📦

learn

Name: learn
Author: agentskill-sh

v2.0 Revisión del contenido r1 Crítico 🌐 Acceso a red📁 Acceso al sistema de archivos⚡ Contiene scripts⚙️ Comandos externos🔑 Variables de entorno

Instalar habilidades de agente a mitad de conversación

Los agentes a menudo necesitan instrucciones especializadas que no se cargan al inicio de una sesión. Esta habilidad permite a Claude, Codex y Claude Code buscar, previsualizar, escanear, instalar, actualizar, eliminar y calificar habilidades de agentskill.sh.

Compatible con: Claude Codex Code(CC)

⚠️ 38 Deficiente

No instales este Skill automáticamente.

La política canónica exige la revisión de un operador antes de cualquier acción de instalación.

Instalar con mi Agente

Copia esta solicitud en tu Agente. Incluye la página canónica del Skill y el manifiesto.

Solicitud de agente

Review the Skillstore skill "learn" from https://skillstore.io/skills/agentskill-sh-learn.md and its manifest at https://skillstore.io/api/skills/agentskill-sh-learn/manifest. Verify the artifact. Do not auto-install. Inspect the skill and report your findings, then wait for an operator or manual installation decision.

Tu Agente debe seguir mostrando su plan y solicitar cualquier confirmación exigida por la política de seguridad.

Recursos legibles por agentes

Usa estos enlaces cuando un agente de IA, crawler o script necesite contexto limpio en vez de leer la página completa.

Detalle Markdown GET /skills/agentskill-sh-learn.md Manifest firmado GET /api/skills/agentskill-sh-learn/manifest Lockfile firmado GET /api/skills/agentskill-sh-learn/lockfile

Pruébalo

Usando "learn". /learn documentation

Resultado esperado:

Una tabla clasificada de habilidades coincidentes con autores, cantidades de instalaciones, puntuaciones de seguridad, descripciones breves y una opción interactiva de instalación.

Usando "learn". /learn scan ./SKILL.md

Resultado esperado:

Un informe de seguridad que lista la puntuación, los problemas detectados, los endpoints de red, el acceso a archivos, los comandos de shell y una recomendación de permitir o bloquear.

Usando "learn". /learn update

Resultado esperado:

Un resumen de habilidades instaladas, estado de actualización, resultados del nuevo escaneo de seguridad y una solicitud de confirmación antes de aplicar actualizaciones.

Auditoría de seguridad

Crítico

v7 • 9/7/2026 Abrir el informe versionado

Most static hits are false positives from documentation and defensive scanner examples, especially references/SECURITY.md and Markdown inline-code in SKILL.md. The real risks are the intended remote marketplace behavior: fetching and installing remote skill content into agent directories, self-updating the installer, and sending feedback or scan reports to agentskill.sh.

Archivos escaneados

1,630

Líneas analizadas

115

Elementos de revisión

Falsos positivos ignorados

Preocupaciones de seguridad confirmadas (8)

Crítico

multiple:1

[HEURISTIC] DANGEROUS COMBINATION: Code execution + Network + Credential access

This combination is common in credential stealers and RATs

The aggregate combination is real because the skill combines external marketplace fetching with writes to agent skill directories and optional telemetry. The intent is legitimate, but the combined behavior creates supply-chain risk.

Crítico

multiple:1

[HEURISTIC] DANGEROUS COMBINATION: Network + Credentials + Evasion techniques

This combination suggests data exfiltration with anti-detection

Alto

multiple:1

[HEURISTIC] SUSPICIOUS COMBINATION: Code execution + Persistence mechanism

This combination is common in malware that maintains access

Alto

multiple:1

[HEURISTIC] SUSPICIOUS COMBINATION: Filesystem + Credentials + Network

This combination could indicate credential harvesting and exfiltration

Alto

SKILL.md:256-331

Remote Skill Installation Can Change Agent Behavior

The install flow fetches skill content from agentskill.sh, scans it, and writes it into the detected agent skill directory. A compromised marketplace response or weak scan result could install instructions that influence future agent behavior.

The cited install flow explicitly fetches remote skill content, scans it, writes a skill file, and tracks the install. This is intended behavior, but it is a clear supply-chain control point.

Alto

SKILL.md:560-568

Self-Update Threshold Is Weaker Than Install Block Threshold

The self-update flow says to overwrite the current learn skill if the new version scan passes with score at least 50, while the install flow blocks skills below 70. This could permit a lower-scoring update to replace the installer itself.

The lines directly describe fetching the latest version and overwriting the current skill when scan score is at least 50. The same file documents a stricter install block threshold elsewhere.

Medio

SKILL.md:772

System reconnaissance

| Invalid score | "Score must be an integer between 1 and 5."

This section describes runtime installation, update, or feedback behavior that fetches remote content, writes skill files, or sends rating data. The behavior is purposeful, but it has supply-chain and privacy impact.

Medio

SKILL.md:634-760

Opt-Out Rating and Feedback Telemetry

The skill instructs agents to rate installed skills by default, send ratings after a short confirmation window, and avoid ending a session with unrated skills. This sends platform and agent-generated comments to an external service unless disabled.

The cited section describes automatic rating, a 5-second default-send path, platform data, comments, and session-end rating behavior. It is disclosed, but it is still privacy-relevant external telemetry.

Elementos de revisión de capacidades (115)

Estas son capacidades locales reales que pueden esperarse para esta habilidad, por lo que requieren revisión, pero no se cuentan como comportamiento malicioso confirmado.

Alto

SKILL.md:582

Hidden file in home directory

1. Check if `.openclaw/` directory exists OR `~/.openclaw/workspace/` exists → **OpenClaw**

The skill detects or writes agent skill directories, which can alter future agent behavior. This is intended functionality, but writing remote skill content into hidden agent configuration paths is a real security-relevant filesystem action.

Alto

SKILL.md:583

Hidden file in home directory

- Install path: `~/.openclaw/workspace/skills/<slug>.md`

Medio

SKILL.md:40-44

Ruby/shell backtick execution

1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?q=<URL-encoded query>&limit=5`

SKILL.md instructs the agent to contact agentskill.sh APIs for search, install, update, tracking, reports, or feedback. The domain matches the stated marketplace purpose, but it is real external network behavior.

Medio

SKILL.md:77-81

Ruby/shell backtick execution

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install?owner=<owner>`

Medio

SKILL.md:87-88

Ruby/shell backtick execution

1. Parse the slug from the URL path (last segment of `https://agentskill.sh/<slug>`)

Medio

SKILL.md:88-91

Ruby/shell backtick execution

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install`

Medio

SKILL.md:121-125

Ruby/shell backtick execution

1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?section=trending&limit=5`

Medio

SKILL.md:133-134

Ruby/shell backtick execution

3. Use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/agent-feedback` with JSON body:

Medio

SKILL.md:179-180

Ruby/shell backtick execution

2. Collect all slugs and call the batch version endpoint: `https://agentskill.sh/api/agent/skills/ve

Medio

SKILL.md:256-270

Ruby/shell backtick execution

1. Fetch skill content from `https://agentskill.sh/api/agent/skills/<slug>/install?platform=<platfor

Medio

SKILL.md:270-280

Ruby/shell backtick execution

```

Medio

SKILL.md:280-284

Ruby/shell backtick execution

```

Medio

SKILL.md:284-296

Ruby/shell backtick execution

```

Medio

SKILL.md:296-318

Ruby/shell backtick execution

```

Medio

SKILL.md:318-329

Ruby/shell backtick execution

```

Medio

SKILL.md:329-331

Ruby/shell backtick execution

```

Medio

SKILL.md:331-333

Ruby/shell backtick execution

9. Track the install — use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/install` wit

Medio

SKILL.md:333-338

Ruby/shell backtick execution

```json

Medio

SKILL.md:338-344

Ruby/shell backtick execution

```

Medio

SKILL.md:344-347

Ruby/shell backtick execution

```

Medio

SKILL.md:347-354

Ruby/shell backtick execution

**Location:** `<install path>`

Medio

SKILL.md:354-355

Ruby/shell backtick execution

Rate this skill later: `/learn feedback <slug> <1-5> [optional comment]`

Medio

SKILL.md:355-371

Ruby/shell backtick execution

```

Medio

SKILL.md:556-560

Ruby/shell backtick execution

Before executing any subcommand, check if this `/learn` skill itself is up to date.

Medio

SKILL.md:560

Ruby/shell backtick execution

1. Read the current `/learn` skill file and extract the `contentSha` from the metadata header

Medio

SKILL.md:561-562

Ruby/shell backtick execution

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/learn/version`

Medio

SKILL.md:562

Ruby/shell backtick execution

3. Compare the local `contentSha` with the remote `contentSha`

Medio

SKILL.md:565-582

Ruby/shell backtick execution

a. Fetch the latest version from `https://agentskill.sh/api/agent/skills/learn/install`

Medio

SKILL.md:582

Ruby/shell backtick execution

1. Check if `.openclaw/` directory exists OR `~/.openclaw/workspace/` exists → **OpenClaw**

Medio

SKILL.md:583-584

Ruby/shell backtick execution

- Install path: `~/.openclaw/workspace/skills/<slug>.md`

Medio

SKILL.md:584-585

Ruby/shell backtick execution

2. Check if `.claude/` directory exists in the project root → **Claude Code / Claude Desktop**

Medio

SKILL.md:585-586

Ruby/shell backtick execution

- Install path: `.claude/skills/<slug>.md`

Medio

SKILL.md:586-587

Ruby/shell backtick execution

3. Check if `.cursor/` directory exists → **Cursor**

Medio

SKILL.md:587-588

Ruby/shell backtick execution

- Install path: `.cursor/skills/<slug>.md`

Medio

SKILL.md:588-589

Ruby/shell backtick execution

4. Check if `.github/copilot/` directory exists → **GitHub Copilot**

Medio

SKILL.md:589-590

Ruby/shell backtick execution

- Install path: `.github/copilot/skills/<slug>.md`

Medio

SKILL.md:590-591

Ruby/shell backtick execution

5. Check if `.windsurf/` directory exists → **Windsurf**

Medio

SKILL.md:591-592

Ruby/shell backtick execution

- Install path: `.windsurf/skills/<slug>.md`

Medio

SKILL.md:592-593

Ruby/shell backtick execution

6. Check if `.cline/` directory exists → **Cline**

Medio

SKILL.md:593-594

Ruby/shell backtick execution

- Install path: `.cline/skills/<slug>.md`

Medio

SKILL.md:594-595

Ruby/shell backtick execution

7. Check if `.codex/` directory exists → **Codex**

Medio

SKILL.md:595-596

Ruby/shell backtick execution

- Install path: `.codex/skills/<slug>.md`

Medio

SKILL.md:596-597

Ruby/shell backtick execution

8. Check if `.opencode/` directory exists → **OpenCode**

Medio

SKILL.md:597-598

Ruby/shell backtick execution

- Install path: `.opencode/skills/<slug>.md`

Medio

SKILL.md:598-599

Ruby/shell backtick execution

9. Check if `.aider/` directory exists → **Aider**

Medio

SKILL.md:599-600

Ruby/shell backtick execution

- Install path: `.aider/skills/<slug>.md`

Medio

SKILL.md:600-601

Ruby/shell backtick execution

10. Check if `.gemini/` directory exists → **Gemini CLI**

Medio

SKILL.md:601-602

Ruby/shell backtick execution

- Install path: `.gemini/skills/<slug>.md`

Medio

SKILL.md:602-603

Ruby/shell backtick execution

11. Check if `.amp/` directory exists → **Amp**

Medio

SKILL.md:603-604

Ruby/shell backtick execution

- Install path: `.amp/skills/<slug>.md`

Medio

SKILL.md:604-605

Ruby/shell backtick execution

12. Check if `.goose/` directory exists → **Goose**

Medio

SKILL.md:605-606

Ruby/shell backtick execution

- Install path: `.goose/skills/<slug>.md`

Medio

SKILL.md:606-607

Ruby/shell backtick execution

13. Check if `.roo-code/` directory exists → **Roo Code**

Medio

SKILL.md:607-608

Ruby/shell backtick execution

- Install path: `.roo-code/skills/<slug>.md`

Medio

SKILL.md:608-609

Ruby/shell backtick execution

14. Check if `.trae/` directory exists → **Trae**

Medio

SKILL.md:609-615

Ruby/shell backtick execution

- Install path: `.trae/skills/<slug>.md`

Medio

SKILL.md:615

Ruby/shell backtick execution

| `.openclaw/` | `openclaw` |

Medio

SKILL.md:616

Ruby/shell backtick execution

| `.claude/` | `claude-code` |

Medio

SKILL.md:617

Ruby/shell backtick execution

| `.cursor/` | `cursor` |

Medio

SKILL.md:618

Ruby/shell backtick execution

| `.github/copilot/` | `copilot` |

Medio

SKILL.md:619

Ruby/shell backtick execution

| `.windsurf/` | `windsurf` |

Medio

SKILL.md:620

Ruby/shell backtick execution

| `.cline/` | `cline` |

Medio

SKILL.md:621

Ruby/shell backtick execution

| `.codex/` | `codex` |

Medio

SKILL.md:622

Ruby/shell backtick execution

| `.opencode/` | `opencode` |

Medio

SKILL.md:623

Ruby/shell backtick execution

| `.aider/` | `aider` |

Medio

SKILL.md:624

Ruby/shell backtick execution

| `.gemini/` | `gemini-cli` |

Medio

SKILL.md:625

Ruby/shell backtick execution

| `.amp/` | `amp` |

Medio

SKILL.md:626

Ruby/shell backtick execution

| `.goose/` | `goose` |

Medio

SKILL.md:627

Ruby/shell backtick execution

| `.roo-code/` | `roo-code` |

Medio

SKILL.md:628

Ruby/shell backtick execution

| `.trae/` | `trae` |

Medio

SKILL.md:630-660

Ruby/shell backtick execution

When creating the skill directory, create it if it doesn't exist (e.g., `mkdir -p .claude/skills/`).

Medio

SKILL.md:660-663

Ruby/shell backtick execution

```

Medio

SKILL.md:663-664

Ruby/shell backtick execution

Send rating? (Y/n) — disable auto-rating: `/learn config autorating off`

Medio

SKILL.md:664-666

Ruby/shell backtick execution

```

Medio

SKILL.md:666-674

Ruby/shell backtick execution

```json

Medio

SKILL.md:674-675

Ruby/shell backtick execution

```

Medio

SKILL.md:675-686

Ruby/shell backtick execution

4. **User can override anytime**: `/learn feedback <slug> <score> [comment]`

Medio

SKILL.md:686-688

Ruby/shell backtick execution

```

Medio

SKILL.md:688-690

Ruby/shell backtick execution

```

Medio

SKILL.md:690-706

Ruby/shell backtick execution

Re-enable with: `/learn config autorating on`

Medio

SKILL.md:706-751

Ruby/shell backtick execution

- `/learn feedback <slug> <new-score> [comment]`

Medio

SKILL.md:751-757

Ruby/shell backtick execution

```

Medio

SKILL.md:757-758

Ruby/shell backtick execution

*Override any rating: `/learn feedback <slug> <score> [comment]`*

Medio

SKILL.md:758-781

Ruby/shell backtick execution

```

Medio

SKILL.md:781-785

Ruby/shell backtick execution

All endpoints are on `https://agentskill.sh`.

Medio

SKILL.md:785-786

Ruby/shell backtick execution

| `/api/agent/search?q=<query>&limit=5` | GET | Search skills

Medio

SKILL.md:786-787

Ruby/shell backtick execution

| `/api/agent/skills/<slug>/install` | GET | Get skill content for installation

Medio

SKILL.md:787-788

Ruby/shell backtick execution

| `/api/agent/skills/<slug>/version` | GET | Get content SHA for version check

Medio

SKILL.md:788-789

Ruby/shell backtick execution

| `/api/agent/skills/version?slugs=<csv>` | GET | Batch version check

Medio

SKILL.md:789-790

Ruby/shell backtick execution

| `/api/skills/<slug>/install` | POST | Track install event

Medio

SKILL.md:790

Ruby/shell backtick execution

| `/api/skills/<slug>/agent-feedback` | POST | Submit score and comment (include `autoRated: t

Medio

SKILL.md:582

Hidden file access

1. Check if `.openclaw/` directory exists OR `~/.openclaw/workspace/` exists → **OpenClaw**

Medio

SKILL.md:583

Hidden file access

- Install path: `~/.openclaw/workspace/skills/<slug>.md`

Bajo

SKILL.md:451

Python HTTP libraries

- Manual: check for `os.system`, `subprocess(shell=True)`, `exec`, `eval`, `pickle.loads`, `requests

Bajo

SKILL.md:771

Python HTTP libraries

| Rate limited (429) | "Too many requests. Please wait a moment and try again."

Bajo

SKILL.md:11

Hardcoded URL

Discover, install, and manage AI agent skills from [agentskill.sh](https://agentskill.sh). This skil

Bajo

SKILL.md:40

Hardcoded URL

1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?q=<URL-encoded query>&limit=5`

Bajo

SKILL.md:68

Hardcoded URL

If no results are found, say: "No skills found for '<query>'. Try different keywords or browse at ht

Bajo

SKILL.md:77

Hardcoded URL

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install?owner=<owner>`

Bajo

SKILL.md:79

Hardcoded URL

4. If not found, say: "Skill @<owner>/<slug> not found. Check the name at https://agentskill.sh"

Bajo

SKILL.md:87

Hardcoded URL

1. Parse the slug from the URL path (last segment of `https://agentskill.sh/<slug>`)

Bajo

SKILL.md:88

Hardcoded URL

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/<slug>/install`

Bajo

SKILL.md:121

Hardcoded URL

1. Use WebFetch to call: `https://agentskill.sh/api/agent/search?section=trending&limit=5`

Bajo

SKILL.md:133

Hardcoded URL

3. Use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/agent-feedback` with JSON body:

Bajo

SKILL.md:179

Hardcoded URL

2. Collect all slugs and call the batch version endpoint: `https://agentskill.sh/api/agent/skills/ve

Bajo

SKILL.md:256

Hardcoded URL

1. Fetch skill content from `https://agentskill.sh/api/agent/skills/<slug>/install?platform=<platfor

Bajo

SKILL.md:325

Hardcoded URL

# source: https://agentskill.sh/<slug>

Bajo

SKILL.md:331

Hardcoded URL

9. Track the install — use WebFetch to POST to `https://agentskill.sh/api/skills/<slug>/install` wit

Bajo

SKILL.md:501

Hardcoded URL

POST https://agentskill.sh/api/agent/security-reports

Bajo

SKILL.md:561

Hardcoded URL

2. Use WebFetch to call: `https://agentskill.sh/api/agent/skills/learn/version`

Bajo

SKILL.md:565

Hardcoded URL

a. Fetch the latest version from `https://agentskill.sh/api/agent/skills/learn/install`

Bajo

SKILL.md:768

Hardcoded URL

| API unreachable / timeout | "Could not reach agentskill.sh. Check your connection or try again lat

Bajo

SKILL.md:769

Hardcoded URL

| No search results | "No skills found for '<query>'. Try different keywords or browse at ht

Bajo

SKILL.md:770

Hardcoded URL

| Skill not found (404) | "Skill '<slug>' not found. It may have been removed. Browse available

Bajo

SKILL.md:781

Hardcoded URL

All endpoints are on `https://agentskill.sh`.

Factores de riesgo

🌐 Acceso a red (30)

📁 Acceso al sistema de archivos (45)

⚡ Contiene scripts (3)

references/SECURITY.md:414 references/SECURITY.md:421 references/SECURITY.md:420

⚙️ Comandos externos (50)

references/SECURITY.md:412 references/SECURITY.md:413 references/SECURITY.md:411 references/SECURITY.md:630-635 references/SECURITY.md:149 SKILL.md:13 SKILL.md:22 SKILL.md:23 SKILL.md:24 SKILL.md:25 SKILL.md:32-34 SKILL.md:34-36 SKILL.md:36-40 SKILL.md:40-44 SKILL.md:44-57 SKILL.md:57-59 SKILL.md:59-70 SKILL.md:70-72 SKILL.md:72-76 SKILL.md:76-77 SKILL.md:77-81 SKILL.md:81-83 SKILL.md:83-87 SKILL.md:87-88 SKILL.md:88-91 SKILL.md:91-93 SKILL.md:93-98 SKILL.md:98-99 SKILL.md:99 SKILL.md:100 SKILL.md:101-103 SKILL.md:103 SKILL.md:104-105 SKILL.md:105-109 SKILL.md:109-113 SKILL.md:113-117 SKILL.md:117-121 SKILL.md:121-125 SKILL.md:125-131 SKILL.md:131 SKILL.md:133-134 SKILL.md:134-141 SKILL.md:141-144 SKILL.md:144-151 SKILL.md:151-153 SKILL.md:153-158 SKILL.md:158-159 SKILL.md:159 SKILL.md:162-171 SKILL.md:171-172

🔑 Variables de entorno (1)

references/SECURITY.md:111

Patrones detectados

System reconnaissance[HEURISTIC] DANGEROUS COMBINATION: Code execution + Network + Credential access[HEURISTIC] DANGEROUS COMBINATION: Network + Credentials + Evasion techniques

Auditado por: claude Ver historial de auditorías →

Compartir y citar este informe

Comparte el informe de evaluación versionado, la insignia neutral, la tarjeta insertable y las citas. Skillstore presenta evidencias sin decidir si este Skill es seguro.

Abrir el informe versionado

Copiar enlace del informe

https://skillstore.io/skills/agentskill-sh-learn/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Insignia Markdown

[![Skillstore security assessment](https://skillstore.io/badges/skills/agentskill-sh-learn/security.svg)](https://skillstore.io/skills/agentskill-sh-learn?utm_source=security_passport_badge)

Insignia HTML

<a href="https://skillstore.io/skills/agentskill-sh-learn?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/agentskill-sh-learn/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Tarjeta para insertar

<iframe src="https://skillstore.io/embed/skills/agentskill-sh-learn.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>

Citas académicas (APA · BibTeX · CFF)

Cita APA

agentskill-sh. (2026). learn security audit report (audit version 7) [Author version 2.0]. Skillstore. https://skillstore.io/skills/agentskill-sh-learn/audits/7

Cita BibTeX

@techreport{agentskill-sh-agentskill-sh-learn-2026,
  author = {agentskill-sh},
  title = {learn security audit report (audit version 7)},
  institution = {Skillstore},
  year = {2026},
  number = {7},
  url = {https://skillstore.io/skills/agentskill-sh-learn/audits/7},
  note = {Author version 2.0}
}

CITATION.cff

cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "learn security audit report (audit version 7)"
version: "2.0"
type: report
authors:
  - name: "agentskill-sh"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/agentskill-sh-learn/audits/7"
identifiers:
  - type: other
    value: "skillstore:agentskill-sh-learn:audit:7"
    description: "Skillstore immutable audit report identifier"

Comparar variantes

2 variantes instalables

Cada autor sigue siendo un skill instalable independiente. La variante recomendada se ordena según la evidencia de Skillstore.

Por qué esta variante es la primera

Mayor puntuación de Skillstore

Autor / fuente Puntuación de Skillstore Confianza de la evidencia Uso en Skillstore Actualizado

0xrdan Recomendado

0xrdan-learn

Puntuación de Skillstore 70

Confianza de la evidencia Alto

Uso en Skillstore 27

Actualizado

2026-09-09

agentskill-sh Actual

agentskill-sh-learn

Puntuación de Skillstore 38

Confianza de la evidencia Medio

Uso en Skillstore 76

Actualizado

2026-09-09

Puntuación de Skillstore

Por qué esta puntuación Confianza de la evidencia: Medio

Arquitectura

Mantenibilidad

Contenido

Comunidad

Cumplimiento de la especificación

Lo que puedes crear

Encontrar una capacidad faltante

Buscar una habilidad que coincida con una tarea actual, como SEO, pagos, documentación o guía sobre frameworks.

Gestionar habilidades instaladas

Listar habilidades instaladas, comprobar actualizaciones, eliminar habilidades sin usar y mantener actualizados los metadatos locales.

Revisar la seguridad de una habilidad antes de instalarla

Escanear una habilidad local o remota en busca de patrones riesgosos antes de permitir que influya en el comportamiento del agente.

Prueba estos prompts

Buscar una habilidad

/learn frontend react components

Instalar una habilidad conocida

/learn @owner/skill-slug

Auditar una habilidad local

/learn scan ./SKILL.md

Actualizar habilidades gestionadas

/learn update

Mejores prácticas

Revisar la previsualización, la fuente y la puntuación de seguridad antes de instalar cualquier habilidad.
Usar el modo de escaneo para habilidades locales o de terceros antes de añadirlas a un espacio de trabajo de agente.
Desactivar la calificación automática si tu equipo no quiere que se envíen comentarios a un servicio externo.

Evitar

No instales habilidades con baja puntuación solo porque coinciden con las palabras clave de la tarea.
No trates los escaneos basados en patrones como un sustituto completo de la revisión manual de instrucciones no confiables.
No permitas actualizaciones remotas de habilidades en espacios de trabajo sensibles sin revisar el contenido modificado.

Preguntas frecuentes

¿Qué hace esta habilidad?

Busca, previsualiza, instala, actualiza, elimina, escanea y califica habilidades de agentes de IA desde agentskill.sh.

¿Funciona con Claude Code?

Sí. La habilidad declara compatibilidad con Claude, Codex y Claude Code.

¿Instala código automáticamente?

Puede escribir archivos de habilidades después de un paso de previsualización, escaneo de seguridad y confirmación del usuario descrito en las instrucciones.

¿Puede el escaneo de seguridad demostrar que una habilidad es segura?

No. Detecta patrones riesgosos conocidos, pero los usuarios aun así deberían revisar el contenido de habilidades no confiables.

¿Qué datos puede enviar externamente?

Contacta con agentskill.sh para flujos de trabajo de búsqueda, instalación, actualización, seguimiento de instalaciones, comentarios e informes de seguridad.

¿Cuándo deberían evitarla los equipos?

Evítala en entornos restringidos donde no se permitan instrucciones remotas, telemetría o escritura de habilidades en el espacio de trabajo.