run-agent

Run a custom agent by name

Repositório: AMindToThink/claude-code-settings
Última atividade na origem: 7 de março de 2026 às 01:59
Idioma detectado do SKILL.md: inglês
Estrelas: 4
Forks: 0

Opções de instalação

Por padrão, está selecionado o prompt que primeiro revisa a origem. Você pode mudar para um comando direto ou baixar uma cópia local.

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.

npx skills add https://github.com/AMindToThink/claude-code-settings --skill run-agent

O comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.

Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.

Revise os arquivos de origem

Leia o SKILL.md e os arquivos complementares exibidos pelo SkillsMP antes de decidir se vai instalar.

SKILL.md

Instruções da origem · Visualização somente leitura

name: run-agent
description: Run a custom agent by name
argument-hint: <agent-name> [task description]
disable-model-invocation: true

Delegate the following task to the **$ARGUMENTS[0]** agent. If additional arguments were provided, use them as the task description. If no task description was provided, ask the user what they'd like the agent to do.

Ver no GitHub

Voltar à pesquisa Voltar à instalação

cited-corpus-audit

Use when fanning out subagents over a corpus (pages, traces, logs, documents) to produce findings that must cite evidence — links, quotes, ids, line numbers. Packages the integrity discipline that keeps agent citations real - freeze the corpus locally, schema-forced per-item results with explicit nulls, verbatim-citation validation against the frozen source, gap-fill for dropped items, journal-based recovery. Triggers - "have agents review each X and report/cite", building datasets from agent analyses, Docent-style trace audits, any workflow where fabricated citations or silently dropped items would corrupt the output.

2026-09-01

handle-machine-shared-memory

Use when a shared multi-user Linux box keeps freezing or going unresponsive from out-of-memory (OOM) events, when one user's process is eating all the RAM, or when someone needs to cap memory so the machine stays usable without starving legitimate work. Covers cgroup-v2 / systemd memory guard rails (MemoryMax / MemoryMin), giving Docker its own capped slice, a preflight that refuses over-budget eval runs, and the reasoning that makes the caps safe. Triggers on "the server keeps freezing", "OOM killed my process / dbus / the session", "someone is hogging all the memory", "put a memory limit on docker/users so the machine never dies", "cgroup memory caps", "MemoryMax", "the box becomes unusable under load". Assumes you have root but NOT hardware control (can't add RAM).

2026-09-01

stackexchange-data

Use when fetching or analyzing StackOverflow / Stack Exchange content (questions, answers, comments, vote scores) for a dataset, audit, or research pipeline. Direct page access is blocked from Matthew's machines (WebFetch refuses the domain; curl gets Cloudflare 403) — this skill gives the working Stack Exchange API path and its empirically-discovered quirks. Triggers - "scrape/fetch/download StackOverflow", "SO answers/comments", "api.stackexchange.com", building datasets from SE sites.

2026-09-01

Ver todas deste repositório

run-agent

Informações da origem

Opções de instalação

Revise os arquivos de origem

Mais deste repositório

Mais deste repositório