Exécutez n'importe quel Skill dans Manus
en un clic

Exécutez n'importe quel Skill dans Manus en un clic

install-agents

Étoiles4

Forks1

Mis à jour17 juillet 2026 à 11:45

Discover, validate, stitch, and install specialist agent templates contributed by Essential and other enabled plugins in the same marketplace. Use when asked to install agents, set up subagents, refresh the agent team, or configure Claude Code on a new machine.

Installation

Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.

Exécuter dans Manus

Source

alvis

alvis/.claude

Ouvrir le dépôt GitHub Voir les dépôts du créateur

Téléchargement

Exécuter dans Manus

Métiers associésSOC

Basé sur la classification professionnelle SOC

Autres occupations informatiquesProfessions informatiques et mathématiques·SOC 15-1299

Explorateur de fichiers

5 fichiers

SKILL.md

readonly

name	install-agents
description	Discover, validate, stitch, and install specialist agent templates contributed by Essential and other enabled plugins in the same marketplace. Use when asked to install agents, set up subagents, refresh the agent team, or configure Claude Code on a new machine.
allowed-tools	Bash, Read

Install Agents

Installs agent templates contributed by Essential and the other enabled plugins in this marketplace. Once stitched under ~/.claude/agents/, Claude Code auto-discovers them without settings.json wiring.

What the installer does

scripts/install-agents.sh is idempotent and safe to re-run:

In a source checkout, discovers plugins/*/templates/agents/*; from an installed Essential plugin, reads claude plugin list --json and discovers templates only from enabled plugins in Essential's marketplace.
Validates every base.md + frontmatter/claude.json pair, including its role-only definition name, three distinct preferred short teammate names, runtime tool inheritance, model/effort, centralized-policy boundary, and required project-memory path and maintenance contract, and rejects malformed or duplicate names before touching the destination.
Stitches all definitions into a temporary staging directory.
Copies staged files into ~/.claude/agents/, overwriting discovered same-named agents while leaving unrelated and formerly managed files untouched.
Prints each installed path and a final count.

Workflow

Step 1: Run the installer

bash "${CLAUDE_PLUGIN_ROOT}/skills/install-agents/scripts/install-agents.sh"

Step 2: Verify

Smoke-check one representative definition after confirming the installer's reported count:

head -3 ~/.claude/agents/tech-lead.md

In a fresh Claude Code session, the roster appears in the agent list.

For maintainer verification, run the deterministic contract suite:

PYTHONDONTWRITEBYTECODE=1 python3 -m unittest plugins/essential/skills/install-agents/scripts/test_install_agents.py

Step 3: Report

Tell the user:

How many agents were installed and the destination (~/.claude/agents/)
That they take effect in the next session (the current session's agent list is fixed at startup)
That re-running overwrites currently discovered agents and does not prune any other files

Plus depuis ce dépôt

même dépôt

create-agent

alvis/.claude

Creates a new specialist agent as two stitched source files, base.md plus frontmatter/claude.json, proposing model, effort, and permissions by role archetype and confirming them with the user before writing. Use when adding a new subagent, defining a new specialist role, scaffolding an agent definition, or when update-agent hands off new-agent creation.

2026-07-184

skill-name

alvis/.claude

[Description] — third person, what the skill does plus a 'Use when...' clause with concrete trigger phrases a user would actually type; 25-60 words; lead with the key use case.

2026-07-174

update-agent

alvis/.claude

Update explicitly selected agent definitions to the current two-file template or a stated behavior change while preserving useful role expertise, trigger boundaries, context, collaboration links, and working voice. Use when migrating agents to a template revision, correcting agent configuration, or batch-updating selected agents; require an exact selector and route genuinely new roles to create-agent.

2026-07-164

lint

alvis/.claude

Enforce coding standards mechanically across a selected scope with batched linters and independent reviewers. Use when source files need lint-error correction, standards enforcement, or consistent formatting, including calls extended by another plugin's portable lint profile; behavior-changing repairs belong to fix.

2026-07-164

review-code

alvis/.claude

Review semantic correctness, security, test intent, documentation, sibling consistency, and alignment with the implementation plan. Use after code changes or for explicit review requests; report findings without editing code and leave mechanical standards enforcement to lint.

2026-07-164

sync-spec

alvis/.claude

Materialize a guaranteed-on-disk Notion specification tree as a flat `.code-spec/` bundle of `{kebab-title}-{32hex-id}.md` files plus `.gitignore`. Use before downstream analysis or code generation, when refreshing a stale bundle, or when a ticket requires local spec evidence; fail unless the root id-suffix file exists and is non-empty.

2026-07-164

name	install-agents
description	Discover, validate, stitch, and install specialist agent templates contributed by Essential and other enabled plugins in the same marketplace. Use when asked to install agents, set up subagents, refresh the agent team, or configure Claude Code on a new machine.
allowed-tools	Bash, Read

Install Agents

What the installer does

scripts/install-agents.sh is idempotent and safe to re-run:

In a source checkout, discovers plugins/*/templates/agents/*; from an installed Essential plugin, reads claude plugin list --json and discovers templates only from enabled plugins in Essential's marketplace.
Validates every base.md + frontmatter/claude.json pair, including its role-only definition name, three distinct preferred short teammate names, runtime tool inheritance, model/effort, centralized-policy boundary, and required project-memory path and maintenance contract, and rejects malformed or duplicate names before touching the destination.
Stitches all definitions into a temporary staging directory.
Copies staged files into ~/.claude/agents/, overwriting discovered same-named agents while leaving unrelated and formerly managed files untouched.
Prints each installed path and a final count.

Workflow

Step 1: Run the installer

bash "${CLAUDE_PLUGIN_ROOT}/skills/install-agents/scripts/install-agents.sh"

Step 2: Verify

Smoke-check one representative definition after confirming the installer's reported count:

head -3 ~/.claude/agents/tech-lead.md

In a fresh Claude Code session, the roster appears in the agent list.

For maintainer verification, run the deterministic contract suite:

PYTHONDONTWRITEBYTECODE=1 python3 -m unittest plugins/essential/skills/install-agents/scripts/test_install_agents.py

Step 3: Report

Tell the user:

How many agents were installed and the destination (~/.claude/agents/)
That they take effect in the next session (the current session's agent list is fixed at startup)
That re-running overwrites currently discovered agents and does not prune any other files