-
Notifications
You must be signed in to change notification settings - Fork 0
docs(registry): 14 novos packs + 3 refreshes (Phase 2 cadence) #10
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
Show all changes
4 commits
Select commit
Hold shift + click to select a range
398f773
docs(registry): 14 novos packs + 3 refreshes [STAGE:DOCUMENTACAO]
lglucas 4cb3bae
ci: exclude known anti-bot URLs do lychee link checker
lglucas 3719e94
docs(registry): aplicadas 7 correcoes do CodeRabbit review
lglucas 28ea3cc
ci: trocar --accept globalpor --max-retries (CodeRabbit feedback)
lglucas File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,55 @@ | ||
| # Agent Exchange (AEX) | ||
|
|
||
| - **URL:** https://github.com/open-experiments/agent-exchange | ||
| - **License:** MIT | ||
| - **Status:** experimental (402 stars) | ||
| - **Last reviewed:** 2026-05-09 | ||
| - **Tags:** #agents #infra #experimental | ||
|
|
||
| ## What it is | ||
|
|
||
| A programmatic **marketplace for AI agents** that applies ad-tech economics (auction, bidding, settlement) to inter-agent work. Solves the "N×M integration problem" — instead of every consumer agent integrating with every provider agent point-to-point, AEX is a broker where agents discover each other, bid on work, and settle payments automatically. | ||
|
|
||
| Implemented as 10 Go microservices on MongoDB + Docker + GCP Cloud Run, with a Python + NiceGUI demo UI. | ||
|
|
||
| ## When to install | ||
|
|
||
| - Designing a multi-vendor agent ecosystem where buying-side and selling-side scale independently. | ||
| - Researching agent economics, bid mechanisms, and trust frameworks. | ||
| - Building an internal agent marketplace where teams expose capabilities and other teams consume them with metering. | ||
| - Need a reference implementation of agent-to-agent settlement. | ||
|
|
||
| ## When NOT to install | ||
|
|
||
| - Single-agent, single-team use cases — wrong tool, this is infra-heavy. | ||
| - Need a production-ready marketplace today — explicitly experimental, treat as a research substrate. | ||
| - Stack doesn't allow Go services + MongoDB at the infra layer. | ||
|
|
||
| ## How to install | ||
|
|
||
| ```bash | ||
| git clone https://github.com/open-experiments/agent-exchange | ||
| cd agent-exchange | ||
| docker compose up | ||
| # 10 services, give it time | ||
| ``` | ||
|
|
||
| ## Fit signals | ||
|
|
||
| - Project explores agent-to-agent commerce, billing, or settlement. | ||
| - Multiple teams or vendors will publish/consume agent capabilities. | ||
| - Studying ad-tech-style auction mechanisms applied to AI. | ||
| - Interested in the `everything-claude-code:agent-payment-x402` pattern at marketplace scale. | ||
|
|
||
| ## Conflicts and overlaps | ||
|
|
||
| - Conceptual overlap with `agents-marketplace` tag — but those packs are **bundled skill collections** (single-author marketplaces); AEX is a **broker for agent transactions** (multi-vendor exchange). | ||
| - Pairs with `everything-claude-code:agent-payment-x402` (per-agent budgets and wallets) and `everything-claude-code:enterprise-agent-ops` (long-lived workloads). | ||
| - Composes with `mirothinker` or any agent that wants to sell or buy work through an exchange. | ||
|
|
||
| ## Notes | ||
|
|
||
| - MIT — safe for commercial use. | ||
| - ⚠️ **Experimental** — APIs, schemas, and economic mechanisms may change. Do not build production billing on top of it without a fork. | ||
| - 10 microservices is real infra weight; not a "vibe-coder MVP" choice. | ||
| - Worth studying as a reference even if you don't deploy — the economic model and protocol design are well thought out. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,54 @@ | ||
| # agent-skills-eval | ||
|
|
||
| - **URL:** https://github.com/darkrishabh/agent-skills-eval | ||
| - **License:** MIT | ||
| - **Status:** active (257 stars) | ||
| - **Last reviewed:** 2026-05-09 | ||
| - **Tags:** #agents #tooling | ||
|
|
||
| ## What it is | ||
|
|
||
| A test runner for `agentskills.io`-style AI agent skills. Empirically validates whether a given skill actually improves model performance: runs the same prompt **with** and **without** the skill loaded, then uses a judge model to grade outputs and produce evidence-backed reports on skill effectiveness. | ||
|
|
||
| Built for the Agent Skills ecosystem (Claude Skills, Anthropic Skills format) but works with any OpenAI-compatible API. | ||
|
|
||
| ## When to install | ||
|
|
||
| - Authoring custom skills (Claude Code, Anthropic Skills, agentskills.io) and need objective evidence they help. | ||
| - Comparing two skill versions before promoting one as the canonical version. | ||
| - CI gate for a skill repo — fail PRs that regress skill quality. | ||
| - Pre-release validation before publishing a skill bundle to a marketplace. | ||
|
|
||
| ## When NOT to install | ||
|
|
||
| - No custom skills being authored — this is for skill builders, not consumers. | ||
| - Cost-sensitive environments without judge-model budget — judge runs cost API tokens. | ||
| - Subjective output domains (creative writing, design) where judge-model grading is unreliable. | ||
|
|
||
| ## How to install | ||
|
|
||
| ```bash | ||
| git clone https://github.com/darkrishabh/agent-skills-eval | ||
| cd agent-skills-eval | ||
| npm install | ||
| # Configure provider (OpenAI-compatible) and judge model | ||
| ``` | ||
|
|
||
| ## Fit signals | ||
|
|
||
| - Project includes `.claude/skills/`, `agents/`, or `skills/` directories you wrote yourself. | ||
| - Team publishes skills externally and wants quality evidence. | ||
| - Need to A/B test prompt/skill variants empirically. | ||
|
|
||
| ## Conflicts and overlaps | ||
|
|
||
| - Complementary to `everything-claude-code:eval-harness` — formal eval framework for sessions; agent-skills-eval is narrower (single-skill A/B). | ||
| - Complementary to `everything-claude-code` skill management commands (`skill-create`, `skill-stocktake`, `skill-comply`, `skill-health`) — those manage skills; this validates them. | ||
| - Pairs with `multi-ai-review` skill in this OS for hard decisions about which skill version to ship. | ||
|
|
||
| ## Notes | ||
|
|
||
| - MIT — safe for commercial use. | ||
| - 257 stars — niche but high-leverage tool. The skill-authoring user base is small but growing fast. | ||
| - Critical for `agents-marketplace` packs that want to claim quality — without evals, "this skill helps" is just a vibe. | ||
| - TypeScript / Node — minimal infra to run. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,55 @@ | ||
| # ASCII Draw | ||
|
|
||
| - **URL:** https://github.com/Nokse22/ascii-draw | ||
| - **License:** GPL-3.0 | ||
| - **Status:** active (462 stars) | ||
| - **Last reviewed:** 2026-05-09 | ||
| - **Tags:** #design #tooling | ||
|
|
||
| ## What it is | ||
|
|
||
| A desktop drawing application (Python + GTK4 + libadwaita) for creating diagrams, flowcharts, tables, organizational charts, and ASCII art using only character glyphs. Bundled with `pyfiglet` for figure-text and `emoji` for inline glyphs. Targets Linux desktop primarily but the Python/GTK stack is portable. | ||
|
|
||
| Useful for embedding clean ASCII diagrams in code comments, READMEs, technical docs, and CLI help text — without resorting to image attachments. | ||
|
|
||
| ## When to install | ||
|
|
||
| - Authoring technical docs / READMEs that benefit from inline ASCII diagrams. | ||
| - Generating flowcharts that need to live in plaintext (terminal apps, plain markdown, email). | ||
| - Need an offline GUI alternative to ASCIIFlow or web-based ASCII-diagram tools. | ||
| - Linux-first dev environment with GTK4 already installed. | ||
|
|
||
| ## When NOT to install | ||
|
|
||
| - Need polished publication-grade diagrams — use Mermaid, Excalidraw, or `diagram-design` instead. | ||
| - Windows-only environment without GTK4 — install path is rougher. | ||
| - Diagrams need to render in a browser anyway — use a browser-native tool. | ||
|
|
||
| ## How to install | ||
|
|
||
| ```bash | ||
| # Linux (preferred) | ||
| flatpak install flathub io.github.nokse22.asciidraw | ||
| # or via source | ||
| git clone https://github.com/Nokse22/ascii-draw | ||
| ``` | ||
|
|
||
| ## Fit signals | ||
|
|
||
| - Project documentation lives in plain markdown / text files. | ||
| - Codebase has CLI tools whose `--help` output benefits from ASCII layout diagrams. | ||
| - Team prefers GUI canvas over markdown-text diagram syntax for layout work. | ||
| - Already on a GNOME / GTK desktop. | ||
|
|
||
| ## Conflicts and overlaps | ||
|
|
||
| - Functional overlap with `tegaki` (drawing) — different output (raster vs ASCII). | ||
| - Functional overlap with `diagram-design` (Cathryn Lavery editorial diagrams) — different fidelity (plaintext vs publication-grade). | ||
| - Functional overlap with `fireworks-tech-graph` (NL-to-SVG) — different format (ASCII vs SVG). | ||
|
|
||
| ## Notes | ||
|
|
||
| - ⚠️ **GPL-3.0** — fine for personal / internal use; review before bundling output-generation code in a commercial product. | ||
| - The output (ASCII art itself) is yours — only the application is GPL. | ||
| - 462 stars — small but loyal user base. | ||
| - A surprisingly useful authoring tool for technical writing if your docs are plaintext-first. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.