using-karpathy-wiki

Tinjau · 68
Diindeks di Registry

Auto-loaded by the SessionStart hook. Defines when to capture and routes the main agent or detached ingester to the appropriate on-demand skill.

Verified installs0
Star101
Versi1.0.0
Kualitas66/100 · Menjanjikan
Kepercayaan68/100 · Hanya sandbox
Audit79/100 · Perlu ditinjau

Profil aset

Riset dan pekerjaan pengetahuan

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

Lihat kategori

Skenario

Agent riset

I need my agent to research a topic, compare sources, and produce a concise report.

Kecocokan Agent

Claude Code + OpenAI Agents + CLI

Cocok untuk Codex, Claude Code, Cursor, CLI, atau Agent khusus.

Pasang

Siap

npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Pemeliharaan

Terkini

2 hari sejak push

Risiko

Perlu ditinjau

Permission surface may require sandboxing

Kualitas GitHub

101

66/100 Kualitas · 76/100 Kepercayaan

Tag cakupan

RisetAgent risetautomationagent-skill

Catatan ulasan

Permission surface may require sandboxing · Financial research output is not financial advice; require human review before any live investment decision

Kartu adopsi Agent

Kepercayaan, audit, dan kesiapan pemasangan dalam sekali lihat

Skor ini menggabungkan metadata repositori publik, sinyal ulasan OpenAgentSkill, kebaruan pemeliharaan, dan kesiapan pemasangan. Ini adalah sinyal shortlist, bukan pengganti peninjauan manusia.

Kualitas

Menjanjikan
66

Useful candidate, but compare it with alternatives before adopting.

Kepercayaan

Hanya sandbox
68

Kandidat berguna dengan sinyal kepercayaan yang kurang atau bercampur. Gunakan di ruang kerja terisolasi hingga loop hasil membuktikan kecocokan tugas.

Audit

Perlu ditinjau
79

Tinjauan yang dapat dibaca mesin tentang kesiapan pemasangan, metadata keamanan, pemeliharaan, dan risiko adopsi.

Trust Score OpenAgentSkill v5

Tinjauan manusia sebelum pemasangan

Jalankan hanya dalam sandbox dan bandingkan alternatif terdekat sebelum digunakan untuk kerja nyata.

CodexClaude CodeCursorOpenAgentSkill CLI

Star

101 star GitHub

Aktivitas repositori

101 star dan 24 fork

Pemeliharaan

2 hari sejak push

Lisensi

MIT

Pasang

npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Keamanan pemasangan

Jalur pemasangan paket atau runtime standar

Cakupan izin

shell or command execution, filesystem or document access

Hasil Agent

Belum ada data hasil Agent

Dokumentasi

Konteks README/SKILL.md kuat

Ringkasan risiko

Tinjau sebelum produksi

  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Stars/forks activity: 101 stars, 24 forks; issue activity unavailable in current metadata

Kesiapan pemasangan

Jalur pemasangan tersedia

  • Jalur pemasangan tersedia
  • Bukti repositori tersedia
  • Lisensi dinyatakan
  • Belum ada bukti hasil Agent-Proven

Metadata yang dapat dibaca Agent

Data keputusan yang dapat dibaca mesin untuk skill ini.

Gunakan blok ini atau JSON tersemat untuk memutuskan apakah Agent perlu memasang skill ini, memilih alternatif, atau meminta tinjauan manusia terlebih dahulu.

Buka JSON

Tugas yang sesuai

  • Alur kerja Agent riset
  • Tim Claude Code
  • builders willing to evaluate younger projects
  • Sumber pencarian

Agent yang sesuai

CodexClaude CodeCursorOpenAgentSkill CLIOpenAI AgentsCLI

Keputusan pemasangan

Perintah
npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki
Kebijakan
Tinjau
Tinjauan manusia
Ya

Kepercayaan dan risiko

Kepercayaan
68/100
Audit
79/100
Tingkat risiko
Perlu ditinjau

Lingkar hasil

Endpoint
/api/agent/outcome
ID event
resolve
Hasil
5

Perintah pemasangan

npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Jangan gunakan ketika

  • Tim yang membutuhkan SLA dengan dukungan vendor
  • Lingkungan berkompliansi tinggi tanpa tinjauan keamanan internal
  • No major risk signals from current metadata
  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
  • Permission surface may require sandboxing

Keamanan Agent v2

47/100 · Hindari pemasangan otomatis

EksperimentalTinjau

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

Selesaikan via API

Tinggi

Eksekusi shell atau perintah

Metadata skill merujuk terminal, CLI, shell, subprocess, atau alur kerja eksekusi perintah.

Sedang

Akses jaringan

Skill kemungkinan mengambil halaman jarak jauh, API, repositori, atau layanan eksternal.

Sedang

Akses sistem file

Skill dapat membaca atau menulis file proyek, dokumen, artefak yang dihasilkan, atau status workspace lokal.

Sedang

Akses database

Skill dapat memeriksa skema, mengkueri database, atau bekerja dengan penyimpanan persisten.

  • Petunjuk izin berisiko tinggi: eksekusi shell atau perintah
  • Permission surface may require sandboxing

Target pemasangan

Pasang skill ini di alur Agent Anda

Gunakan endpoint publik untuk mengambil perintah, checklist keamanan, prompt target, dan tautan kanonis.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install toolboxmd-using-karpathy-wiki

Rencana resolusi Agent

Biarkan Agent memverifikasi kecocokan sebelum memasang.

API Resolve mengembalikan skill utama, alternatif, kebijakan keamanan, catatan audit, target pemasangan, dan prompt siap pakai.

Buka rencana teks

Agent harus memeriksa

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Salin prompt

Task: Use using-karpathy-wiki in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20using-karpathy-wiki%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/toolboxmd-using-karpathy-wiki/install
Install command: npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Serah-terima Agent

Berikan jalur pemasangan kepada Agent, bukan direktori lain.

Gunakan endpoint publik untuk mengambil perintah, checklist keamanan, prompt target, dan tautan kanonis.

Buka API pemasangan

Prompt Agent

Use using-karpathy-wiki for this task. Review https://www.openagentskill.com/api/skills/toolboxmd-using-karpathy-wiki/install, then install with: npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki

Metadata Registry

Profil yang dapat dibaca Agent untuk pemilihan skill otomatis.

API Registry menyediakan sinyal keputusan, kepercayaan, audit, use case, dan pemasangan tanpa mengikis UI.

Buka Manifest

Kecocokan Agent

68/100

Agent riset

Platform

Claude Code, OpenAI Agents

Laporan audit

Perlu ditinjau · 79/100

Tinjauan yang dapat dibaca mesin tentang kesiapan pemasangan, metadata keamanan, pemeliharaan, dan risiko adopsi.

Lihat laporan auditLihat laporan evaluasi

Panel keputusan Agent

Fallback candidate for Research agents

Prototype with this skill first; keep a fallback candidate ready.

68
Kesiapan
Prototipe
Tahap

Peran di stack

Kandidat cadangan

Kecocokan utama

Agent riset

Label kepercayaan

Buat prototipe dulu

Jalur pemasangan

Perintah siap

Gunakan saat

  • Alur kerja Agent riset
  • Tim Claude Code
  • builders willing to evaluate younger projects

Bukti

  • recent repository activity
  • install command or GitHub repo available
  • profil kualitas 66/100
  • 7 event interaksi OpenAgentSkill

tinjau dulu

  • No major risk signals from current metadata

Jalur implementasi

  1. 1Pasang di Agent sandbox dan jalankan satu tugas Agent riset dari awal hingga akhir.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Profil kepercayaan

Hanya sandbox

Kandidat berguna dengan sinyal kepercayaan yang kurang atau bercampur. Gunakan di ruang kerja terisolasi hingga loop hasil membuktikan kecocokan tugas.

68
Trust Score OpenAgentSkill

Adopsi GitHub

Info

101 star GitHub

Aktivitas star/fork

Periksa

101 star dan 24 fork; aktivitas issue tidak tersedia dalam metadata saat ini

Pemeliharaan terbaru

Lulus

2 hari sejak push

Kejelasan lisensi

Lulus

MIT

Sinyal positif

  • Tinjauan AI disetujui
  • Jalur pemasangan tersedia
  • Bukti repositori tersedia
  • Repositori yang baru dipelihara
  • Perintah pemasangan tidak memiliki pola berisiko tinggi yang jelas
  • Loop hasil siap tetapi membutuhkan eksekusi Agent nyata pertama

Tinjau sebelum memasang

  • Financial research output is not financial advice; require human review before any live investment decision.
  • Quality score needs review
  • Permission surface needs review: shell or command execution, filesystem or document access
  • Stars/forks activity: 101 stars, 24 forks; issue activity unavailable in current metadata
  • Permission surface: shell or command execution, filesystem or document access
  • Belum ada laporan hasil Agent nyata
  • Tinjauan manusia diperlukan sebelum pemasangan tanpa pengawasan

Tindakan yang disarankan

Jalankan hanya dalam sandbox dan bandingkan alternatif terdekat sebelum digunakan untuk kerja nyata.

Profil kualitas

Menjanjikan kandidat untuk alur kerja Agent

Useful candidate, but compare it with alternatives before adopting.

66
Star GitHub
101
Keterkinian
2 hari lalu
Siap dipasang
Ya
Lisensi
MIT

Kecocokan alur kerja

Gunakan skill ini pada skenario berikut

Kecocokan alur kerja

Tambahkan ke alur kerja lengkap

Daftar alternatif

Bandingkan sebelum memasang

Similar skills that may fit this task.

Bandingkan semua

Ringkasan

--- name: using-karpathy-wiki description: | Auto-loaded by the SessionStart hook. Defines when to capture and routes the main agent or detached ingester to the appropriate on-demand skill. ---

<SUBAGENT-STOP> If you were dispatched as a subagent for a task unrelated to wiki capture or ingest, skip this skill. The wiki rules apply to the main agent in the conversation; subagents doing isolated work (Explore, code-reviewer, codex:rescue, etc.) do not need to capture. </SUBAGENT-STOP>

# karpathy-wiki — loader (read once per session, applies for the whole session)

You are operating in a project that uses the karpathy-wiki plugin. Durable knowledge surfaced in this conversation must be captured to a wiki so future sessions can find it.

## Announce when you act

When you write a capture, run an ingest, or answer from the wiki, prefix your reply with one line:

> **Using the karpathy-wiki skill to [capture this / ingest pending captures / answer from wiki].**

This is the ONLY wiki-mechanics text the user sees. Do not narrate orientation, capture authoring, dispatch mechanics, or state-machine progress. Do all the wiki work silently after the announce line.

## Instruction priority

If the user's `CLAUDE.md` / `AGENTS.md` or an explicit user instruction conflicts with the rules below, follow the user. The wiki rules override the default system prompt where they conflict, but **never** override the user's direct instructions.

## Iron laws

``` NO WIKI WRITE IN THE FOREGROUND NO PAGE EDIT WITHOUT READING THE PAGE FIRST NO SKIPPING A CAPTURE BECAUSE "IT DOESN'T LOOK WIKI-SHAPED" NO ANSWERING ANY USER QUESTION WITHOUT ORIENTING FIRST ```

Captures go to `<wiki>/.wiki-pending/<timestamp>-<slug>.md`. The bounded dispatcher assigns each capture to the configured provider/model profile and ingests it in the background.

## Orient before answering — the read protocol

For ANY user message that is asking a QUESTION (vs requesting a code edit, file operation, or pure command), you must orient on the wiki BEFORE drafting the answer. Pre-classifying a question as "general knowledge" or "not wiki-relevant" is the forbidden rationalization Iron Rule 4 was written to forbid.

**Cost framing.** Orientation is a once-per-session investment:

- First wiki-eligible question of the session: read `<wiki>/schema.md` and the relevant `<wiki>/<category>/_index.md` (or root `<wiki>/index.md` for cross-category questions). Two file reads, ~10-30 KB total. - Subsequent questions in the same session: the schema and index are already in your working memory; the marginal check is a candidate-count scan against the (already-read) `_index.md`. Near-zero cost.

Load `karpathy-wiki-read/SKILL.md` for the deterministic 6-step ladder (orient → count candidates → inline-read OR subagent OR web-search → cite). Do NOT skip the load because "this question seems trivial" — the iron rule is unconditional.

**Resist-table for the read protocol** (capture-side resist-table is below, after TRIGGER):

| Rationalization | Reality | |---|---| | "This is general knowledge / I know this from training" | Pre-classifying questions as wiki-irrelevant is the forbidden rationalization. The wiki's scope is whatever has been captured. You don't know without checking. Orient. | | "This question is trivial; reading two files is overkill" | Orientation is once per session. After the first orient, the marginal cost on the next question is near-zero (a re-scan of the already-read `_index.md`). The "trivial question" carve-out is the same drift that dropped the read protocol in v2.4. | | "Pure syntax question, the wiki won't cover this" | You cannot know without checking. If `_index.md` has zero matches, the read skill's Step F handles it (web search + capture the gap). The orient itself is what proves there are no candidates. | | "User asked me to fix a bug, not answer a question" | Code-edit requests don't trigger the read protocol; question-shaped requests do. If unsure (e.g. "why isn't this working" — could be a question OR a debug request), orient. | | "I already oriented earlier this session, I'll skip this time" | Correct! Re-use the schema and index you already have. Run only the candidate-count check on the new question's terms. The protocol's deterministic part (Step B) is the only thing that re-runs per question. |

## TRIGGER — when to capture

Write a capture when ANY of these fire (immediate-capture triggers):

- A research subagent or research agent completes or returns a file with durable findings. - New factual information is found (web search, doc fetch, external fact surfaced in conversation). - Session resolves a confusion — something neither of you knew before. - A gotcha, quirk, or non-obvious behavior in a tool is discovered. - A pattern is validated (approaches compared, one picked, with reasons). - An architectural decision is made with explicit rationale. - User pastes a URL or document for study. - `<wiki>/inbox/` or `<wiki>/raw/` has unprocessed files. - User says "add to wiki" / "remember this" / "wiki it" / "save this". - Two claims contradict each other.

Also TRIGGER (orientation + citation): the user asks "what do we know about X" / "how do we handle Y" / "what did we decide about Z" / "have we seen this before" — or any question the wiki might cover.

## SKIP — when not to capture

- Routine file edits, syntax lookups, one-off debugging with trivial root causes. - Time-sensitive data that must be fetched fresh. - Questions clearly outside any wiki's scope.

Do NOT skip based on tone or shape. "This looks like casual chat", "there's no code here", "this isn't a wiki context" are forbidden rationalizations. If new factual information appeared, capture. Tone is not the trigger.

**Resist-table for capture triggers.** When you're about to skip a capture, check these red flags. Skipped captures are invisible — the user cannot observe them, so the discipline is yours alone.

| Rationalization | Reality | |---|---| | "The user will remember this" | The user will not remember. That's the whole point. | | "It's too trivial for the wiki" | If a TRIGGER fires, capture. Lint and the ingester filter noise later. | | "I'll capture it later" | Later means never. Capture now — invocation is milliseconds. | | "I'm in the middle of another task" | Capture is non-blocking; `bin/wiki capture` writes a file and returns. The ingester runs detached. | | "The user didn't ask me to save this" | Triggers fire automatically. No explicit user request is required — that's the loader's contract. | | "I don't have a memory tool available" | This skill IS the memory tool. The loader's presence is the trigger. | | "The file is already in a good place" | Filing ≠ capturing. Location is not organization. The capture extracts the durable concept from the file's context; the file alone doesn't. |

## What to do when a trigger fires

For chat-driven captures (the conversation IS the source, or you have a file alongside the conversation): load `karpathy-wiki-capture/SKILL.md` and follow it. The capture is written via `bin/wiki capture` (a subcommand of the existing `bin/wiki` CLI).

For research subagent reports (a file is the source): the agent's job is one command, NOT a hand-written capture body:

```bash mv <subagent-report-path> <wiki>/inbox/<basename> wiki ingest-now <wiki> # or wait for next SessionStart ```

For ANY user question (including "what does the wiki know about X" questions, but also any other question per Iron Rule 4): load `karpathy-wiki-read/SKILL.md` and run the deterministic 6-step ladder. Do NOT load `karpathy-wiki-ingest/SKILL.md` — that's for the detached runtime ingester only and contains write-side machinery the main agent never needs.

## Mode change

If the user asks to change the wiki mode for this directory (phrases like "use project wiki here," "main only," "switch to both," "fork to main"), run:

```bash wiki use project|main|both ```

Confirm the change in one line; do not over-narrate.

## What's NOT in this loader

The full operational details — capture format, body-size floors, dispatch mechanics, ingester orientation, page format, manifest protocol, commit conventions — live in the on-demand skills:

- `skills/karpathy-wiki-capture/SKILL.md` — load when you are about to write a capture. - `skills/karpathy-wiki-read/SKILL.md` — load when you are about to answer a user question (Iron Rule 4). - `skills/karpathy-wiki-ingest/SKILL.md` — loaded by the detached ingester via its provider prompt; the main agent never reads this.

If you do not know what to do at a particular step, load the on-demand skill — do not invent.

Detail teknis

Versi
1.0.0
Lisensi
MIT
Pembaruan terakhir
20 Agu 2026
Diterbitkan
20 Agu 2026

Ringkasan keputusan

Kandidat cadangan

68
Siap
Prototipe
Tahap

recent repository activity

Audit

Tinjauan pemasangan

Tinjauan pemasangan dan adopsi

79
Perlu ditinjau
Keamanan
79/100
Pemeliharaan
100/100
Pasang
92/100
Buka audit lengkapLihat laporan evaluasi

Bukti tervalidasi Agent

Bukti tervalidasi Agent

Laporan hasil setelah resolve, tinjau, pasang, dan satu eksekusi terbatas.

0
Terbukti
Needs first agent runPasang otomatis: tinjau duluTerakhir: Tidak diketahui
Tingkat sukses
Kegagalan terbaru
Hasil
0
Kualitas output
Gagal
0
Tidak relevan
0
Pemasangan
0
Diblokir risiko
0
Perlu penyiapan
0
Produksi
0

Belum ada data hasil Agent. Eksekusi pertama dapat melaporkan keberhasilan, kebutuhan setup, blok risiko, kegagalan, atau tidak relevan melalui /api/agent/outcome.

Pasang

Tambahkan ke alur Agent

Gratis dan sumber terbuka. Tinjau laporan sebelum memasang pada Agent produksi.

Siklus pertumbuhan

Kit berbagi

X

Draf berbasis skenario untuk using-karpathy-wiki, siap untuk posting manual di X.

Catatan kurator
using-karpathy-wiki: Auto-loaded by the SessionStart hook. Defines when to capture and routes the main agent or de...

101 stars

https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki?ref=x
Buka draf X
Balasan opsional dengan perintah pemasangan
Listing + install path for using-karpathy-wiki:
https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki?ref=x

Install: npx skills add toolboxmd/karpathy-wiki --skill using-karpathy-wiki
Buka draf balasan

Sumber listing

Diindeks Registry

Dapat diklaim

Listing ini diindeks dari sumber publik dan belum ditandai resmi hingga klaim pemelihara disetujui.

Kreator
toolboxmd
Diindeks oleh
Indeks komunitas OpenAgentSkill

Atribusi menautkan ke repositori publik atau profil kreator. Kreator dapat mengklaim listing untuk memperbarui sinyal kepemilikan.

Klaim skill ini

Klaim pemilik

Klaim listing skill ini

Listing Diindeks Registry ini dikaitkan dengan toolboxmd, tetapi belum ditandai resmi. Klaim untuk menambahkan sinyal pemilik terverifikasi dan membuat pembaruan peluncuran, pemasangan, serta audit berikutnya lebih tepercaya.

Kit backlink kreator

Tambahkan badge bukti ke README Anda

Tampilkan listing kanonis, sinyal kepercayaan dan audit saat ini, serta bukti Agent-Proven nyata di tempat pengembang mengevaluasi repositori.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/toolboxmd-using-karpathy-wiki?metric=listed&label=Listed)](https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/toolboxmd-using-karpathy-wiki?metric=trust&label=Trust)](https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/toolboxmd-using-karpathy-wiki?metric=audit&label=Audit)](https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/toolboxmd-using-karpathy-wiki?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/toolboxmd-using-karpathy-wiki)

Penulis

T

toolboxmd

@toolboxmd

Kecocokan platform

Sinyal kesehatan

Star GitHub
101
Skor kualitas
37/100
Push GitHub terakhir
20 Agu 2026
Petunjuk framework
Tidak diketahui
Tampilan OpenAgentSkill
7
Salinan pemasangan
0
Klik keluar
0

Sinyal komunitas

Bagikan apakah skill ini bermanfaat untuk alur kerja Agent Anda. Masukan gabungan meningkatkan peringkat dari waktu ke waktu.

Kepercayaan & keamanan

Hanya sandbox

68
  • Adopsi GitHub101 star GitHubInfo
  • Aktivitas star/fork101 star dan 24 fork; aktivitas issue tidak tersedia dalam metadata saat iniPeriksa
  • Pemeliharaan terbaru2 hari sejak pushLulus
  • Kejelasan lisensiMITLulus
  • Kelengkapan README/SKILL.mdMetadata memuat konteks penggunaan dan alur kerja yang cukupLulus
  • Risiko dependensi/runtimecommand execution surface, network or browser surfaceInfo