claude SKILL.md skillA

claude from dzhng/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add dzhng/skills/claude@git:20261015.f6819ca

Pins git:20261015.f6819ca in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
dzhng/skills
Path
skills/engineering/claude/SKILL.md
Versions recorded
4
Latest version
git:20261015.f6819ca, committed Oct 15, 2026
First version recorded
Jul 3, 2026
Size
6,468 bytes
Repository stars
1,377
License
MIT

Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent opinion from Claude, or asks to delegate a well-scoped task to Claude. Supports selecting `--model` and thinking/effort level with defaults of the current `opus` alias and `high`.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# Claude

Claude Code is an independent agent on PATH (`claude`), sharing this working
tree and already authenticated. Use it as a second opinion or delegated worker,
not as ground truth: verify its claims, own any changes, and keep its task
contract narrow.

## Defaults

Use `claude -p --model opus --effort high` unless the user or task calls for a
different model or thinking level. Keep `opus` as an alias so Claude Code
resolves the current Opus release; do not pin a dated model ID in this skill.

- **Model:** prefer aliases such as `opus`, `sonnet`, or `fable`, which follow
  the current Claude releases. Accept a full model name only when the user or
  task requires that specific model, and verify it is current first. Default
  `opus`.
- **Thinking level:** pass Claude Code's `--effort` flag. Valid levels are
  `low`, `medium`, `high`, `xhigh`, and `max`. Default `high`.
- **Cost guard:** for exploratory asks, add `--max-budget-usd <amount>` when
  the user gives a budget or the task is likely to sprawl.

Example:

```sh
claude -p --model opus --effort high "<prompt>"
```

## Prompting Claude

Prompt Claude like an operator: compact, block-structured, and explicit about
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add dzhng/skills/claude@sha256:601c5497920d0947

The line at the top of this page pins the label git:20261015.f6819ca, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_uetn2bo2dmacsxfu.svg)](https://markdownregistry.com/a/art_uetn2bo2dmacsxfu)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 4 versions of this file, between Jul 3, 2026 and Oct 15, 2026, about one every 35 days.

versioncommittedcommitsizeaudit
git:20261015.f6819ca latest2026-10-15 f6819ca 6,468 BA view · diff
git:20261014.0e1d4562026-10-14 0e1d456 6,126 BA view · diff
git:20260705.6bcf1392026-07-05 6bcf139 5,321 BA view · diff
git:20260703.dfeecab2026-07-03 dfeecab 5,284 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (6468 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

dzhng/skills · 1,377 stars · license MIT · pushed 2026-10-21 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_uetn2bo2dmacsxfu
GET https://markdownregistry.com/api/v1/resolve?ref=dzhng/skills/claude
GET https://markdownregistry.com/api/v1/blob/601c5497920d09470d06d6b655fcc453472d26500729deef0caebab5a2af7110

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from dzhng/skills

audit-agents SKILL.md skill
dzhng/skills · skills/authoring/audit-agents/SKILL.md · Audit or rewrite AGENTS.md so it holds only lasting principles. Run it only when the user asks for it by name; never…
git:20261002.5fa4602 · audit A · 1,377 stars
eval-skills SKILL.md skill
dzhng/skills · skills/authoring/eval-skills/SKILL.md · Eval and improve a skill against golden cases — run the target skill blind in a fresh, context-free subagent on each…
git:20260705.adffd39 · audit A · 1,377 stars
write-skills SKILL.md skill
dzhng/skills · skills/authoring/write-skills/SKILL.md · Create or revise agent skills. Use when adding a new skill file, renaming a skill, simplifying an existing skill…
git:20261004.3e02e02 · audit A · 1,377 stars
audit-choices SKILL.md skill
dzhng/skills · skills/engineering/audit-choices/SKILL.md · Audit the choices an implementing agent made, not its diff — a pure decision audit that traces the session's history…
git:20260813.dbb1aa5 · audit A · 1,377 stars
audit-performance SKILL.md skill
dzhng/skills · skills/engineering/audit-performance/SKILL.md · Audit and prioritize performance work through bounded-work and forward-progress checks. Use when asked to find…
git:20261002.8aea537 · audit A · 1,377 stars
audit-tests SKILL.md skill
dzhng/skills · skills/engineering/audit-tests/SKILL.md · Audit whether tests earn their maintenance cost and which suite owns each contract. Use when pruning redundant tests…
git:20260929.2fa832d · audit A · 1,377 stars
auto-research SKILL.md skill
dzhng/skills · skills/engineering/auto-research/SKILL.md · Run fast, progressive experiments to map tunable parameters and their effects. Use when optimizing code, prompts…
git:20260925.120cae1 · audit A · 1,377 stars
close-spec SKILL.md skill
dzhng/skills · skills/engineering/close-spec/SKILL.md · When a spec under specs/<feature>/ is done shipping (a write-spec build, or any planned task that produced a spec)…
git:20260721.2ee48ec · audit A · 1,377 stars
code-review SKILL.md skill
dzhng/skills · skills/engineering/code-review/SKILL.md · Review changed code for naming, stale references, unnecessary complexity, and comment quality. Use after completing…
git:20261021.8e74252 · audit A · 1,377 stars
codex SKILL.md skill
dzhng/skills · skills/engineering/codex/SKILL.md · Use the local Codex CLI as an independent second agent. Two branches — (1) proactively run `codex review` for a second…
git:20261015.f6819ca · audit A · 1,377 stars
eli5 SKILL.md skill
dzhng/skills · skills/engineering/eli5/SKILL.md · Explain a technical spec or proposed change in plain language: what problem it solves, how the solution works, and…
git:20260813.dbb1aa5 · audit A · 1,377 stars
explore-unknowns SKILL.md skill
dzhng/skills · skills/engineering/explore-unknowns/SKILL.md · Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work…
git:20260930.60ae302 · audit A · 1,377 stars

Every file in dzhng/skills

Other files named claude

claude SKILL.md skill
dzhng/duet-agent · .agents/skills/claude/SKILL.md · Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent…
git:20261015.0e6cd08 · audit A · 50 stars
claude SKILL.md skill
smturtle2/codex-skills · skills/claude/SKILL.md · Exchange messages with an already-running local Claude Code session and inspect its history on demand. Use for…
git:20261015.b79cc4b · audit A · 14 stars
claude SKILL.md skill
ridelink0/ultimate-frontend-skills · packs/bergside-awesome-design-skills/claude/SKILL.md · A research-journal aesthetic printed on warm stone — authoritative, editorial, almost achromatic. Pages live on warm…
git:20260921.6026393 · audit A · 7 stars
claude SKILL.md skill
timurgaleev/vibestack · skills/claude/SKILL.md · Independent second opinion from the Claude Code CLI: review a diff, challenge it adversarially, or consult.
git:20261009.553d413 · audit A · 7 stars
claude SKILL.md skill
transitive-bullshit/skills · skills/claude/SKILL.md · Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent…
git:20261018.0333997 · audit A · 4 stars
claude SKILL.md skill
transitive-bullshit/skills · provenance/upstream/claude/skill/SKILL.md · Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a second-agent…
git:20261018.0333997 · audit A · 4 stars
claude SKILL.md skill
darshitpp/x-agent · claude/SKILL.md · Delegate tasks or get a second opinion from Claude Code CLI.
git:20261006.36549ce · audit A · 2 stars

Browse by kind, by grade A, or by owner.