agentsmith

KO | EN

gitlite — search

#php #java #html #git #rust #chatgpt #json #graphql #kubernetes #css

(★ 9)

Agent rules and reusable skills from my daily setup

파일 탐색기

ZIP 다운로드

- - pages.yml
- learnings.md
- - copilot-api.json
  - hackathon-winners.md
- - defillama-api.json
- - a16z-big-ideas-2025.md
  - a16z-state-of-crypto-2025.md
  - alliance-ideas.md
  - deploy-runbook.md
  - rpc-wallet-guide.md
  - rwa-defi-2026-ideas.md
  - security-checklist.md
  - yash-defi-2024-ideas.md
  - yc-crypto-companies-p2.md
  - yc-crypto-companies.md
  - yc-requests-for-startups.md
- - a16z-big-ideas-2025.json
  - a16z-state-of-crypto-2025.json
  - alliance-ideas.json
  - rwa-defi-2026-ideas.json
  - superteam-ideas.json
  - web3-ideas-combined.json
  - web3-ideas-summary.json
  - yash-defi-2024-ideas.json
  - yc-crypto-companies.json
  - yc-requests-for-startups.json
- - 01-what-and-why-solana.md
  - 02-what-makes-solana-unique.md
  - 03-contract-level.md
  - 04-protocols-and-sdks.md
  - 05-app-layer-consumer.md
  - 06-opensource-research.md
  - cookbook-index.md
- - phase-handoff.md
- - SKILL.md
- - SKILL.md
- - EXAMPLES.md
  - REFERENCE.md
  - SKILL.md
- - SKILL.md
- - PROMPTS.md
  - SKILL.md
- - REFERENCE.md
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - .gitkeep
- - .gitkeep
- - .gitkeep
- - .gitkeep
- README.md
- 12-factor-agents.md
- advanced-context-engineering.md
- agent-smith-flow.html
- maciejdziuba-agentic-coding.md
- - sync.cpython-314.pyc
- AGENTS.md
- omp-config.example.yml
- README.md
- settings.example.json
- sync.py
- build-index.py
- - SKILL.md
- - .gitattributes
  - .gitignore
  - CHANGELOG.md
  - CLAUDE.md
  - CONTRIBUTING.md
  - LICENSE
  - package.json
  - README.md
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - README.md
  - SKILL.md
- - README.md
  - SKILL.md
- - README.md
  - SKILL.md
- - README.md
  - SECURITY.md
  - SKILL.md
- - README.md
  - SKILL.md
- - README.md
  - SKILL.md
- - README.md
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - ADR-FORMAT.md
  - CONTEXT-FORMAT.md
  - SKILL.md
- - SKILL.md
- - AGENTS.md
  - LICENSE
  - README.md
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - DEEPENING.md
  - INTERFACE-DESIGN.md
  - LANGUAGE.md
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - LICENSE.txt
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - LOGIC.md
  - SKILL.md
  - UI.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - domain.md
  - issue-tracker-github.md
  - issue-tracker-gitlab.md
  - issue-tracker-local.md
  - SKILL.md
  - triage-labels.md
- - SKILL.md
- - LICENSE.txt
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - FORMAT.md
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - deep-modules.md
  - interface-design.md
  - mocking.md
  - refactoring.md
  - SKILL.md
  - tests.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - AGENT-BRIEF.md
  - OUT-OF-SCOPE.md
  - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
  - template.sh
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- - SKILL.md
- agentic-engineering.md
- orchestration.md
.gitignore
.nojekyll
AGENTS.md
ATTRIBUTION.md
CONTRIBUTING.md
README.md
SKILLS.md
skills.sh.json

# CDN으로 사용하기

jsDelivr

jsDelivr는 공개 GitHub 리포지토리를 별도 설정 없이 CDN으로 즉시 서빙합니다. 버전과 파일을 고르면 웹페이지에 바로 붙일 수 있는 링크와 예시 코드가 만들어집니다.

버전

파일

링크

예시

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

Agent rules and reusable skills from my daily setup, with a separate workspace for plugin packaging.

![skills](https://img.shields.io/badge/skills-125-1a1a1a?style=flat-square&labelColor=1a1a1a&color=FF51FF)
![rules](https://img.shields.io/badge/rules-25-1a1a1a?style=flat-square)
![coding](https://img.shields.io/badge/coding-62-1a1a1a?style=flat-square)
![crypto](https://img.shields.io/badge/crypto-24-1a1a1a?style=flat-square)
![writing](https://img.shields.io/badge/writing-6-1a1a1a?style=flat-square)
![product](https://img.shields.io/badge/product-8-1a1a1a?style=flat-square)

</div>

## Install

Install selected skills:

```bash
npx skills add Sarthib7/agentsmith
```

Install everything globally:

```bash
npx skills add Sarthib7/agentsmith --all -g
```

Read one skill without installing it:

```bash
npx skills use Sarthib7/agentsmith@caveman
```

Browse the collection on [Skills.sh](https://www.skills.sh/sarthib7/agentsmith) or open the full generated [skill catalog](SKILLS.md).

Changes and new skills: [CONTRIBUTING.md](CONTRIBUTING.md).

## Start here

Read in this order:

1. [`rules/`](rules/) — the standing instructions every session runs under. Everything else assumes them.
2. [`my-skills/`](my-skills/) — the skills written here, then the full collection via the [skill catalog](SKILLS.md).
3. [`workflows/`](workflows/) — the operating workflows the rules link to.

## Repository layout

```text
agentsmith/
├── AGENTS.md          rules for contributing to this repository
├── CONTRIBUTING.md    contributor workflow and validation steps
├── rules/             global AGENTS.md snapshot and harness config examples
├── workflows/         reusable operating workflows linked by agent rules
├── skills/            collected skills used in my setup
├── my-skills/         skills with verified sarthib7 authorship
├── plugin/            agents, commands, hooks, and manifests
├── scripts/           catalog generation and validation
├── data/              shared skill reference data
├── SKILLS.md          generated skill catalog
└── skills.sh.json     generated skills.sh grouping manifest
```

Ownership and purpose stay separate. `skills/` answers what I use. `my-skills/` answers what I wrote. [ATTRIBUTION.md](ATTRIBUTION.md) records known authors, licenses, and source gaps.

## My skills

These eight skills declare `author: sarthib7` in their source:

| Skill | Purpose |
|---|---|
| [`adhd`](my-skills/adhd/SKILL.md) | Parallel divergent ideation for coding agents |
| [`bench-it`](my-skills/bench-it/SKILL.md) | Compare performance claims against a named baseline |
| [`deterministic-code-review`](my-skills/deterministic-code-review/SKILL.md) | Review diffs with frozen scope, exact anchors, and a falsification pass |
| [`followup-review`](my-skills/followup-review/SKILL.md) | Review fixes made after an earlier code review |
| [`fresh-eyes`](my-skills/fresh-eyes/SKILL.md) | Get an independent second opinion without shared context |
| [`git-worktree-runner`](my-skills/git-worktree-runner/SKILL.md) | Run isolated agent tasks through `git gtr` worktrees |
| [`prove-it`](my-skills/prove-it/SKILL.md) | Verify that a check passes and can fail |
| [`research-url`](my-skills/research-url/SKILL.md) | Research a URL with one subagent per URL into a fixed-format report plus learnings |

Authorship stays conservative. A skill remains in `skills/` when its origin is uncertain.

## How the pieces fit

`rules/` contains standing instructions loaded for every session. One `AGENTS.md` snapshot serves every harness: Oh My Pi and Codex read `AGENTS.md` natively, and Claude Code reads the same policy from its live `CLAUDE.md` source. [`workflows/orchestration.md`](workflows/orchestration.md) records how delegation and parallel agents run on top of those rules.

`skills/` and `my-skills/` contain task procedures. Each skill has a `SKILL.md` entry point and may include references, scripts, templates, or assets.

`plugin/` is the packaging workspace. Its capability split follows the [Vercel plugin](https://github.com/vercel/vercel-plugin): specialist agents, commands, hooks, and platform manifests remain separate from skill source. The plugin is a scaffold today and has no published manifest.

## DYOR

Treat every skill as untrusted until you review it. Inclusion in this collection is not a security review or endorsement.

Before installing a skill:

- Read its `SKILL.md`, scripts, hooks, and requested permissions.
- Check its source and license in [ATTRIBUTION.md](ATTRIBUTION.md).
- Record the commit SHA you reviewed when reproducibility matters.
- Test unfamiliar skills in an isolated repository or worktree.

## Known limitations

- Some Solana and DeFi skills reference `../../../data/...`. Those paths depend on the installation layout.
- `skills/spec-build/` declares `name: build` because the skills CLI treats a directory named `build` as generated output.
- `skills/tempo-request/` declares `name: tempo`, matching its upstream source.
- Provenance is incomplete for skills that arrived without author metadata, a license, or a recorded source.

Generated files should not be edited by hand. Follow [CONTRIBUTING.md](CONTRIBUTING.md) when changing the collection.

agentsmith

파일 탐색기

# CDN으로 사용하기

Was this content helpful?

Recent Feedback

Download README