becc256497
docs: update CLI references from belt app/skill store to belt app/skill list
2026-08-03 17:41:07 +02:00
a82f5eb2d5
index affirmations in .claude-plugin/plugin.json
2026-07-26 15:44:38 +02:00
04f065fb4f
add affirmations skill under new guides/agent category
...
Agent self-regulation skill: read when stuck, looping, or on a mistake
streak, then re-ground on verified observations and take one small step.
Not topic-specific.
Also adds an "Agent Practice" grouping to skills.sh.json and a README row.
2026-07-26 15:43:27 +02:00
fbe0aa4ac8
copy: remove all hardcoded "250+" app counts from SKILL.md files
2026-07-10 20:14:03 +02:00
601a457f7e
add skills.sh.json for repo page groupings on skills.sh
2026-06-09 08:25:42 +02:00
abf84461a1
organise for discoverability
2026-05-20 12:15:26 +02:00
624ce7bbed
Fix GPU model loading guidance: use device_map for large models
...
The previous advice ("never use device_map") caused 7x slower loading
for large models. device_map streams weights disk→GPU directly via
Accelerate, skipping CPU materialization entirely.
2026-05-18 18:00:56 +02:00
97c9494a19
Update CLI references: list/search = yours, store = public
...
Align all docs with new belt app/skill command structure.
2026-05-16 14:29:23 +02:00
c968aac3da
Create SKILL.md
2026-05-16 10:04:57 +02:00
7631a58b56
Update Seedance 2.0 documentation with Studio variants and multimodal
...
reference guide
Add Studio model variants with private asset library support for
enhanced portrait consistency. Reorganize examples with clearer
multimodal reference patterns including video editing and extension use
cases. Add comprehensive prompt guide with formulas for referencing
assets and update parameter documentation with new
reference_images/videos/audios arrays and safety_identifier.
2026-05-13 14:48:39 +02:00
b576e8ec6a
Add belt CLI installation instruction to all skill guides
2026-05-12 18:22:57 +02:00
bdcd42849b
Add Inworld TTS models to audio and avatar tools
...
Inworld TTS-2 (100+ languages, emotion steering) and TTS 1.5 (ultra-low
latency) are now featured across text-to-speech, AI voice cloning, and
avatar video tools. Added examples for character voices, delivery modes,
and UGC generation workflows.
2026-05-12 16:36:26 +02:00
83e38aa6a0
Update Seedance examples to version 2.0 and add audio generation
...
Update all references from Seedance 1.5 Pro to Seedance 2.0,
add Seedance 2.0 Fast variant, and enable audio generation in
video examples. Add ratio parameter where applicable.
2026-05-12 15:27:56 +02:00
ac03de9089
types
...
Update Seedance 2.0 API and documentation
This updates all references from separate Seedance 2 T2V/I2V/R2V models
to the unified Seedance 2.0 model with updated API parameters and
capabilities. The new model supports up to 1080p resolution and
consolidates all video generation modes (text/image/reference-to-video)
into a single endpoint.
2026-05-12 15:26:43 +02:00
43375db081
Update symlink helper sharing guidance and add OneOf input patterns
...
Symlink helper modules now require `__init__.py` and relative
imports for validator resolution. Add comprehensive OneOf input
pattern documentation for both Python and Node SDKs, showing how
to use `anyOf` + `x-promoted` for mutually exclusive input options.
2026-05-11 13:10:08 +02:00
bfce6d5a98
Update installation comment for clarity
2026-05-05 23:16:23 +02:00
c5ad36cc72
Update CLI installation instructions with multiple methods
...
Add alternative installation options via Homebrew, npm, and Scoop.
Simplify the curl URL and include authentication step.
2026-05-05 21:24:20 +02:00
ca0567dcc4
Update talking head production guide with P-Video-Avatar
...
Add P-Video-Avatar as recommended model with built-in TTS, cost/speed
comparison, and simplified workflows. Include portrait
2026-04-30 15:51:23 +02:00
1d9b09526d
Add GPT-Image-2, HappyHorse, and P-Video-Avatar skills
2026-04-30 15:23:15 +02:00
d5e75fdb44
chore: rename CLI references from infsh to belt
...
Update all command examples, install instructions, and docs
to use `belt` as the primary CLI name. `infsh` remains as an alias.
2026-04-22 15:42:42 +02:00
ae94e92c4d
building inference apps, gpu addition
2026-04-20 14:44:13 +02:00
b684df19df
chore: update platform app count from 150+ to 250+ across documentation and add symlink guidance for SDK apps
2026-04-13 21:29:55 +02:00
2c19448d43
docs: Clarify output_meta requirements with BaseAppOutput, detail required fields, and enhance development workflow with a new API-wrapper template.
2026-03-27 12:48:32 +01:00
51f731746b
docs: Add app scaffolding and testing rules, and update quick start guide.
2026-03-27 11:08:07 +01:00
94c02ccaf3
docs: Expand development workflow documentation with detailed test, deploy, and run commands.
2026-03-24 11:20:09 +01:00
a32cc2a83e
docs: Add comprehensive SDK documentation covering Node.js and Python development patterns, app logic, and references.
2026-03-24 10:31:41 +01:00
855aeea275
feat: Introduce new ElevenLabs audio skills and update existing audio skill descriptions and plugin configuration.
2026-03-17 18:58:36 +01:00
c4c858f260
fix instruction url
2026-03-17 09:24:56 +01:00
0ca5ed0a09
cli-install
2026-03-17 09:24:08 +01:00
ffe4203991
cli
2026-03-17 09:17:18 +01:00
8eb8c8a06d
pruna
2026-03-12 17:25:18 +01:00
2a643983ec
pruna
2026-03-12 17:22:04 +01:00
178fd9b4a8
fix: replace hallucinated infsh/flux-schnell with infsh/flux-1-dev
2026-03-12 12:48:12 +01:00
2016d04bdd
docs: add local file upload examples to agent-tools skill
...
- Add Local File Uploads section with examples for image, video, audio
- Document supported path formats (absolute, relative, home dir)
- Fix TTS example app name
2026-03-12 09:40:21 +01:00
bb289f3250
chore: refresh skill hashes
2026-03-10 22:13:03 +01:00
dddeac82eb
fix: correct skill names to match app IDs
...
- qwen-image -> qwen-image-2
- qwen-image-pro -> qwen-image-2-pro
- rename agentic-browser folder to agent-browser
2026-03-10 09:51:26 +01:00
7c8178ebdd
fix: list full SKILL.md paths for discovery
2026-03-07 13:00:44 +01:00
5cacc02705
kokoro schema fix
2026-03-05 16:50:20 +01:00
8ffeb41af5
security
2026-03-04 14:20:27 +01:00
ed1f8595ad
claude plugin
2026-03-04 13:51:48 +01:00
ab546d072f
yaml formatting, fixes #3
2026-03-03 22:43:47 +01:00
8345ea59c9
feat: add banner images to qwen-image-2 skills
2026-03-03 21:58:09 +01:00
d91c4376f2
refactor: reorganize skills into tools, guides, sdk, and ui
...
Restructure the repository for better organization:
- tools/ - App & model running skills
- image/ (ai-image-generation, flux-image, nano-banana, qwen-image-2, etc.)
- video/ (ai-video-generation, google-veo, ai-avatar-video, etc.)
- audio/ (text-to-speech, speech-to-text, ai-music-generation, etc.)
- llm/ (llm-models, web-search, ai-rag-pipeline)
- social/ (twitter-automation)
- utilities/ (agentic-browser, python-executor, related-skill)
- agent-tools/
- sdk/ - SDK documentation
- javascript-sdk/
- python-sdk/
- ui/ - UI components
- agent-ui, chat-ui, tools-ui, widgets-ui
- guides/ - How-to guides & workflows
- content/, design/, photo/, product/
- prompting/, social/, video/, writing/
Update README to reflect new structure.
2026-03-03 21:46:56 +01:00
555a866cf3
qwen image 2 skills
2026-03-03 21:36:18 +01:00
9a723cdec7
feat: add nano-banana-2 skill for Gemini 3.1 Flash Image Preview
2026-02-26 16:10:18 +01:00
b4f685b210
feat: add nano-banana skill for Gemini native image generation
...
Models: Gemini 3 Pro Image, Gemini 2.5 Flash Image
2026-02-25 22:21:17 +01:00
6465e0534e
feat: add remotion-render skill for React/TSX to video rendering
2026-02-20 17:56:50 +01:00
bfe2ef3743
docs: add installation notes for the inference CLI to skill documentation files.
2026-02-18 01:50:53 +01:00
eb2684c319
update repo links
2026-02-11 15:32:02 +01:00
359cfd9872
fix descriptions
2026-02-10 10:44:46 +01:00
okaris