Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

just shipped taskmaster v0.17 🚀 → multi-context task management via tagged lists → `research` MCP tool with interactive CLI → get-task/show upgrades & batch ops → --append for update-task → save research to docs → multi-status filters follow + bookmark + dive in 👀👇

37,012 görüntüleme • 1 yıl önce •via X (Twitter)

15 Yorum

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

1 tagged lists is our biggest upgrade ever → keep master list clean & focused → spin up isolated contexts for experiments, prototypes & personal tasks → easily create tags for @github branches → taskmaster scales complexity per project maturity it's next-level flexibility

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

rapid prototyping and versioned task lists → clearly separate experimental work → easily manage tasks across versions/teammates → keep your master task list stable & release-ready your agent will intelligently suggest creating tags like mvp, v1, when and if appropriate

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

taskmaster multiplayer is finally possible → taskmaster proactively suggests personal tags → avoid conflicts & keep your tasks neatly isolated → master list stays full of business value → other tagged lists for chores, refactors, experiments perfect for existing codebases

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

tackling something ambitious? → taskmaster will automatically create dedicated tags for major features → agent will research, co-author and generate PRDs to parse them into isolated task lists → strategic planning made effortless → use --tag on any command which means...

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

agentic parallel development workflows powered by taskmaster are more powerful than ever → isolate work for agents to complete in tagged list → spin up parallel agents against pending tasks on list → agent can research, generate PRDs, parse them, expand them, and deliver 🤖

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

2 introducing the new `research` MCP tool and CLI your agent can now: → query fresh, latest info beyond AI knowledge cutoff → challenge its own assumptions, validate approaches, find best practices & debug smarter → integrated directly into taskmaster workflow more:

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

the main goal of the research command is to make your agent even smarter but it also comes with an interactive CLI: → explore ideas without leaving the terminal → ask follow-up questions → save info into tasks → export to files and use as a PRD fully workflow integration

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

research results are fully actionable: → save directly to tasks/subtasks (--save-to) → export full research conversations to markdown docs → build PRDs & strategic plans from fresh insights research is powered by your research model of choice use it to explore raw ideas

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

3 you no longer need to call get-task/show on one tasks/subtask at a time. just get it all at once. → batch-fetch multiple tasks/subtasks at once → richer task details & dependency visualization → agent instantly sees what's next & what's blocking will save many tool calls

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

the `show` CLI command now accepts comma-separated tasks/subtasks → scope down task lists to a small task selections → execute batch actions like setting statuses → expand ranges of tasks this will get more love over time as we polish CLI more

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

4 --append flag support for update-task too → append timestamped notes & progress updates → perfect for iterative logging & tracking implementation journeys → keep your task history rich & informative works just like --append for update-subtask

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

5 multi-status filters for the `get_tasks` MCP tool and `list` CLI → filter your lists by multiple statuses at a time → helpful for consolidating items for review → crucial for scoping agentic workflow progress pass multiple comma-separated statuses to use this

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

6 QoL & other fixes → task move & dependency handling → improved batch ops & multi-status filtering → active tag indicators to CLI/MCP outputs → various bug & stability fixes always made with love BUT big upgrades CAN break things plz send any bugs you find, we'll fix

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

that's it for now, till next time! we're nearing 15,000⭐ @github! v0.17 changelog → npm i -g task-master-ai@latest → MCP auto-updates → join → more info → hug your parents vibe on friends

Eyal Toledano profil fotoğrafı
Eyal Toledano1 yıl önce

help taskmaster reach more people by retweeting the first tweet and sharing it with your friends who are tired of getting stuck coding with ai follow if you bookmark!

Benzer Videolar

watch this anon. i gave NVIDIA's biggest model ever a single task. 100 minutes and 440,000 tokens later, it had rendered nothing. not one important thing on the screen. this is Nemotron 3 Ultra. 550 billion parameters, a hybrid Mamba Transformer MoE, the largest model NVIDIA has ever shipped, and they built it specifically for long-running agentic coding. so i handed it exactly that: build a 3D scene from a spec, multiple files, iterate until the tests pass. the same task a frontier model one shotted in minutes. i genuinely wanted to be impressed. it ran for an hour and forty. burned through 440,000 tokens. wrote every file, passed its own tests, and proudly printed "task complete."the browser was blank. the 3D scene never rendered. not once. and the long horizon agentic behavior was genuinely good. it stayed on task the whole hour and forty, wrote real multi-file code, drove its own tools without derailing. it just couldn't turn any of that into something that actually runs. here's the part that gets me. it's a text model, it cannot see its own output. so it sat there looping on a broken vision tool, trying to "look" at the page, hitting error after error, never once reasoning its way out. it declared victory on an empty screen because it had no way to know the screen was empty. to be fair, i genuinely don't know what quant the NIM was serving, so maybe some of that's on the serving, not the model. but the biggest model NVIDIA has ever made, on the exact task it was designed for, couldn't tell it had built nothing in 100 minutes. same task on a local model, below thread👇.

Sudo su

32,589 görüntüleme • 27 gün önce

We OPPOSED Black Caucus Bill SB437 by Senator Akilah Weber-Pierson Chair of the California Legislative Black Caucus today. Here’s why: First, the proposal directly contradicts the recommendations of the California Reparations Task Force. The Task Force did not recommend that the state conduct additional research to determine how an individual might demonstrate their descendancy from U.S. Chattel Slavery. Second, third, fourth, fifth, and sixth: the proposal is unnecessary, redundant, raises serious risk of fiscal waste, would create crippling and cascading implementation delays, and was already rejected by community advocates. Specifically, it’s unnecessary because tracing Ancestry to U.S. Chattel Slavery is already a known practice conducted by genealogists literally every single day. It raises serious risks of fiscal waste because the research proposed directs millions of taxpayer dollars originally budgeted for Reparations implementation away from implementation and instead to a multi-million dollar genealogy research project with NO start date and NO end date to the research. It would create severe implementation delays because none of the other Black Caucus bills currently moving in the legislature targeting descendants can actually take effect until the proposed research project is completed. Furthermore, last year, this same proposal was rejected by community advocates and former Senator Stephen Bradford when Governor Newsom's office proposed nearly a carbon copy of what is now SB 437 as amendments to Senator Bradford's SB1403. Lastly, the proposal in SB 437 conflicts with another one of Senator Weber-Pierson's proposals, namely SB 518. Californians whose ancestors built this country through hundreds of years of free labor, are tired of research. We don’t need more research. We need action. We need Reparations. #AmericanFreedmen Coalition For A Just & Equitable California ETM MEDIA GROUP #cjeccoalition

Coalition For A Just & Equitable California

14,044 görüntüleme • 1 yıl önce