Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
中文简介正在准备中。当前显示原文说明。
Surface current and recent Stellar Community Fund (SCF) round activity. Use when a user says "current SCF round", "what's happening with SCF", "active SCF submissions", "should I apply to SCF this round", "SCF deadline", "who is applying to SCF right now", "SCF round status", or "show me this round's submissions". Fetches live data from communityfund.stellar.org and cross-references with the LumenLoop ecosystem DB to flag repeat builders and category trends.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Fetch https://communityfund.stellar.org/awards. The currently open round has status "Submission". Extract its rec ID from the round's link (/awards/<rec-id>).
The site is a client-rendered React app — plain curl returns mostly empty HTML. Use the WebFetch tool (Claude Code built-in) which handles client-rendered pages via its parsing layer:
WebFetch(
url="https://communityfund.stellar.org/awards",
prompt="Find the round with status 'Submission' (currently open). Return its name (e.g., 'SCF #44'), its rec-id from the link (/awards/<rec-id>), the deadline date, and the maximum award amount."
)
If WebFetch isn't available in the runtime, fall back to a headless-browser fetch (e.g., playwright or puppeteer via uvx) — curl alone won't get rendered content for this site.
Fetch https://communityfund.stellar.org/awards/<round-rec-id>. Parse the submissions list — each entry has: project name, requested amount, status.
If a "See All" link is present, follow it for the full list (not just the first 11 visible on the round page).
For each submission, follow its "view" link → /project/<submission-rec-id>. Fetch in parallel (5 at a time, polite to the server). Extract: project description, category, team members + GitHub links, Stellar integration summary, requested amount.
Load ~/.claude/skills/data/lumenloop/projects.json (or fetch from https://raw.githubusercontent.com/lumenloop/stellar-ecosystem-db/main/... if missing).
For each submission team, check if any team's project is already in the LumenLoop DB. If yes, flag them as repeat builder with their past SCF rounds and total prior funding.
Load ~/.claude/skills/data/electric-capital/stellar-repos.json (~9000 repos). For each submission's GitHub org/user (extracted from team links on /project/<rec-id>), count how many Stellar-tagged repos that org has.
Bucket:
whitebelt/orangebelt/etc → graduated Stellar's training program, applying directly afterThis often reveals more than the LumenLoop check alone, because LumenLoop only catalogs projects with SCF history; many serious builders have GitHub activity but no funded project yet.
Format as:
## SCF Round #<N> — <STATUS>
Deadline: <DATE> (<X days remaining>)
### Top facts
- <N> submissions visible
- Total requested: $<sum>K
- Top 3 categories: <category 1> (N), <category 2> (N), <category 3> (N)
- Repeat builders: <N> teams previously funded by SCF
- First-timers: <N>
### Notable submissions
| Project | Asks | Category | Builder status | What they do |
|---------|------|----------|----------------|--------------|
| ... | $X K | ... | repeat / first-time | one-line description |
### Patterns this round
<2-3 sentences on what categories or themes are dominant>
For each active submission, optionally cross-reference with:
~/.claude/skills/data/ideas/a16z-big-ideas-2025.json — does this submission ride an a16z 2025 thesis (RWA, agentic payments, prediction markets, etc.)?~/.claude/skills/data/ideas/yc-requests-for-startups.json — does YC explicitly want something in this category?Submissions that hit BOTH Stellar ecosystem-fit AND broader investor thesis are 2x more likely to win the round. Flag them as "thesis-aligned" in the summary table.
If user is considering applying:
scf-prescreen-checker to test their idea against the prescreen filterscf-competitor-analyst if they're worried about overlap with other submissionsscf-submission-drafter if ready to draftIf user is researching:
scf.awarded_round patterns in projects.json)~/.stellar-build/cache/scf-round/<rec-id>.json for the session还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Push the LLM to reconsider, refine, and improve its recent output. Use when user asks for deeper critique or mentions a known deeper critique method, e.g. socratic, first principles, pre-mortem, red team.
中文简介正在准备中。当前显示原文说明。
Agentic and machine-to-machine payments on Stellar. Covers x402 (HTTP 402 paid APIs via OZ Channels facilitator, fee-sponsored clients) and MPP (Machine Payments Protocol) in both Charge mode (per-request SAC) and Channel mode (off-chain commits, high-frequency). Defaults to USDC (SEP-41 SAC) on `stellar:testnet`/`stellar:pubnet` (CAIP-2). Use when selling a paid API to AI agents, building an x402 client, or designing a payment-channel architecture for high-frequency agent traffic.
中文简介正在准备中。当前显示原文说明。
Stellar Assets (classic) + trustlines + Stellar Asset Contract (SAC) bridge to smart contracts. Covers asset issuance, distribution, authorization flags, clawback, regulated assets, trustline management, and the SAC interop layer that exposes classic assets as SEP-41 contract tokens. Use when tokenizing real-world assets, issuing stablecoins, managing trustlines, or bridging classic assets to smart contracts.
中文简介正在准备中。当前显示原文说明。
Benchmark stellar-build skills to measure quality and the lift from optimization. Use when the user says "bench my skills", "bench-skills", "benchmark skills", "did optimization help", "measure my skills", "stellar-loop bench", or wants to quantify whether /optimize-skills actually improved things. Held-out eval prompts scored by an LLM judge, reproducible with fixed seeds. Fully local.
中文简介正在准备中。当前显示原文说明。
Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.
中文简介正在准备中。当前显示原文说明。
Technical documentation specialist and knowledge curator. Use when the user asks to talk to Bri or requests the tech writer.
中文简介正在准备中。当前显示原文说明。