- Python 65%
- Shell 13.6%
- JavaScript 10.9%
- PowerShell 10.5%
| Filename | Latest commit message | Latest commit date |
|---|---|---|
dev
604b0d930a
Use host tools for vault and S3 checks, and Python for structured Dedaub, Vykar, and model guidance workflows. Keep the skill catalog limited to tracked folders and document platform requirements. |
||
| browserless | ||
| dedaub-decompile | ||
| full-audit | ||
| gui-responsiveness | ||
| model-effort-recommendation | ||
| obsidian-safe-write | ||
| onchain-audit | ||
| s3-ops | ||
| vykar-ops | ||
| .gitignore | ||
| LICENSE | ||
| README.md | ||
Agent Skills
Portable Agent Skills for browser automation, contract decompilation, correctness audits, on-chain diagnosis, provider-scoped model selection, safe Obsidian writes, and Vykar operations.
Skills
| Skill | What it does |
|---|---|
| browserless | Opens rendered web pages through a configured Browserless service for screenshots, PDFs, and browser sessions. |
| dedaub-decompile | Saves decompiled source for a deployed EVM contract through a signed-in Dedaub session. |
| full-audit | Audits an application for correctness bugs, fixes them, and verifies the fixes against real behavior. |
| gui-responsiveness | Measures and fixes UI stalls using a profiler and UI-thread watchdog. |
| model-effort-recommendation | Recommends a model and reasoning setting from current provider guidance and local availability. |
| obsidian-safe-write | Checks vault space and inodes before writes, optionally runs a configured cleanup hook, then verifies the result. |
| onchain-audit | Checks live on-chain systems for accessor inconsistencies and silent stoppages. |
| s3-ops | Manages S3-compatible buckets and objects using explicit endpoints and protected credentials. |
| vykar-ops | Installs, updates, checks, and operates Vykar backups. |
Supported clients
| Client | Project location | User location |
|---|---|---|
| AGY / Google Antigravity | .agents/skills/<skill-name>/ |
~/.gemini/config/skills/<skill-name>/ |
| Claude Code | .claude/skills/<skill-name>/ |
~/.claude/skills/<skill-name>/ |
| Codex CLI | .agents/skills/<skill-name>/ |
~/.codex/skills/<skill-name>/ |
| Cursor | .cursor/skills/<skill-name>/ or .agents/skills/<skill-name>/ |
~/.cursor/skills/<skill-name>/ or ~/.agents/skills/<skill-name>/ |
| Gemini CLI | .gemini/skills/<skill-name>/ or .agents/skills/<skill-name>/ |
~/.gemini/skills/<skill-name>/ or ~/.agents/skills/<skill-name>/ |
| GitHub Copilot | .github/skills/<skill-name>/, .claude/skills/<skill-name>/, or .agents/skills/<skill-name>/ |
~/.copilot/skills/<skill-name>/ or ~/.agents/skills/<skill-name>/ |
| OpenCode | .opencode/skills/<skill-name>/, .claude/skills/<skill-name>/, or .agents/skills/<skill-name>/ |
~/.config/opencode/skills/<skill-name>/, ~/.claude/skills/<skill-name>/, or ~/.agents/skills/<skill-name>/ |
Copy the complete skill directory to the applicable location. Each directory follows the open Agent Skills format and can also be installed in another client that explicitly documents support for that format.
Each agents/openai.yaml file is runtime metadata consumed by Codex. The other YAML files in agents/ are compatibility records with verified client paths and activation behavior; those clients consume SKILL.md directly rather than reading the sidecars.
Host compatibility
| Skills | Linux/macOS | Windows |
|---|---|---|
obsidian-safe-write, s3-ops |
Shell and host tools | PowerShell 5.1 and host tools |
dedaub-decompile, model-effort-recommendation, vykar-ops |
Python 3.11+ | Python 3.11+ |
| Other skills | Host tools or configured services | Host tools or configured services |
The Dedaub JavaScript payload runs in Browserless; it does not require local Node. Linux has fixture and selected live checks. macOS and Windows have static and fixture verification, not native runtime tests.
Keep endpoints, credentials, vault paths, runtime caches, and service-specific settings in the external configuration locations documented by each skill.
Validate each skill against the Agent Skills specification after installation. Run the focused tests in a skill's scripts/ directory when changing its helpers.
License
MIT — see LICENSE.