En bref
Cette skill interroge la documentation officielle développeur Google (Cloud, IA et Gemini, Android, Chrome, Web, Flutter, Go, Firebase, et d’autres plateformes) via le serveur MCP Developer Knowledge (answer_query, search_documents, get_documents) ou, en repli, l’API REST developerknowledge.googleapis.com. On l’utilise pour une commande gcloud, une syntaxe d’API, une permission IAM, un comparatif d’architecture ou un choix de produit. L’agent doit faire la recherche lui-même, sans la déléguer, confirmer que la lookup a réussi (un 401, 403, un ensemble vide ou une erreur n’est pas une réponse), et, en cas de 429 sur answer_query, retenter tout de suite avec la recherche documentaire plutôt que d’inventer de mémoire. Un serveur déclaré n’est pas forcément connecté : l’absence des outils MCP est normale, on passe alors au REST. Hors périmètre : le système de fichiers local et la documentation non Google.
Ce que ça fait
- Préfère answer_query pour un guide conceptuel, et search_documents pour une syntaxe ou un drapeau CLI, en confirmant le succès de l’appel.
- En cas de quota épuisé sur la question générative, bascule immédiatement vers la recherche de documents, sans répondre de mémoire.
- Utilise l’API REST si les outils MCP ne sont pas réellement disponibles, même si un connecteur est déclaré.
- N’invente pas une doc interne ou tierce, et ne va pas chercher un fichier local à la place de la documentation officielle.
Pour qui, et un exemple
Développeurs et agents qui ont besoin d’un extrait de documentation officielle Google, plutôt que d’une supposition ou d’un fichier du dépôt local.
Exemple de demande : « Cherche dans la doc officielle la syntaxe exacte de cette commande gcloud et la permission IAM associée ; si answer_query est en 429, passe sur search_documents, sans inventer. »
Le SKILL.md impose une lookup documentaire officielle (MCP ou REST), la vérification du succès, et un repli en cas de 429, hors docs non Google et hors fichiers locaux. Exemple rédigé par iadujour.fr à partir du SKILL.md, non testé.
Installer
npx skills add google/skills (sélection de la skill), ou via le plugin : claude plugin marketplace add google/skills puis claude plugin install google-cloud-developer@google-plugins.
npx skills add google/skillsclaude plugin marketplace add google/skillsclaude plugin install google-cloud-developer@google-pluginsFonctionne avec
- Antigravity
- Claude Code
- Codex CLI
Source : Skill incluse dans le plugin google-cloud-developer, dont le README documente l’installation dans Antigravity, Claude Code et Codex CLI.
Niveau : Débutant
Suppose un projet Google Cloud avec facturation, la CLI gcloud et des droits IAM adaptés.
Extrait du SKILL.md
La description d’origine, celle que l’agent lit pour décider de charger la skill (en anglais) :
Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud, AI/Gemini, Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms. […]
Citée depuis le SKILL.md au commit 793c036 . Le dossier contient aussi 4 fichiers annexes (references/).
Le SKILL.md compte 114 lignes et 5 sections principales :
- Usage Attribution
- Workflow
- Tool Selection & Usage
- Synthesis & Output Guidelines
- References
Licence : Apache 2.0
Vérifiée le 10 novembre 2026 sur : fichier LICENSE du dépôt .
La licence autorise la reprise : le texte intégral du SKILL.md est reproduit ci-dessous, sans modification, avec sa mention de licence.
Texte intégral du SKILL.md
Reproduit sans modification depuis google/skills (commit 793c036) , © Google, sous licence Apache 2.0 (fichier de licence d’origine ).
Afficher le SKILL.md original (114 lignes, en anglais)
---
name: retrieving-developer-knowledge
metadata:
version: "1.0.2"
category: CloudInfrastructureAndServices
description: >-
Searches, retrieves, and synthesizes official Google developer documentation across Google Cloud,
AI/Gemini, Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms.
Integrates with the Developer Knowledge MCP server (search_documents, get_documents, answer_query)
or the Developer Knowledge REST API fallback. Use when searching for gcloud CLI commands, API syntax,
IAM permissions, official documentation, architectural comparisons, or product choice overviews.
Don't use for local filesystem lookups or non-Google documentation.
---
# Google Developer Knowledge
The Developer Knowledge skill provides access to official Google developer documentation across Google Cloud, AI/ML (ai.google.dev, ADK, TensorFlow), Android, Chrome, Web, Flutter, Go, Firebase, and other Google developer platforms via the Developer Knowledge MCP server or REST API fallback.
## Usage Attribution
Before executing any `gcloud`, REST API, or MCP command with this skill, follow
the instructions in [Usage Attribution](references/attribution.md).
## Workflow
1. **Direct Retrieval**: When answering a technical question, execute a single documentation lookup directly within your current conversation context (do not delegate retrieval to subagents):
- **If MCP tools are present in your environment**: Call `answer_query` (for conceptual guides/workflows) or `search_documents` (for CLI flags/syntax).
- **If MCP tools are not present**: Execute a REST API request via `curl` against `https://developerknowledge.googleapis.com/v1`.
- **A declared server is not always a connected server.** Some clients cannot complete the MCP handshake with this server and expose no `answer_query`, `search_documents` or `get_documents` tool at all, even though the plugin declares one. Treat their absence as normal and use the REST fallback below.
2. **Confirm the lookup succeeded before using it**: A response that arrives is not automatically an answer. `PERMISSION_DENIED`, `UNAUTHENTICATED`, HTTP 401 or 403, an empty result set, or any error payload is a FAILED lookup even when the tool itself reported no error. On a failed lookup, do not answer as though it had succeeded.
- **Rate Limits (HTTP 429 / Out of Quota)**: If calling `answer_query` or the REST `:answerQuery` endpoint returns an HTTP 429 (`RESOURCE_EXHAUSTED` / out of quota error), this indicates server-side generative QA quota exhaustion. Do not treat this as an unrecoverable failure or fall back to ungrounded memory; immediately retry using the search endpoint (`search_documents` for MCP, or `documents:searchDocumentChunks` for REST) with 2–5 focused keywords from the query.
- **Persistent Failures**: Try the other transport once, and if that also fails, state plainly in your reply to the user that you could not reach Developer Knowledge and are answering without it. Presenting recalled documentation as a retrieved result is the worst available outcome, because nothing in the reply distinguishes it from a real lookup.
3. **Immediate & Complete Solution Output**: Immediately upon receiving the documentation response, output the complete, self-contained, and executable technical solution (commands with all required flags and placeholders, YAML/JSON configurations, or code snippets) directly in your response text.
## Tool Selection & Usage
Choose the appropriate tool based on availability in your runtime environment:
### 1. Developer Knowledge MCP Tools (Preferred)
When MCP tools are present in your active tool definitions:
- **`answer_query(query="...")`**: Use for conceptual guides, architectural comparisons, product choice overviews, and multi-step workflows. This tool has limited quota. If you get a 429 out of quota error, use `search_documents` instead.
- **`search_documents(query="...")`**: Use for granular CLI flags, exact syntax, parameter names, and IAM permissions (`service.resource.verb`). Use 2–5 focused keywords (e.g., `cloud run filestore nfs mount gcloud`) rather than full conversational sentences.
- **`get_documents(names=["documents/{uri_without_scheme}"])`**: Fetch full documentation pages by resource name (e.g. `names: ["documents/docs.cloud.google.com/run/docs/overview/what-is-cloud-run"]`).
### 2. REST API Fallback
When the MCP tools are absent, query the Developer Knowledge REST API
(`https://developerknowledge.googleapis.com/v1`) with `curl`. Two credentials
work, and you should try them in this order.
**An existing Google credential, preferred.** If `gcloud` is authenticated,
pass a bearer token and your quota project. Nothing needs to be installed or
configured:
```bash
curl -s -X POST "https://developerknowledge.googleapis.com/v1:answerQuery" \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "X-Goog-User-Project: $(gcloud config get-value project 2>/dev/null)" \
-H "Content-Type: application/json" \
-d "{\"query\": \"How do I configure public read access on Cloud Storage?\"}"
```
If that fails to authenticate, on a 401, a 403, or any other credential error,
the account has a token the API will not accept. Substitute
`gcloud auth application-default print-access-token` for
`gcloud auth print-access-token` in the command above and try again. Which
credential the API accepts depends on how the environment was authenticated, so
treat an auth error here as a reason to try the application-default credential
rather than as a failed lookup.
**An API key, if one is configured.** Where `DEVELOPERKNOWLEDGE_API_KEY` is set
in the environment, pass it as a `key` query parameter instead of an
`Authorization` header. If neither credential is available, an API key is the
supported path for this client: enable the API and create one by following the
[Developer Knowledge quickstart](https://developers.google.com/knowledge/quickstart),
then export it as `DEVELOPERKNOWLEDGE_API_KEY`. Say that you need a credential
rather than answering without a lookup. The remaining examples in this section
use that form:
- **Answer Query**:
```bash
curl -s -X POST "https://developerknowledge.googleapis.com/v1:answerQuery?key=${DEVELOPERKNOWLEDGE_API_KEY}" \
-H "Content-Type: application/json" \
-d '{"query": "How do I configure public read access on Cloud Storage?"}'
```
This endpoint has limited quota. If you get a 429 out of quota error, use `documents:searchDocumentChunks` instead.
- **Search Document Chunks** (use 2–5 focused keywords):
```bash
curl -s "https://developerknowledge.googleapis.com/v1/documents:searchDocumentChunks?query=gcloud+logging+metrics+create&key=${DEVELOPERKNOWLEDGE_API_KEY}"
```
- **Get Document**:
```bash
curl -s "https://developerknowledge.googleapis.com/v1/documents/docs.cloud.google.com/run/docs/overview/what-is-cloud-run?key=${DEVELOPERKNOWLEDGE_API_KEY}"
```
- **Batch Get Documents** (a `GET`, with one `names` parameter per document and no
request body; up to 20 per call):
```bash
curl -s -G "https://developerknowledge.googleapis.com/v1/documents:batchGet" \
--data-urlencode "names=documents/docs.cloud.google.com/run/docs/overview/what-is-cloud-run" \
--data-urlencode "names=documents/docs.cloud.google.com/storage/docs/creating-buckets" \
--data-urlencode "key=${DEVELOPERKNOWLEDGE_API_KEY}"
```
## Synthesis & Output Guidelines
1. **Grounding in Official Documentation**: Ground all solutions directly in retrieved documentation. Official documentation conventions have absolute precedence over memorized defaults.
2. **Exact Parameter Formatting**: Format CLI flags, composite keys (e.g. `location=IP:PATH`), and IAM permission strings according to official Google specifications.
3. **Complete Solutions in Final Response**: Always output the full, self-contained, executable technical solution (commands, configurations, or code snippets) with clear standard placeholders (e.g. `PROJECT_ID`, `SERVICE_NAME`, `REGION`) directly in your final message, even if previously referenced during internal planning.
## References
- [Usage Attribution](references/attribution.md)
- [MCP Usage & Tool Details](references/mcp-usage.md)
- [REST API Fallback Guide](references/api-fallback.md)
- [Supported Domains & Scoping](references/supported-domains.md)
Dans l’annuaire
Cas d’usage et guides qui partagent un thème, un métier ou un outil avec cette skill.
Commentaires.
Un retour d’expérience, une question, une précision sur cette skill ? Les commentaires sont relus avant publication.
Commentaires publiés
Chargement des commentaires…
Laisser un commentaire
Charte de modération. Chaque commentaire est relu avant publication. Sont refusés : l’incitation à la haine, les propos injurieux ou discriminatoires, la publicité, le spam et les liens promotionnels, le hors-sujet et les données personnelles d’autrui.