skills/skill-packager/SKILL.md
Package a skill directory into a distributable `.skill` archive placed on the Desktop. Use when the user asks to "package", "bundle", "zip up", "export", "distribute", or "ship" a skill, or mentions creating a `.skill` file from `~/.claude/skills/<skill-name>/`.
npx skillsauth add danishi/claude-code-config skill-packagerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Compresses ~/.claude/skills/<skill-name>/ into ~/Desktop/<skill-name>.skill — a zip archive with a .skill extension, ready for sharing or installation via Claude Desktop.
Determine which skill to package from the user's request.
ls ~/.claude/skills/
List every file that will be included, so the user can spot anything unexpected before it ships:
cd ~/.claude/skills/<skill-name> && \
find . -type f \
-not -path '*/__pycache__/*' \
-not -name '*.pyc' \
-not -name '.DS_Store' \
| sort
Confirm that caches (__pycache__/, *.pyc) and OS metadata (.DS_Store) are excluded. Flag anything suspicious before zipping — large binaries, credentials, .env files, local-only configs, personal data — and confirm with the user if in doubt.
.skill archivecd ~/.claude/skills/<skill-name> && \
zip -r ~/Desktop/<skill-name>.skill . \
-x '__pycache__/*' '*/__pycache__/*' '*.pyc' '.DS_Store' '*/.DS_Store'
~/Desktop/<skill-name>.skillSKILL.md or supporting scripts accordingly.Confirm the archive exists and report its path and size:
ls -lh ~/Desktop/<skill-name>.skill
Tell the user the full output path and the file size. If the archive is unexpectedly large (e.g., >5 MB for a typical skill), suggest reviewing Step 2's file list for accidentally-bundled assets.
tools
Produce rich, finished video content with React Remotion by orchestrating the repository's media-generation skills (nanobanana for images, veo for video clips, lyria for BGM, gemini-tts for narration) and composing them on a data-driven Remotion timeline. Follows an approval-gated workflow: first return a video composition plan for the user to approve, then generate assets, compose, run a multimodal self-review loop, and deliver only when the result meets the quality bar. Use when the user wants to "create a video", "make a promo / explainer / social clip", or combine images, video, music, and voiceover into one polished video.
tools
Generate videos using Google Gemini Veo 3.1. Defaults to the cost-effective Veo 3.1 Lite model; the premium (Veo 3.1) and Fast models are used only when explicitly requested via --pro / --fast. Supports text-to-video and image-to-video (first frame + optional last frame), 16:9 / 9:16, 720p / 1080p (4k on Pro), 4-8s clips, and 1-4 videos per request. Works with both the Gemini Developer API and Vertex AI.
tools
Salesforce CLIを使ってSalesforceのデータ操作・管理を行うスキル。 取引先・商談・プロジェクト・外注管理のCRUD操作、SOQLクエリ、パイプライン分析、レポート生成を実行する。 ユーザーがSalesforceのデータを照会・更新・分析したいとき、商談のステージを確認・変更したいとき、 プロジェクトや外注の状況を確認したいとき、売上・粗利・パイプラインのレポートが必要なとき、 取引先や案件の情報を調べたいとき、SOQLクエリを実行したいときに使用する。 「Salesforce」「SF」「商談」「取引先」「パイプライン」「案件」「プロジェクト」「外注」「粗利」 「売上」「受注」「失注」「ステージ」「SOQL」などのキーワードが含まれる場合はこのスキルを使う。 Salesforceに関する質問や操作依頼であれば、明示的にスキル名を言及していなくても積極的にこのスキルを使用すること。
development
Generate and edit images using Google Gemini (Nano Banana Pro / Nano Banana 2). Automatically selects the best model based on prompt complexity. Supports text-to-image generation, image editing with reference images, configurable aspect ratios, 1K/2K/4K output, Google Search grounding, and batch generation. Works with both Gemini Developer API and Vertex AI.