Index of every page on this site: llms.txt
All skills
apollographql avatar

/graphos-factory

@9dda139 official
by Apollo GraphQLapollographql/skills134 stars
14
Run it yourself

Build and iterate on an Apollo Connectors subgraph for a GraphOS supergraph from a REST API, with or without an OpenAPI or Swagger spec, in a dedicated git workspace that records what the API offers, the user's operation and field selection, every design decision, and the evidence each verification layer produced. Use whenever the user wants to wrap a REST API as a GraphQL subgraph for their supergraph, add or remove operations or fields from an existing connector subgraph, refresh one against a new spec, or record live API traffic as test fixtures, even if they do not say "connector", "subgraph" or "Apollo".

Use this Skill: https://skilld.dev/gh/apollographql/skills/graphos-factory

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

graphos-factory-corereferencesselection-review.md

≈472 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Read-only selection review

Use this optional instrument to explain or validate proposed changes to selection.yaml. It is available from an ordinary agent chat and does not require a UI or a service process.

graphos-factory-core selection review /path/to/workspace
graphos-factory-core selection review /path/to/workspace --candidate /path/to/candidate.yaml --expect-input INPUT_TOKEN
graphos-factory-core selection review /path/to/workspace --candidate /path/to/candidate.yaml --expect-input INPUT_TOKEN --expect-review REVIEW_TOKEN

The first call returns JSON containing the current selection and an input token. Author candidate YAML separately, then pass the input token with that candidate. Validation checks workspace, inventory and selection schemas and requires operation keys to exist in inventory. The report preserves exact YAML and describes additions, removals, changed decisions, explicitly unconfirmed response hints and writes assigned to GraphQL queries.

The input token covers the canonical workspace path, embedded inventory/selection schemas, and the bytes or absence of workspace.yaml, inventory.json, selection.yaml, sources.lock.yaml, applied.lock.yaml, decisions.json, findings.json and memory.md inside .factory. The review token additionally binds the exact candidate bytes. Expected-token mismatches refuse the review.

Tokens establish observed content equality, not uninterrupted history or user approval. Edit-then-revert between observations cannot be detected. A report is not comprehensive lint, proof of confirmation, a write lock or permission to save. .factory and its named inputs cannot be symlinks. Successful calls emit JSON contract version 1; refusals exit 1 with stderr. No call writes files, confirms hints or starts apply. The usual user decisions and validation rules remain in force whether or not this instrument is used.

Source: SKILL.md on GitHub

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

No alerts20d3 checks · Risk SAFE
  • Gen Agent Trust Hub20d

    The skill is a professional tool for building Apollo Connector subgraphs. It installs and uses official vendor tools (Apollo Rover, Apollo Router, WireMock) from official sources. It follows security best practices for credential management, including redaction and environment variable usage. It requires explicit user consent for tool installation and licensing. While it processes untrusted OpenAPI specifications, it includes instructions for auditing results to mitigate indirect prompt injection risks.

  • Socket20d

    No alerts

  • Snyk20d

    Risk: LOW · No issues

Signed by skilld at 9dda139. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 3 weeks ago.

Activeupdated last month
metadata
{
  "version": "0.12.3"
}
Other metadata
compatibility
macOS or Linux (WSL on Windows) with bash, curl, git and jq; Java 17+ for the end-to-end and live layers. Any Agent Skills host (Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI and others) that can run shell commands.

README badge

README badge for apollographql/skills/graphos-factory