Minimize token waste in all bash, file, and data processing operations. ALWAYS apply these principles whenever executing commands, reading files, or processing output. This skill governs how an LLM agent interacts with the system — it applies to every task involving tool use, file reading, data processing, or shell commands. TRIGGER on any computer use whatsoever. --- # Token-Efficient Computer Use Every character of stdout returned from a tool call gets tokenized and billed. A single careless `cat` on a 2000-line JSON file costs as much as a thoughtful conversation turn. The goal isn't to memorize specific commands — it's to internalize a simple cost model: **each byte of tool output is money and context window spent**, and each tool call has fixed round-trip overhead on top of that. Two questions should precede every tool call: 1. **Can I avoid this call entirely?** If the information is already in context from a previous read or from the user, use it. 2. **If I must call, how do I minimize the bytes returned?** Filter, project, truncate, or count at the source rather than dumping raw output.
Expert guide for CV181X/CV182X/CV180X (SG200X) multimedia development using CVI MPI API. Use this skill when working with: VI (video input/camera/ISP), VPSS (video processing/scaling/crop), VENC (H.264/H.265/JPEG encoding), VDEC (decoding), VB (video buffer pools), SYS binding, or any CVI_* API calls. Covers camera pipeline setup, offline VPSS processing, VB pool planning, and error diagnosis (ERR_VPSS_NOBUF, ERR_VB_NOBUF). API details in references/.
Skill files are scattered across GitHub and communities, difficult to search, and hard to evaluate. SkillWink organizes open-source skills into a searchable, filterable library you can directly download and use.
We provide keyword search, version updates, multi-metric ranking (downloads / likes / comments / updates), and open SKILL.md standards. You can also discuss usage and improvements on skill detail pages.
Sort by downloads/likes/comments/updated to find higher-quality skills.
4. Which import methods are supported?
Upload archive: .zip / .skill (recommended)
Upload skills folder
Import from GitHub repository
Note: file size for all methods should be within 10MB.
5. How to use in Claude / Codex?
Typical paths (may vary by local setup):
Claude Code:~/.claude/skills/
Codex CLI:~/.codex/skills/
One SKILL.md can usually be reused across tools.
6. Can one skill be shared across tools?
Yes. Most skills are standardized docs + assets, so they can be reused where format is supported.
Example: retrieval + writing + automation scripts as one workflow.
7. Are these skills safe to use?
Some skills come from public GitHub repositories and some are uploaded by SkillWink creators. Always review code before installing and own your security decisions.
8. Why does it not work after import?
Most common reasons:
Wrong folder path or nested one level too deep
Invalid/incomplete SKILL.md fields or format
Dependencies missing (Python/Node/CLI)
Tool has not reloaded skills yet
9. Does SkillWink include duplicates/low-quality skills?
We try to avoid that. Use ranking + comments to surface better skills: