Read, answer and post on the Buda community forum at community.buda.im through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $buda-community or /buda-community, asks what is happening in the Buda community, wants an unanswered question triaged or answered, or wants something posted or announced there.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
A zero-dependency CLI over the forum's own REST API: read, post, reply, edit
what you wrote, and upload images. community.buda.im is the source of truth; this
skill keeps no local copy.
node skills/buda-community/scripts/community.mjs <command> [--json]
printf 'BUDA_API_KEY=%s\n' '<key>' >> skills/buda-community/.env
chmod 600 skills/buda-community/.env
node skills/buda-community/scripts/community.mjs whoami
Create the key at https://buda.im/en/docs/developers/authentication, signed in with the account you use on the
forum. Values are read in this order, first one wins: an exported variable,
$BUDA_ENV_FILE, skills/buda-community/.env (gitignored), ~/.buda/.env.
| Variable | What it is |
|---|---|
BUDA_API_KEY | Required. The default account |
BUDA_API_KEY_<NAME> | Another account, used with --as <name> |
BUDA_ACCOUNT | Default account name when --as is absent |
BUDA_COMMUNITY_API_URL | API origin (default https://buda.im) |
BUDA_COMMUNITY_URL | Forum origin for links (default https://community.buda.im) |
Buda serves the API on both hosts; the default is the documented apex, https://buda.im.
If the key is missing, every command prints these instructions. Never ask for
the key in chat, never write it to a tracked file, never print it — setup
shows only its length.
| Command | What it does |
|---|---|
setup | Is it configured, and from which files |
accounts [--verify] | List configured accounts; --verify checks each one |
whoami | Verify the key, print the account and the API/forum origins |
categories | Category slugs, kinds and post counts |
posts [--category S] [--sort active|latest|top] [--unanswered] [--status s1,s2] [--solved] [--q TEXT] [--lang XX] [--limit N] [--offset N] | List posts |
post <slug> | One post with its replies |
new --category S --title T --body B [--lang XX] [--yes] | Publish a post |
reply <postId> --body B [--yes] | Publish a reply |
edit <postId> [--title T] [--body B] [--lang XX] [--yes] | Edit a post the selected account wrote |
edit-reply <replyId> --body B [--yes] | Edit a reply the selected account wrote |
upload <file.png> | Store an image and print its markdown line |
--category takes a slug (run categories first). post takes a slug;
reply and edit take the post id from post <slug>.
This API has no draft or review state, so the gate is local:
new, reply, edit and edit-reply without --yes print the exact
payload and send nothing.--yes only after they approve it, in the same turn.Read the thread before answering it, post in the thread's language, and publish the user's wording as given. A write is done only when the command prints the new id or URL — quote it back.
An image is a markdown link in the body, not an attachment:
node scripts/community.mjs upload ./screenshot.png # → 
node scripts/community.mjs new --category ask --title "…" --body "……" --yes
png, jpg, gif or webp, up to 10MB. Identical bytes are stored once and anyone with the URL can fetch it — do not upload what you would not post.
# skills/buda-community/.env
BUDA_API_KEY=... # default
BUDA_API_KEY_ALT=... # --as alt
--as <name> works on every command; BUDA_ACCOUNT sets the default for a
shell. An unknown name is an error, never a fallback to the default. Every
preview and confirmation names the account — say which one was used, and ask
when the user has several and has not said.
references/api.md is the endpoint contract. Tests are offline (no key, no
network): npm run test:community.
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Align all AI coding agents to a single source of truth. AGENTS.md for rules, .agents/skills/ for skills, symlinks for everything else. Use when setting up a repo for multiple agents, or when links are missing, broken, or out of date.
日本語の概要は準備中です。原文の説明を表示しています。
Read, answer and post on the Busabase community forum at community.busabase.com through its /api/v1/community REST API. Lists categories and posts, reads a thread with its replies, searches, and publishes posts and replies behind an explicit confirmation. Use when the user invokes $busabase-community or /busabase-community, asks what is happening in the Busabase community, wants an unanswered question triaged or answered, or wants something posted or announced there.
日本語の概要は準備中です。原文の説明を表示しています。
Ad-campaign command desk (投放指挥台, Busabase App-in-Skill) for a cross-border e-commerce seller running Amazon Ads, Meta (FB/IG), TikTok Ads, and Google Ads. Use when the user invokes $kelly-ads or /kelly-ads, or asks about 投放, ad campaigns, ad spend, ACOS, ROAS, Amazon Ads, TikTok ads, Meta ads, Google Ads, search terms, negative keywords, bid adjustment, budget pacing, CPC spikes, rejected ads, ad anomaly detection, 广告优化, or reviewing agent-proposed adjustment cards (negative keyword, bid down/up, pause target, budget shift, creative refresh).
日本語の概要は準備中です。原文の説明を表示しています。
Busabase-backed App-in-Skill low-code agent configuration and governance console for a platform team. Use when the user invokes $kelly-agent-builder or /kelly-agent-builder, wants to review or edit a catalog of mock LLM agent configs, check quota usage, find configs that need attention, move a draft to live, pause a live agent, or archive an agent. Mock config/governance console only — it never provisions or calls any real agent.
日本語の概要は準備中です。原文の説明を表示しています。
Review board (Busabase App-in-Skill) that runs a fixed suite of mock test cases against a baseline vs candidate agent version and surfaces rubric-scored regressions before a release. Use when the user invokes $kelly-agent-eval or /kelly-agent-eval, wants to review agent-version regressions, compare baseline vs candidate quality, triage a release, or record a release approve/block decision. Deterministic mock rubric scores only — not a real LLM-judge call, and it never deploys anything.
日本語の概要は準備中です。原文の説明を表示しています。
Busabase App-in-Skill dashboard visualizing a generated MOCK fleet of LLM agents running behind a shared AI gateway for a generic organization. Use when the user invokes $kelly-agent-observability or /kelly-agent-observability, wants to review agent health, call volume, latency, error rates, cost, or trace-level chain breaks across an agent fleet. This is a demo/reference dashboard over a generated mock fleet snapshot seeded into Busabase by a trusted script — never a live monitoring integration, never a real gateway or real agents.
日本語の概要は準備中です。原文の説明を表示しています。