Skip to content

Relewise/relewise-agent-plugins / plugins/relewise/skills/relewise-core

relewise-core

Verified

Discover, identify, inspect, and compare Relewise Datasets. Use when a user asks which Datasets they can access, wants details or Agent Gateway capabilities for a Dataset, or needs Dataset context resolved before another Relewise task.

Relewise Core

Before any Agent Gateway call, activate and follow the installed relewise-agent-gateway skill from this plugin. Pass it the selected REST operation ID and/or MCP tool plus validated parameters; do not resolve the CLI, choose a transport, or handle authentication in this domain skill.

Resolve Dataset context

  1. Discover candidate Datasets and authentication metadata for the current connection using REST operation IdentityGetCurrentUser or related MCP tool get_me through the Agent Gateway skill. For no Datasets or a missing expected Dataset, follow the setup skill's Dataset access guidance, selecting PAT or OAuth guidance from the returned authentication method.
  2. Match the user's wording against returned Dataset and License display names. Never invent or infer a Dataset ID that was not returned.
  3. If multiple Datasets plausibly match and the intended one changes the answer, present the concise candidates and ask the user to choose.
  4. Retrieve details for each selected Dataset before relying on its metadata or effective Agent Gateway policy. Use REST operation CoreGetDataset or related MCP tool get_dataset_details through the Agent Gateway skill.

Keep Dataset selection local to the current request. Do not establish one global Dataset. Resolve and validate each Dataset independently for comparisons.

Work with Dataset capabilities

For missing configuration or a policy restriction, follow Dataset policy guidance and verify again after the user confirms changes.

Use the effective policy to explain whether REST and MCP are enabled and which Agent Gateway Areas are available. Do not claim a capability that its policy disables.

When Dataset-specific vocabulary such as languages, currencies, Data Keys, or Classification Values is needed, use the Dataset-metadata capability. Inspect the selected transport's current schema first; over REST its operation ID is CoreGetDatasetMetadata. Treat Data Key names as case-sensitive.

Respond

Use Dataset display names in the answer and include IDs only when they help disambiguate or the user requests them. For comparisons, preserve the association between each result and its Dataset. Explain access or policy limitations plainly; do not silently substitute another Dataset.

reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 469kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 321kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 321kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 321kUpdated Claude CodeCodexVerifiedInstall