates.sh
```
## Output
Two verified file paths pointing to the source skill directories.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |