- name
SKILL.md
El archivo de la skill permanece en el repositorio del publicador.
Pega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add dzhng/skills --skill claude -a cursor -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add dzhng/skills --skill claude -a claude-code -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add dzhng/skills --skill claude -a codex -yPega el comando copiado en una terminal. Instala este SKILL.md en ese agente.
npx skills add dzhng/skills --skill claude -a grok -yEnvía el mensaje copiado en un chat de Grok Bot. El Bot obtiene este SKILL.md de GitHub y lo añade a las skills que comparten todos tus Bots.
Install this skill: https://github.com/dzhng/skills/tree/HEAD/skills/implement/claudeDel publicador
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.
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.
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.--effort flag. Valid levels are
low, medium, high, xhigh, and max. Default high.--max-budget-usd <amount> when
the user gives a budget or the task is likely to sprawl.Example:
claude -p --model opus --effort high "<prompt>"
Prompt Claude like an operator: compact, block-structured, and explicit about the artifact you need. A sharper contract beats higher effort.
<task> — the concrete job, context, and expected end state.<output_contract> — exact response shape, highest-value first.<default_follow_through> — take low-risk interpretations and continue;
stop only when a missing detail changes correctness, safety, or an
irreversible action.<verification_loop> — inspect the result against requirements and revise
before finalizing.<grounding> — ground every claim in code or tool output; label
inferences.<action_safety> — keep the diff tightly scoped; no drive-by refactors.Use Claude for consultation when the user asks for Claude's view or when a second-agent read would materially reduce risk. Keep it read-oriented unless the user explicitly asks it to edit.
--tools "Read,Grep,Glob,Bash" --permission-mode dontAsk.Delegate implementation to Claude only when the user names Claude for the task. Never hand it work on your own initiative, and never re-delegate follow-up work without a fresh ask.
--tools "Read,Grep,Glob,Bash" --permission-mode dontAsk.--dangerously-skip-permissions only in a
dedicated worktree, with a self-authored prompt and a mandatory diff
review after.--output-format text by default. Use
--output-format json only when the caller needs structured metadata.claude -p is a networked, authenticated non-interactive run. If it fails,
classify the failure before retrying.
claude -p says Not logged in, retry once with the
required approval because local auth can depend on keychain/session access.--max-budget-usd or a narrower prompt before raising
effort.-p skips the interactive trust dialog, so run it only from
a repo or worktree you intentionally trust.claude -p --model opus --effort high as the default invocation; keep
the alias unversioned so it follows the current Opus release.--model and --effort.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 se
---name: claudedescription: Use Claude Code as an independent `claude -p` subagent when the user explicitly asks for Claude, wants a…---# skills/implement/claude/SKILL.mdResumen general
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`.
Preguntas frecuentes
Descarga skills/implement/claude/SKILL.md desde el publicador, o copia la ruta y abre el repositorio. PlugMCP lista la skill y no aloja el archivo.
El publicador lo mantiene en https://github.com/dzhng/skills.
Claude, Cursor, Codex y Grok Build pueden leer un SKILL.md que añadas desde el repositorio del publicador. Grok Bot lo instala cuando envías en un chat el enlace a la carpeta de la skill en GitHub.