Agent skill

Apply Grant

by sendaifun in sendaifun/solana-new

Prepare an Agentic Engineering Grant application by gathering project data, git history, and context files, then presenting all fields needed to fill the Solana Earn grant form.

MITAuto-check passedDevelopment

Install Apply Grant

skills CLI
$ npx skills add sendaifun/solana-new --skill apply-grant -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sendaifun/solana-new apply-grant --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sendaifun/solana-new.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/launch/apply-grant .claude/skills/apply-grant && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
apply-grant
GitHub stars
179
Token cost
~2.2k tokens
SKILL.md length
849 words
Files
3
Skills in repo
13
Repo updated
First seen
Licence
MIT

At a glance

Prepare an Agentic Engineering Grant application by gathering project data, git history, and context files, then presenting all fields needed to fill the Solana Earn grant form.

  • Works in 5 steps: Export session transcript → Collect project context → Generate grant application draft → …
  • The user says apply for grant
  • SKILL.md covers Preamble (run first), Skill Router, Grant Link and Workflow, plus 2 more sections
  • Runs Shell scripts from its folder; calls git, curl and bash

What it does

Apply Grant is an agent skill from sendaifun/solana-new. Prepare an Agentic Engineering Grant application by gathering project data, git history, and context files, then presenting all fields needed to fill the Solana Earn grant form. Use when the user says "apply for grant", "agentic engineering grant", "apply-grant", "grant application", "fill grant form", "200 USDG grant", "ST earn", "Superteam earn", "Superteam grant", "earn grant", "help me apply for grant", "solana earn grant", or "submit grant".

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `export-session.sh` and `openai.yaml`).

It sits in Development, covering Git workflow. It works with Solana. The repository describes itself as: think. build. ship. tasteful & useful crypto apps. using a curated skills + knowledge base for AI agents on solana contracts & integrations. The licence is MIT.

When your agent uses it

  • The user says apply for grant
  • Agentic engineering grant
  • Grant application
  • Fill grant form

Example prompts

  • “apply for grant”
  • “agentic engineering grant”
  • “apply-grant”
  • “/apply-grant”

Requirements

  • A Bash shell

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Export session transcript
  2. Collect project context
  3. Generate grant application draft
  4. Present the draft
  5. Iterate

What it can do on your machine

Read from SKILL.md and the folder at commit 38a494a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships script files (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • git
    • curl
    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • superteam.fun
    • colosseum.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Apply Grant loads about 2.2k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 849 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~116
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sendaifun/solana-new at commit 38a494a, republished under its MIT licence (© sendaifun). 849 words, ~2,223 tokens.

Download SKILL.mdSave it as .claude/skills/apply-grant/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
apply-grant
description
Prepare an Agentic Engineering Grant application by gathering project data, git history, and context files, then presenting all fields needed to fill the Solana Earn grant form. Use when the user says "apply for grant", "agentic engineering grant", "apply-grant", "grant application", "fill grant form", "200 USDG grant", "ST earn", "Superteam earn", "Superteam grant", "earn grant", "help me apply for grant", "solana earn grant", or "submit grant".

Preamble (run first)

bash
_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"telemetryTier": *"[^"]*"' | head -1 | sed 's/.*"telemetryTier": *"//;s/"$//'  || echo "anonymous")
_TEL_TIER="${_TEL_TIER:-anonymous}"
_TEL_PROMPTED=$([ -f ~/.superstack/.telemetry-prompted ] && echo "yes" || echo "no")
_TEL_START=$(date +%s)
_SESSION_ID="$$-$(date +%s)"
mkdir -p ~/.superstack
echo "TELEMETRY: $_TEL_TIER"
echo "TEL_PROMPTED: $_TEL_PROMPTED"
if [ "$_TEL_TIER" != "off" ]; then
_TEL_EVENT='{"skill":"apply-grant","phase":"launch","event":"started","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'"}' 
echo "$_TEL_EVENT" >> ~/.superstack/telemetry.jsonl 2>/dev/null || true
_CONVEX_URL=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"convexUrl":"[^"]*"' | head -1 | cut -d'"' -f4 || echo "")
[ -n "$_CONVEX_URL" ] && curl -s -X POST "$_CONVEX_URL/api/mutation" -H "Content-Type: application/json" -d '{"path":"telemetry:track","args":{"skill":"apply-grant","phase":"launch","status":"success","version":"0.2.0","platform":"'$(uname -s)-$(uname -m)'","timestamp":'$(date +%s)000'}}' >/dev/null 2>&1 &
true
fi

If TEL_PROMPTED is no: Before starting the skill workflow, ask the user about telemetry. Use AskUserQuestion:

Help superstack get better! We track which skills get used and how long they take — no code, no file paths, no PII. Change anytime in ~/.superstack/config.json.

Options:

  • A) Sure, help superstack improve (anonymous)
  • B) No thanks

If A: run this bash:

bash
echo '{"telemetryTier":"anonymous"}' > ~/.superstack/config.json
_TEL_TIER="anonymous"
touch ~/.superstack/.telemetry-prompted

If B: run this bash:

bash
echo '{"telemetryTier":"off"}' > ~/.superstack/config.json
_TEL_TIER="off"
touch ~/.superstack/.telemetry-prompted

This only happens once. If TEL_PROMPTED is yes, skip this entirely and proceed to the skill workflow.


Apply for Agentic Engineering Grant

Gather everything the user needs to submit an Agentic Engineering Grant Application on Solana Earn. The grant is fixed at 200 USDG. Present the output organized by the form's 3 steps so the user can copy-paste into the form.

Skill Router

{{SKILL_ROUTER.md}}


Submit here: https://superteam.fun/earn/grants/agentic-engineering

Always show this link to the user at the start and end of the skill.

Workflow

Phase 0 — Export session transcript

Before anything else, run the bundled export script to copy the current AI session transcript to the project root:

bash
bash ~/.claude/skills/apply-grant/export-session.sh .

The script automatically:

  • Finds the latest Claude Code session .jsonl from ~/.claude/projects/<project-slug>/ → copies as ./claude-session.jsonl
  • Finds the latest Codex session from ~/.codex/sessions/ → copies as ./codex-session.jsonl

After running, confirm to the user which file(s) were exported and where they are. These files are proof of AI-assisted development for the grant application.

Fallback: If the script fails or no session is found, tell the user to manually export:

  • Claude Code: Run /export in the chat — this saves a .txt transcript to the working directory. Attach that file instead.
  • Codex: Session logs are in ~/.codex/sessions/ — find the latest .jsonl and copy it to the project root.
Phase 1 — Collect project context
  1. Look for idea-context.md, build-context.md, README.md, package.json, Cargo.toml, or Anchor.toml in the working directory.
  2. Read git log --oneline -20 for recent work history.
  3. Read git remote -v to get the GitHub repo URL.
  4. Check for any prior phase handoff files in skills/data/specs/.
  5. Ask the user for any missing required fields (TG username, wallet address, X profile) that cannot be inferred.
Phase 2 — Generate grant application draft

Present the output as a copy-paste-ready draft organized by the 3 form steps:


Step 1: Basics
FieldRequiredWhat to fill
Project TitleYesInfer from package.json name, Anchor.toml, or README title. Ask if unclear.
One Line DescriptionYesGenerate a concise one-liner from project context.
TG usernameYesAsk the user. Format: t.me/<username>
Wallet AddressYesAsk the user for their Solana wallet address.
Step 2: Details
FieldRequiredWhat to fill
Project DetailsYesWrite a 2-4 paragraph description covering the problem statement and proposed solution. Pull from idea-context.md, build-context.md, and README.
DeadlineYesAsk the user for their target shipping deadline (timezone: Asia/Calcutta).
Proof of WorkYesCompile from: git history, shipped demos, deployed programs, live URLs, prior hackathon submissions, agent demos. Include links.
Personal X ProfileYesAsk the user. Format: x.com/<handle>
Personal GitHub ProfileNoInfer from git config or remote URL. Format: github.com/<username>
Colosseum Crowdedness ScoreYesRemind the user to visit https://colosseum.com/copilot to get their project's Crowdedness Score, take a screenshot, upload to a publicly accessible Google Drive, and paste the link.
AI Session TranscriptYesAuto-exported in Phase 0. The file is at ./claude-session.jsonl (Claude Code) or ./codex-session.jsonl (Codex) in the project root — user should attach this to the form.
Show full SKILL.md (289 more words)Show less
Step 3: Milestones
FieldRequiredWhat to fill
Goals and MilestonesYesGenerate 3-5 concrete milestones with dates based on the project scope and deadline.
Primary KPIYesSuggest a single measurable metric (e.g., "X daily active users", "Y TVL", "Z transactions per day"). Ask user to confirm.
Final tranche checkboxYesRemind the user: to receive the final tranche, they must submit the Colosseum project link, GitHub repo, and AI subscription receipt.

Phase 3 — Present the draft

Output the complete application as a structured markdown document with clear section headers matching the form steps. Use blockquotes (>) for each field value so the user can easily copy them.

Format example:

## Step 1: Basics

**Project Title**
> MyProject

**One Line Description**
> A one-liner describing the project.

**TG username**
> t.me/username

**Wallet Address**
> <user's wallet>
Phase 4 — Iterate

After presenting the draft:

  1. Ask the user to review each section.
  2. Offer to refine any field.
  3. Remind the user about the exported session file(s) in the project root.
  4. Show the grant submission link: https://superteam.fun/earn/grants/agentic-engineering
  5. Summarize what files the user should have ready to submit:
    • Session transcript (./claude-session.jsonl or ./codex-session.jsonl)
    • Colosseum Crowdedness Score screenshot
    • The copy-paste-ready application text above

Important Notes

  • The grant amount is fixed at 200 USDG.
  • Always generate proof of work from actual git history and project artifacts — never fabricate.
  • If the project has a Colosseum submission, reference it in proof of work.
  • If prior skills have been used (idea validation, scaffold, build), reference those outputs as proof of work.
  • Keep the tone professional but concise — grant reviewers read many applications.

Telemetry (run last)

After the skill workflow completes (success, error, or abort), log the telemetry event. Determine the outcome from the workflow result: success if completed normally, error if it failed, abort if the user interrupted.

Run this bash:

bash
_TEL_END=$(date +%s)
_TEL_DUR=$(( _TEL_END - ${_TEL_START:-$_TEL_END} ))
_TEL_TIER=$(cat ~/.superstack/config.json 2>/dev/null | grep -o '"telemetryTier": *"[^"]*"' | head -1 | sed 's/.*"telemetryTier": *"//;s/"$//' || echo "anonymous")
if [ "$_TEL_TIER" != "off" ]; then
echo '{"skill":"apply-grant","phase":"launch","event":"completed","outcome":"OUTCOME","duration_s":"'"$_TEL_DUR"'","session":"'"$_SESSION_ID"'","ts":"'$(date -u +%Y-%m-%dT%H:%M:%SZ)'","platform":"'$(uname -s)-$(uname -m)'"}' >> ~/.superstack/telemetry.jsonl 2>/dev/null || true
true
fi

Replace OUTCOME with success/error/abort based on the workflow result.

© sendaifun, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files in skills/launch/apply-grant of sendaifun/solana-new.

  • SKILL.md
  • export-session.sh
  • openai.yaml

Open the folder on GitHubat commit 38a494a

Compare with similar skills

Apply Grant next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Apply Grant compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Apply Grant this skillsendaifun/solana-new179—~2.2kAutomated safety check: PassMIT
Finishing a Development Branchobra/superpowers297k5 repos~1.9kAutomated safety check: PassMIT
Contributor-First PR MergeHKUDS/OpenHarness16k1 repos~847Automated safety check: PassMIT
Migrate Internal Package into GhostTryGhost/Ghost56k—~3.8kAutomated safety check: PassMIT
Create Pull Requestcline/cline70k1 repos~1.6kAutomated safety check: PassApache-2.0
Contextual Commit Messagesyamadashy/repomix29k1 repos~2.7kAutomated safety check: PassMIT

Similar skills

  • Walks the last step of a branch: confirm tests pass, detect the git environment, ask how to integrate, carry out your choice and clean up the worktree.

    297k GitHub starsUsed in 5 repos~1.9k tokens
    DevelopmentAuto-check passed
  • Merges external GitHub pull requests while keeping the original author credited, and fixes conflicts after the merge instead of rewriting the contribution.

    16k GitHub starsUsed in 1 repo~847 tokens
    DevelopmentAuto-check passed
  • Moves a package from another TryGhost repository into Ghost as an internal workspace package while keeping its Git history, with checkpoints for the steps that need an administrator.

    56k GitHub stars~3.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Opens a GitHub pull request from your current branch with the gh CLI, after reviewing the commits and diff and gathering the details the PR needs.

    70k GitHub starsUsed in 1 repo~1.6k tokens
    DevelopmentAuto-check passed
  • Writes Conventional Commits whose bodies carry action lines recording the intent, decisions and constraints behind a change, not only what changed.

    29k GitHub starsUsed in 1 repo~2.7k tokens
    DevelopmentAuto-check passed
  • Git Merge Conflict Resolver

    tailcallhq/forgecode

    Resolves Git merge conflicts with a plan-first workflow that keeps both sides' intent, regenerates lock files and backs up deleted-but-modified files.

    7.6k GitHub starsUsed in 1 repo~4.5k tokens
    DevelopmentAuto-check passed

More from sendaifun/solana-new

All 13 skills in this repo
  • Find Next Crypto Idea

    sendaifun/solana-new

    Interview users sharply to discover, rank, or validate what they should build in crypto.

    179 GitHub stars~2.5k tokensUpdated 8 days ago
    Auto-check passed
  • Colosseum Copilot

    sendaifun/solana-new

    Search and analyze 5,400+ Solana hackathon projects using Colosseum Copilot.

    179 GitHub stars~2.9k tokensUpdated 8 days ago
    Auto-check passed
  • Competitive Landscape

    sendaifun/solana-new

    Map the competitive landscape for a crypto product idea. An agent skill from sendaifun/solana-new.

    179 GitHub stars~1.7k tokensUpdated 8 days ago
    Auto-check passed
  • Defillama Research

    sendaifun/solana-new

    Research DeFi protocols and market opportunities using DefiLlama data.

    179 GitHub stars~1.8k tokensUpdated 8 days ago
    Auto-check passed
  • Deploy To Mainnet

    sendaifun/solana-new

    Guide a Solana project from devnet to mainnet production deployment.

    179 GitHub stars~1.8k tokensUpdated 8 days ago
    Auto-check passed
  • Solana Beginner

    sendaifun/solana-new

    Teach Solana fundamentals to developers new to the ecosystem.

    179 GitHub stars~2.4k tokensUpdated 8 days ago
    Auto-check passed

Works with

Categories

Questions about Apply Grant

What does Apply Grant do?

Prepare an Agentic Engineering Grant application by gathering project data, git history, and context files, then presenting all fields needed to fill the Solana Earn grant form. Apply Grant is an agent skill from sendaifun/solana-new. Prepare an Agentic Engineering Grant application by gathering project data, git history, and context files, then presenting all fields needed to fill the Solana Earn grant form.

When should I use Apply Grant?

Apply Grant fits situations like: the user says apply for grant; agentic engineering grant; grant application; fill grant form.

How do I install Apply Grant in Claude Code?

Run `npx skills add sendaifun/solana-new --skill apply-grant -a claude-code`. Or copy the skill folder (skills/launch/apply-grant in sendaifun/solana-new) into .claude/skills/apply-grant in your project. Claude Code loads it when a task matches its description.

How do I install Apply Grant in Codex?

Run `npx skills add sendaifun/solana-new --skill apply-grant -a codex`. Or copy the skill folder (skills/launch/apply-grant in sendaifun/solana-new) into .agents/skills/apply-grant in your project. Codex loads it when a task matches its description.

Can I use Apply Grant in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sendaifun/solana-new --skill apply-grant -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/apply-grant, .gemini/skills/apply-grant, .github/skills/apply-grant and .opencode/skills/apply-grant in your project.

What does Apply Grant need to run?

Going by SKILL.md and its folder, Apply Grant needs a shell for the scripts in its folder and the command-line tools its instructions call (git, curl and bash). Our summary lists: A Bash shell.

Does Apply Grant access the network?

SKILL.md names 2 domains. As links in the text: superteam.fun and colosseum.com. This is read from the text; nothing was executed.

Is Apply Grant safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Apply Grant use?

Apply Grant is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Apply Grant use?

About 2.2k tokens (SKILL.md is roughly 8.9k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Apply Grant?

Skills that share tags, products or a category with Apply Grant: Finishing a Development Branch (obra/superpowers, 297k stars), Contributor-First PR Merge (HKUDS/OpenHarness, 16k stars), Migrate Internal Package into Ghost (TryGhost/Ghost, 56k stars) and Create Pull Request (cline/cline, 70k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Apply Grant?

sendaifun (a GitHub organization) maintains it in sendaifun/solana-new, which has 179 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 2, 2026.

Source: sendaifun/solana-new on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.