Index of every page on this site: llms.txt
All skills
open-neko avatar

/graphjin-config

@621f131
by open-nekoopen-neko/openneko22 stars
3
Run it yourself

Use when viewing or proposing changes to GraphJin sources, roles, access, security, runtime settings, and reload behavior.

  • 1 file
  • 3 KB
  • Updated 3 months ago
  • GitHub
Use this Skill: https://skilld.dev/gh/open-neko/openneko/graphjin-config

Nothing lands on disk. Nothing to clean up.

Fork this Skill

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

SKILL.md

≈35 tokens for metadata: the name and description. ≈729 when used: this file.

Description uses 1.8% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈140 characters, or 1.8%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

GraphJin Config

Use the source-config manager tools for GraphJin configuration requests.

Workflow

  1. Call mcp_neko_source_config_manager_describe_source_graph to identify the selected GraphJin data engine and its current sources.
  2. Call mcp_neko_source_config_manager_ask_graphjin_config_agent with the user's configuration question or requested change.
  3. For a view or explanation, answer with the redacted configuration-agent result and the relevant source-graph details.
  4. For a database source registration, call mcp_neko_source_config_manager_list_source_secret_names and use a stored name as secretRef. When the required name is absent, direct the admin to Admin > Settings > GraphJin Config to add it.
  5. For an API source, use the managed OpenAPI asset from the submitted card. When the admin provides a hosted HTTPS URL in chat, call mcp_neko_source_config_manager_import_openapi_spec. When they uploaded a file, read the asset ID from the submitted values. When the submitted card provides metadata only, call mcp_neko_source_config_manager_list_openapi_specs to resolve its managed asset ID.
  6. For a local file source, use the localFiles manifest from the submitted card. For S3 or GCS, collect the bucket and applicable prefix, region, endpoint, public base URL, and presign TTL; GraphJin uses the deployment runtime identity for object-store credentials.
  7. For a supported edit, call mcp_neko_source_config_manager_request_source_config_change with the confirmed fields.
  8. Summarize the proposed change and its approval status.

A view or explanation succeeds when the response includes the redacted result from ask_graphjin_config_agent. An edit succeeds when the response includes the proposal result from request_source_config_change.

When a tool returns an error, report the error and the workflow step that needs attention.

Supported Edits

  • register_source: provide name, one of the customer source kinds (database, api, or file), and the fields for that kind. Database uses connection metadata and a stored secretRef; API uses a managed OpenAPI specAssetId; local file uses the card's managed localFiles manifest; S3 and GCS use an object-store bucket and deployment runtime identity. File sources receive authenticated read-only access. A suitable database default is read: authenticated, write: blocked, and delete: blocked.
  • set_source_access: provide the source name and confirmed read, write, and delete access modes.
  • add_role: provide the role name and the JWT match expression confirmed by the admin.

Use an unused source name for registration. Source access patches the named source, and role changes upsert by role name. A full replacement is a separate configuration operation requiring the current configuration and explicit admin intent.

Source: SKILL.md on GitHub

No rule matched.

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 third-party reports yet.

Signed by skilld at 621f131. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 4 weeks ago.

Activeupdated 3 months ago
type
Skill

README badge

README badge for open-neko/openneko/graphjin-config