本文へ移動
cccskills
無料GitHub で公開

scf-tranche-reporter

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.

インストール方法を見る

含まれるファイル(1)

  • SKILL.md9.0 KB

SKILL.md(原文)

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。

SCF Tranche Reporter

Overview

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.

When to Use

  • A funded team has completed a tranche milestone and needs to submit deliverables for review
  • A team wants to understand what tranche reviewers expect before they start building
  • A team received feedback requesting more documentation on a previous tranche

How Tranche Review Works

Build Awards are paid in four tranches tied to three milestones:

Tranche% of AwardWhen Released
T010%Automatically on award approval — no deliverables required
T120%After MVP milestone deliverables are reviewed and approved
T230%After Testnet milestone deliverables are reviewed and approved
T340%After Mainnet milestone deliverables (including UX readiness) are approved

Key facts:

  • T0 is automatic — you receive 10% as soon as your project is approved
  • For T1, T2, and T3, you submit milestone deliverables for review via the SCF Build Tranche Completion Form (emailed to you after your T0 payment is sent)
  • Each submission is reviewed by an SCF reviewer (often a Pilot or delegate)
  • The reviewer checks whether each deliverable meets its stated completion criteria
  • If deliverables are incomplete or evidence is insufficient, the team is asked to revise
  • Delays in tranche approval are most commonly caused by insufficient documentation, not incomplete work
  • The team's original application (with its deliverables and completion criteria) is the benchmark

Process

Step 1: Gather Deliverables

Pull the deliverables for this tranche from the original application. For each one, confirm:

  1. What was promised? — Exact deliverable description and completion criteria from the application
  2. What was delivered? — What the team actually built
  3. Any deviations? — If the delivered work differs from what was proposed, explain why

Step 2: Document Each Deliverable

For each deliverable, prepare:

Summary

One paragraph describing what was built and how it meets the completion criteria.

Evidence

Provide concrete, verifiable proof of completion. The type of evidence depends on the deliverable:

Deliverable TypeExpected Evidence
Smart contractDeployed contract address (testnet or mainnet), source code repo, passing test suite
API / BackendAPI documentation, endpoint URLs, request/response examples, source code
Frontend / UILive URL or demo recording, screenshots of key flows, source code
SDK / LibraryPublished package (npm, crates.io, etc.), documentation, usage examples, source code
DocumentationPublished docs URL, table of contents, completeness description
IntegrationWorking integration demo, partner confirmation if applicable, transaction evidence
Protocol / InfrastructureNetwork deployment, performance benchmarks, architecture documentation
Research / DesignPublished report, design files, findings summary

Evidence quality matters:

  • Links must work. Test every URL before submitting.
  • Code must be accessible. Public repo or reviewer-accessible private repo. Include the specific commit hash or tag for the tranche.
  • Demos must be reproducible. If it's a video, show the full flow. If it's a live URL, make sure it's stable.
  • On-chain evidence is strongest. Contract addresses, transaction hashes, and block explorer links are unambiguous.

Completion Criteria Mapping

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].

Step 3: Address Deviations

If anything changed from the original plan:

  • Scope changes — What changed and why. Was scope added, removed, or modified?
  • Timeline changes — If delivery was later than estimated, briefly explain.
  • Approach changes — If the technical approach changed, explain the reasoning.

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.

Step 4: Milestone-Specific Requirements

T1: MVP

  • Must include a technical deliverable interacting with Stellar or Soroban — this is your proof of intent
  • Core functionality should be demonstrable
  • Typically: deployed testnet contract, working prototype, or functional proof of concept alongside working app
  • Not acceptable: design docs, research papers, or environment setup alone

T2: Testnet

  • All core functionality should be working on testnet
  • Audit readiness (if applicable — eligible projects can request an audit through the Audit Bank around this stage, typically after the testnet tranche when nearly mainnet-ready; SDF covers up to 100% of the cost, with a 5% refundable initial co-pay)
  • Integration testing complete
  • This is where the project should be functionally complete and testable, even if not yet production-ready

T3: Mainnet

  • UX readiness is mandatory — Functional interfaces, usable onboarding, documentation for end users
  • Mainnet deployment
  • Comprehensive documentation
  • Launch readiness — the project should be usable by its target audience
  • Include adoption metrics or launch plan

Step 5: Format the Report

Structure the tranche submission report clearly.

Output Format

## 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]

Common Delays and How to Avoid Them

Delay CausePrevention
Broken links in submissionTest every URL before submitting
Private repos without reviewer accessMake repos public or grant explicit access
Vague completion evidence ("see repo")Point to specific files, commits, and test results
Missing deliverables with no explanationAddress every deliverable — even if incomplete, explain status
Demo not reproducibleRecord a backup video; don't rely solely on live URLs
UX not ready at T3Plan UX work from MVP, not as a Mainnet afterthought
Scope changes not disclosedDocument any changes proactively in the submission

What Not to Do

  • Don't submit incomplete tranches without explanation. If a deliverable isn't done, say so and propose a plan.
  • Don't rely on "see the repo" as evidence. Reviewers need specific pointers — files, commits, test results.
  • Don't skip T3 UX requirements. Since SCF 7.0, UX readiness at T3 is mandatory.
  • Don't wait until the last minute. Prepare documentation as you build, not after.
  • Don't change scope silently. If plans changed, document it in the tranche report.

Reference Guides

Reference Links

レビュー

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。

同じリポジトリのスキル

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。

stellar-zk/stellar-zk42026年10月10日 更新

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-zk/stellar-zk42026年10月10日 更新

assets

無料

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。

stellar-zk/stellar-zk42026年10月10日 更新

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。

stellar-zk/stellar-zk42026年10月10日 更新

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。

stellar-zk/stellar-zk42026年10月10日 更新

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。

stellar-zk/stellar-zk42026年10月10日 更新

stellar-zk のスキルをすべて見る

このスキルの問題を報告する