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.
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。
Help funded SCF teams write tranche submission reports. Use when a team has completed a tranche milestone and needs to document their deliverables for review to unlock the next payment. Covers deliverable documentation, completion evidence, demo preparation, and the specific format tranche reviewers expect.
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。
Helps funded SCF Build Award teams write tranche submission reports that clearly demonstrate deliverable completion. Each tranche must be reviewed and approved before the next payment is released. A well-documented tranche submission speeds up review and avoids back-and-forth delays.
Build Awards are paid in four tranches tied to three milestones:
| Tranche | % of Award | When Released |
|---|---|---|
| T0 | 10% | Automatically on award approval — no deliverables required |
| T1 | 20% | After MVP milestone deliverables are reviewed and approved |
| T2 | 30% | After Testnet milestone deliverables are reviewed and approved |
| T3 | 40% | After Mainnet milestone deliverables (including UX readiness) are approved |
Key facts:
Pull the deliverables for this tranche from the original application. For each one, confirm:
For each deliverable, prepare:
One paragraph describing what was built and how it meets the completion criteria.
Provide concrete, verifiable proof of completion. The type of evidence depends on the deliverable:
| Deliverable Type | Expected Evidence |
|---|---|
| Smart contract | Deployed contract address (testnet or mainnet), source code repo, passing test suite |
| API / Backend | API documentation, endpoint URLs, request/response examples, source code |
| Frontend / UI | Live URL or demo recording, screenshots of key flows, source code |
| SDK / Library | Published package (npm, crates.io, etc.), documentation, usage examples, source code |
| Documentation | Published docs URL, table of contents, completeness description |
| Integration | Working integration demo, partner confirmation if applicable, transaction evidence |
| Protocol / Infrastructure | Network deployment, performance benchmarks, architecture documentation |
| Research / Design | Published report, design files, findings summary |
Evidence quality matters:
For each completion criterion from the original application, explicitly state how it was met:
**Completion Criterion:** "Soroban contract deployed on testnet with passing test suite"
**Status:** Met
**Evidence:** Contract deployed at [address] on Stellar Testnet. Test suite: 47 tests passing (see CI run [link]). Source code: [repo link, commit hash].
If anything changed from the original plan:
Small deviations are normal and expected. Reviewers want transparency, not perfection. What causes problems is undisclosed changes or missing deliverables with no explanation.
If a tranche's scope has materially changed, contact the SCF team before submitting the modified tranche — explain what changed and why, and update your success metrics or proof formats if needed. Then submit through the SCF Build Tranche Completion Form.
Structure the tranche submission report clearly.
## Tranche [N] Submission: [Project Name]
**Award ID:** [SCF award identifier]
**Tranche:** T[N] ([percentage]%)
**Submission Date:** [Date]
---
### Deliverable 1: [Name]
**Description:** [What was promised]
**What was delivered:** [Brief summary of what was built]
**Completion Criteria:**
| Criterion | Status | Evidence |
|---|---|---|
| [Criterion from application] | Met | [Link/proof] |
| [Criterion from application] | Met | [Link/proof] |
**Links:**
- Source code: [repo URL, commit/tag]
- Deployment: [URL or contract address]
- Demo: [video or live URL]
---
### Deliverable 2: [Name]
[Same structure]
---
### Deviations from Original Plan
[If any — describe what changed and why. If none, state "No deviations from the original application."]
### Additional Notes
[Anything the reviewer should know — blockers resolved, lessons learned, plans for next tranche]
| Delay Cause | Prevention |
|---|---|
| Broken links in submission | Test every URL before submitting |
| Private repos without reviewer access | Make repos public or grant explicit access |
| Vague completion evidence ("see repo") | Point to specific files, commits, and test results |
| Missing deliverables with no explanation | Address every deliverable — even if incomplete, explain status |
| Demo not reproducible | Record a backup video; don't rely solely on live URLs |
| UX not ready at T3 | Plan UX work from MVP, not as a Mainnet afterthought |
| Scope changes not disclosed | Document any changes proactively in the submission |
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
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.
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。
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.
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。
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.
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。
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.
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。
Facilitate interactive brainstorming sessions using diverse creative techniques and ideation methods. Use when the user says help me brainstorm or help me ideate.
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。
Technical documentation specialist and knowledge curator. Use when the user asks to talk to Bri or requests the tech writer.
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。