**Orkas** (⭐7.2k) is a local-first desktop AI team app: a Commander agent breaks your goal into to-dos and coordinates 16 built-in specialist agents, plus whatever CLI coding agents — Claude Code, Codex, and others — you already have installed, treated as local sessions under one roof. **vercel-labs/agent-desktop** (⭐6.5k) gives agents reliable computer use by reading the OS accessibility tree in Rust and returning a JSON snapshot with stable element refs instead of guessing from screenshots; it just picked up Linux support. **unclebob/ub-mode** (⭐6.2k) is an agent skill from Robert C. "Uncle Bob" Martin that hands the question of whether code is actually good to deterministic tools — crapper, dryer, mutator — instead of trusting the agent's own word for it. No major framework release today.
**T3 Code** (⭐ 22.6k) turns an iOS/Android/desktop app into a remote control surface for multiple coding agents at once — Codex, Claude Code, Cursor, Grok Build, OpenCode, Google Antigravity. **Lightpanda** (⭐ 36k) rewrites the headless browser from scratch in Zig; its own benchmark shows memory use at roughly 1/16 of headless Chrome and page-fetch time about 9x faster. **anthropics/skills** gained 2,300 stars this week alone, crossing 185.7k — a sign Agent Skills is moving from a Claude-only feature to a format other platforms share. On the release side, **Pydantic AI v2.64.0** ships four compatibility notes that change how failed retries surface errors and how server state crosses providers, while **Claude Code v2.1.316** announces the retirement of Opus 4.8 fast mode at the end of November.
**obra/superpowers** (⭐ 307,258, +1,096 today) and **Nutlope/hallmark** (⭐ 40,442, +2,109 today) both hit GitHub trending the same day, each teaching a coding agent not to produce output that reads as obviously AI-made; **nightly-labs/openbot** (⭐ 3,097) manages a fleet of agents from one desktop app, and **expo/skills** is an official framework team shipping its own skill pack. On the release side, pydantic-ai v2.63.0 ships a batch of compatibility changes, and crewAI v1.15.31 patches deserialization, SQL injection, and path traversal vulnerabilities.
**pbakaus/impeccable** (⭐ 88,893) defines and fixes the recurring tells of AI-generated interfaces with 62 deterministic rules; **JetBrains/thinkrail** (⭐ 2,638) wraps a third-party `pi` coding agent inside JetBrains' own IDE, isolating each agent's work in its own git worktree; **nightly-labs/openbot** (⭐ 1,317) is a local-first desktop app that lets Codex, Claude, Grok, and other agents message each other and collaborate; **boyuchengz/canvas-mcp** (⭐ 115) is a read-only MCP server that connects the Canvas LMS used by universities to Claude and ChatGPT. No notable framework releases today.
When you install a skill, connect an MCP server or let an agent run commands, risk can be seen as coming in through four entry points. I sort the open-source tools around them into seven kinds by when they step in, from pre-install scanning and sandboxes to guardrails, audit and red teaming. This post covers what each kind handles and three limits that keep recurring: no single tool works as the only defense, defaults often work against you, and published detection numbers lack independent evaluation.
The two representatives take opposite approaches: Cloudflare's security-audit skill is a pure-LLM multi-stage process, and Cloudflare says that when its internal harness wired in Semgrep, the hunting agents did not call it once in a month; Trail of Bits combines Semgrep and CodeQL scripts with LLM judgment. I found no checks specific to Workers, D1, KV or Astro in the rules or supporting files of either, and neither publishes accuracy figures from real projects. This post is based on documentation only and was not run against any project.
These four pre-install scanners work in one of three ways, usually combining two: static rules, LLM judgment, or actually connecting to the MCP server. Cisco's own documentation shows rules alone catch about 8% of malicious samples they have not seen, and third-party tests show the numbers shift a lot when the sample mix changes. Use scanners as a first filter; "no findings" does not mean safe.
**stablyai/orca** (96,374 stars) is a YC-backed desktop orchestrator for a fleet of coding agents — Claude Code, Codex, Grok and more, each running in its own git worktree, monitored from desktop and mobile. **agentscope-ai/AgentTeams** (5,772 stars) is Alibaba's AgentScope team's open-source multi-agent OS, routing all agent-to-agent and human-to-agent communication through Matrix chat rooms instead of a custom dashboard. **wheresryan22/anatomy** (15,866 stars) is a Claude Code-compatible agent skill that turns a technical idea into a working isometric mechanical illustration — it went from creation to 15K+ stars in about 10 days. No notable framework releases today: langgraph and claude-code both shipped patch-only releases inside the 48-hour window, with no breaking changes.
To cut the input tokens resent every turn, agent platforms often truncate, clear, or summarize old tool results, and skill instructions, write receipts, and error messages get cut along with them. The Complexity Trap shows observation masking can halve cost, yet Gemini 2.5 Flash with thinking still dropped from 40.4% to 36.4% solve rate. Measure savings against full history and fixes against the current setup, and judge by total cost per successful task, not shorter per-turn input.
Matt Pocock posted 18 'mistakes you might be making' on X with no explanations. Grouped against his public skills and talks, they fall into five: verification, letting go, context, alignment, thinking. Six map directly onto /retro's check categories, so you can try one session tonight.
pstack is an MIT-licensed set of agent skills from Cursor engineer Lauren Tan. One entry point, /poteto-mode, picks one of 23 playbooks per task and calls other skills and 24 principles as steps need them. Install takes one command and one model setup; the price is extra tokens for subagents and review panels.
**mattpocock/skills** (283,680★) is the agent-skills collection its author actually uses day to day — now listed in Claude Code's official plugin marketplace, installable with one command in Codex, Copilot, and Gemini CLI too. **morluto/rea** (61,585★) wires an agent into Ghidra, Hopper, and IDA to reverse-engineer native binaries, JS/Electron apps, and websites. **cathrynlavery/diagram-design** (48,496★) is an agent skill for drawing diagrams — 44 types, each exported as a single self-styled HTML+SVG file. **anthropics/knowledge-work-plugins** (28,593★) is Anthropic's own open-sourced set of 11 role-specific plugins, bundling Slack/Notion/HubSpot connectors into Claude Cowork. **mksglu/context-mode** (26,062★) is an MCP server built to stop tool output from flooding an agent's context window. pydantic-ai v2.55.0 raises its minimum Python version to 3.11 and adds a `Conversation` object; Claude Code v2.1.296 fixes how plain-language hooks are evaluated.
An 83-page paper from Wavestone AI Lab dissects 11 coding harnesses, including Claude Code, Codex CLI, Gemini CLI and OpenClaw. Across roughly 4 million lines of code, none imports a general-purpose agent framework and none retrieves code with vector embeddings. If you are building or choosing an agent, you can follow the paper's 18 recommendations and start from one bash tool and one while loop.
Cursor engineer Lauren Tan (poteto) says she merges roughly 2,000–2,500 PRs a month, a self-reported figure no one has audited. Her method is three moves: build a verification skill first, turn repeated mistakes into lint and type constraints, and sample-review after merge. The method transfers if your domain can be verified by code.
The first lecture of Hung-yi Lee's ML 2026 breaks OpenClaw into five questions: how an agent knows who it is, how it uses tools and SKILLs, how it remembers, how it runs on a schedule, and how it keeps working on its own for a long time. Every answer comes back to one fact: the language model only predicts the next token and starts fresh every turn. Identity, memory, and SOPs are all text files that OpenClaw puts into the prompt, or files the model reads and writes through tools. This post walks through the 60-slide intro.pdf and the lecture recording, including the defenses the slides recommend.
Plugin Extensions, announced at DevDay 2026 (Sep 29), let a plugin put a home in the ChatGPT sidebar, a panel beside the conversation, and a viewer for its file types — up to three entrypoints per MCP App. A plugin is now Skill + MCP + external services + UI, which adds a new product question: which capabilities should ship as a plugin an agent can install?
The 2026 syllabus for CME295 Lecture 6 (November 6, 2026) lists seven topics. Tool calling, MCP and retrieval were already covered in the 2025 Lecture 7; the genuinely new ones are context compaction, harness optimization, coding agents, and skills/plugins. This pre-lecture edition explains those four using engineering posts from Anthropic and OpenAI, the MCP 2026-07-28 spec, and the Meta-Harness paper.
CMU 11-768's first assignment starts from an empty ReAct loop: a bash-only CodeAgent fixes a bug in a chess app, context compaction is added to solve a SWE-bench task, and the same loop becomes a ChessAgent that runs a two-ply search with simulate_move, run_python, and a skill. All 100 points are graded by replaying submitted patches and trajectories offline.
Lecture 4 of CMU 11-768 sorts cross-task experience into episodes, facts, and skills, stored as external artifacts rather than in context or weights. Human-written skills load through SKILL.md and progressive disclosure, lifting the average SkillsBench pass rate from 33.9% to 50.5%. Skills an agent induces itself can be tested before admission when written as code, but break easily on a new website. The hard part is the lifecycle: imperfect judges, over-retrieval, and bloated skill libraries each eat into the gains.
An AI assistant platform running Opus 4.6 hit stream_stall (90s timeout) twice consecutively when generating docx. Root cause: skill instructions lacked one sentence — 'Write a script' — causing the model to output JS code inline instead of writing a file and executing with node. Claude.ai's official SKILL.md has that sentence, and the model consistently takes the safe path.
alibaba/open-code-review replaces prompt-only review with a deterministic-engineering-plus-agent hybrid, using roughly 1/9 the tokens of a general-purpose agent; cloudflare/security-audit-skill packages Cloudflare's own vulnerability-hunting pipeline into a six-phase skill built around adversarial validation; microsoft/skills bundles 175 pieces of Azure SDK domain knowledge into one-click-install skills and MCP configs; Pydantic AI shipped v2.45.0 and v2.46.0 two days apart, adding TypeSafeModel and a Choices helper
GPUtw AI Skill is an official Agent Skill pack plus MCP server that lets Claude Code, Codex, Cursor, Copilot, and Gemini CLI manage GPUtw's Taiwan-based GPU cloud using natural language. 18 MCP tools cover catalog queries, instance lifecycle, status monitoring, and Vault operations. MIT licensed.
JustVugg/colibri uses memory tiering across storage/RAM/VRAM to run 744B–2.8T MoE models on consumer hardware in pure C; tech-leads-club/agent-skills wants to get supply-chain verification for agent skills sorted out before they become the next npm trust problem; alphaXiv/OpenResearch turns Claude Code / Codex into experiment-running researchers with git-native reproducibility; calesthio/OpenMontage wraps 12 production pipelines, 100+ tools, and 700+ agent skill files into a full video production framework; alibaba/open-code-review open-sources their hybrid 'rule engine + LLM agent' code review tool; Claude Code v2.1.269 raises the Workflow tool's concurrent agent cap to 256
A skill is organizational tacit knowledge made operational — a folder with a SKILL.md that Claude loads automatically when trigger conditions are met. The course's key principle: skills make violations rare; hooks make them nearly impossible.
Anthropic's Claude Academy offers a free 14-lesson course that takes AI-assisted coding from 'individuals using Claude Code' to 'an organization-wide development lifecycle.' Four core concepts — intent.md, CLAUDE.md, Skills, and Hooks — wire together into a complete AI-native SDLC.
obra/superpowers hardens a full development methodology into a skill installable across 8+ harnesses; affaan-m/ECC is a performance-optimization system with 68 agents + 286 skills for agent harnesses; cathrynlavery/diagram-design gained 2,286 stars in a single day, swapping Mermaid for 39 editorial diagram types; Tencent's teamai-cli lets a team distribute skill/rule/MCP config centrally; Pydantic AI v2.42.0 adds a GitHub Copilot provider
mattpocock/skills gained 2,757 stars in a single day — the fastest-growing repo on GitHub today. Anthropic's own anthropics/skills and the open-source coding agent anomalyco/opencode are trending alongside it. Meanwhile MCP server reverify ran a benchmark on 71 real Windows system files and found AI has a 97% error rate reverse-engineering binaries from memory — deterministic tools caught every single one. On the framework side, pydantic-ai, agno, and haystack all shipped routine patches today, nothing major.
NousResearch/hermes-agent keeps climbing (239,994 stars) on a self-improving learning loop that remembers how to use your tools and who you are across sessions. pacifio/atlas gained 895 stars in a day by giving multiple coding agents shared, traceable version control — every commit links back to the session that made it. blader/humanizer strips the AI tell from writing using 35 patterns, without inventing facts. On the document side, firecrawl/pdf-inspector decides in under 50ms whether a PDF needs OCR, and superlinked/sie folds every model an agent needs into one self-hosted inference cluster. On the framework side, AG2 v1.0.3 ports fully to MCP 2.0 (a breaking change) and adds TealTigerMiddleware, a deterministic, non-LLM prompt-injection guard.
can1357/oh-my-pi forked the well-known coding agent 'Pi' and, by obsessing over tool-call formats, pushed Grok Code Fast 1's task success rate from 6.7% to 68.3%; K-Dense-AI/scientific-agent-skills opens 163 research skills to any agent that supports the Agent Skills standard; addyosmani/agent-skills packages a senior engineer's six-stage workflow into a skill set and hit 90k stars in a week; THU-MAIC/OpenMAIC v1.0.0 adds a conversational Pro workbench, landing multi-agent orchestration in the concrete vertical of course content production. On the framework side, agno v3.0.2 is the one release that clears the bar: it publishes Agents/Teams/Workflows as named MCP tools and ships several breaking changes along the way.
calesthio/OpenMontage turns a general-purpose coding agent into a full video-production studio with 12 pipelines and 700+ skill files, jumping to 50k stars this week; Anthropic's own official plugin marketplace claude-plugins-official gained +292 stars in a single day; rohitg00/agentmemory gives coding agents cross-session memory via BM25 + vector + knowledge graph retrieval, claiming 95.2% R@5 on its own LongMemEval-S benchmark; sodiumsun/agenttrail builds a local, real-time task map for Claude Code, Codex, and Cursor. No major framework releases today.
I turned Anthropic's session-cost advice into a global skill, and the first version made the very mistakes it was meant to prevent: a description stuffed with trigger keywords, hard thresholds based on file counts and minutes, and 'protect the main context' conflated with 'spend fewer tokens overall'. Three rounds later the entry point is one page, details live in references, numeric thresholds became four judgment dimensions, and every claim from a draft post was checked against official docs.
Agent Plugins 1.0 is a packaging format that bundles Agent Skills (markdown instructions) and MCP server configs into a single directory, loadable by ChatGPT, Cursor, GitHub Copilot, Kiro, and VS Code. It's not a new protocol — it's the wrapper above protocols. Vercel initiated it, OpenAI/AWS/Microsoft/Cursor co-authored it, and Google joined on launch day. Anthropic isn't on the governance board, but MCP is a core primitive of the spec.
The 2026 consensus for agent-built slide decks: outline-first, separate content from construction, then render to images and let a fresh-eyes subagent do visual QA. Anthropic's and OpenAI's official slides skills both converged on PptxGenJS plus a visual verification loop, and the research line (PPTAgent → PreGenie → DeepPresenter) points the same way. But two later corrections matter: PresentBench shows the widely cited PPTEval scores too generously, and SeaSlides argues the model should not write free-form HTML/SVG at all.
The Agent Skills spec fits in a sentence: a directory containing a SKILL.md. The real design is three levels of progressive disclosure — only name and description load at startup, the body loads on a match, bundled files load on demand. This site's own repo carries 35 skills and 7,893 lines of SKILL.md, and startup still costs only those 35 metadata pairs.
PIMiner uses a transferable strategy library to push prompt injection ASR to 76–87% at ~$20 query cost; Agent Skills Can Be Harmful finds that seemingly relevant skills are more likely to derail tasks than obviously unrelated ones, with excessive procedures accounting for 62.6% of efficiency degradation; Order 66 scenario analysis uses a compositional threat model to show that dormant implants, post-hoc memory poisoning, and peer-to-peer diffusion are individually non-fatal but can sustain self-propagation when combined
MCP governs agent-to-tool, A2A governs agent-to-agent, Skills govern reusable knowledge. The test is whether the data changes: if it changes between calls you need MCP; if it's stable enough to write down, a skill file is simpler and has no runtime that can fail on its own.
HeyGen's open-source HyperFrames defines video timelines with HTML data attributes, uses headless Chrome for frame-accurate seek-and-capture, then encodes via FFmpeg to MP4. 33k stars in 3 months, Apache 2.0, 21 agent skills — AI agents write HTML to produce video, no React needed.
MUSE-Autoskill (2026) introduces a five-stage skill lifecycle framework. Self-created skills achieve 60.35% (+7.16%) on SkillsBench overall, and an impressive 87.94% on tasks where skill generation succeeds — surpassing the human-authored skill ceiling. This post synthesizes six arXiv papers to map the full landscape of skill evolution research.
browse.sh, launched by Browserbase in May 2026, is two things: a browser skill catalog and the Browse CLI. The core thesis: the bottleneck for browser agents isn't reasoning — it's amnesia. By storing learned site-specific workflows as plain-text SKILL.md files, Autobrowse cut Craigslist task costs from ~$0.22 to ~$0.12 by their own metrics. Note: this has nothing to do with the 2018 Browsh text-mode browser.
Claude has no docx_tool or pdf_tool -- it relies on bash + file tools, plus SKILL.md instructions and pre-installed libraries like pdfplumber / python-pptx inside the container, assembling file handling capabilities from three layers.
A Skill is an SOP written for AI. Define the steps in a Markdown file and Claude follows them. No coding required, no frameworks to learn — just write down what an experienced person would do.