Index of every page on this site: llms.txt
All skills
kunchenguid avatar
by Kun Chenkunchenguid/kun503 stars
46
Run it yourself

Summon Kun to solve your problems. Use on /kun or when asked how Kun thinks, builds, or solves problems.

Use this Skill: https://skilld.dev/gh/kunchenguid/kun/kun

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈27 tokens for metadata: the name and description. ≈299 when used: this file.

Description uses 1.4% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈110 characters, or 1.4%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

/kun

Load the latest instructions from kunchenguid/kun via the public pull script, then answer from the local cache. Do not guess file contents.

Loading instructions

1. Pull (no LLM)

Download the public pull script, then run it with Node. Prefer raw GitHub; use jsDelivr only as fallback:

  • https://raw.githubusercontent.com/kunchenguid/kun/main/scripts/pull-kun.mjs
  • fallback: https://cdn.jsdelivr.net/gh/kunchenguid/kun@main/scripts/pull-kun.mjs
# cache defaults to $KUN_PULL_DIR or ~/.cache/kun
node /path/to/pull-kun.mjs --dir <cache>

The script is incremental via content/MANIFEST.json: it syncs root docs (ENTRY.md, TOOLS.md, OPINIONS.md, VOICE.md) and only new/changed content/ files. Do not re-fetch every content file by hand.

If the pull fails, stop and say so. Do not guess.

2. Read from the local cache

After a successful pull, read the FULL local copies from <cache>:

  • ENTRY.md
  • TOOLS.md
  • OPINIONS.md
  • VOICE.md

When a question needs Kun's actual words, open matching files under <cache>/content/ (do not dump the whole tree into context).

3. Answer

Follow ENTRY.md exactly to answer the user.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

1 alert1mo3 checks · Risk SAFE
  • Gen Agent Trust Hub1mo

    The skill fetches its core instructions and personality guidelines from the author's GitHub repository at runtime. This allows the skill to be updated without changing the skill definition, but introduces a dependency on the availability and integrity of the external GitHub repository.

  • Socket1mo

    1 alert: gptSecurity

  • Snyk1mo

    Risk: CRITICAL · 2 issues

Signed by skilld at d43b5d9. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub yesterday.

Activeupdated 2 months ago
user-invocable
true
metadata
{
  "short-description": "Summon Kun to solve your problems."
}

README badge

README badge for kunchenguid/kun