Loading...
Loading...
Found 2,946 Skills
Provides active execution protocols to rigorously audit how code, directory structures, and agent actions comply with the authoritative ecosystem specs. Trigger when validating new skills, plugins, or workflows.
Configures Elastic Cloud authentication and environment defaults. Use when setting up EC_API_KEY, configuring Cloud API access, or when another cloud skill requires credentials.
This skill should be used when the user asks to "create a skill", "write a new skill", "add a skill", "SKILL.md format", "skill frontmatter", or needs guidance on skill structure, progressive disclosure, or OpenCode skill development.
Pre-flight check before pushing to production. Catches TypeScript errors, accidentally staged secrets, pending migrations, and hygiene gaps before they hit live users.
Fetch PR feedback from all GitHub sources and validate every comment before acting. Use when user needs to process PR review comments, address reviewer feedback, or triage pull request discussions. Use for "review comments", "PR feedback", "address reviews", "address feedback", or "what did reviewers say". Do NOT use for creating new PRs, code review of local changes, or general code analysis without an existing PR.
Audit applications against your platform engineering constitution. Use when validating that code, configurations, and deployments align with organizational infrastructure standards.
Discuss and brainstorm a spec-driven change from a rough idea, then propose a change name and, after explicit confirmation, generate the same five proposal artifacts as spec-driven-propose.
Evaluate the output of a journey-builder run, identify instruction gaps, and edit the project root AGENTS.md (or add pitfalls to the gist) to fix those gaps. Does NOT modify the journey-builder skill itself.
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".
Critically review strategy drafts from edge-strategy-designer for edge plausibility, overfitting risk, sample size adequacy, and execution realism. Use when strategy_drafts/*.yaml exists and needs quality gate before pipeline export. Outputs PASS/REVISE/REJECT verdicts with confidence scores.
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own data", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model and technique, and reports whether the data is ready for training or evaluation.
Personalized links without explicit login for authentication. Apply when implementing authentication flows that don't require traditional login.