All Agent Skills
41,263 results
- Init ModeGitHubOfficialTeam initialization flow (Phase 1 proposal + Phase 2 creation)
- Iterative RetrievalGitHubOfficialMax-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.
- Javascript RefactoringGitHubOfficialSplit large JavaScript files into maintainable modules safely.
- JqschemaGitHubOfficialInfer JSON structure and types with jq-based schema discovery.
- MessagesGitHubOfficialAdd new safe-output message types and wire validation/rendering.
- Model Routing GoldenGitHubOfficialMaintain model-routing audit golden fixtures and expected outputs.
- Model SelectionGitHubOfficialDetermines which LLM model to use for each agent spawn
- NapGitHubOfficialContext hygiene — compress, prune, archive .squad/ state
- Notification RoutingGitHubOfficialRoute agent notifications to specific channels by type — prevent alert fatigue from single-channel flooding
- NpmGitHubOfficialTroubleshoot npm registry, proxy, and certificate failures on the Microsoft corporate network or VPN using the 1ES public npm feed.
- Open Pull RequestGitHubOfficialPublish validated gh-aw changes as a draft pull request from a cloud agent.
- Operational Value DesignerGitHubOfficialDesign recorded-session outcome metrics using built-ins, isolated JavaScript, or separate-job operational-value Bash. Usage: /operational-value-designer OWNER/REPO WORKFLOW-NAME.
- Optimize Agentic WorkflowGitHubOfficialAnalyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.
- Otel QueriesGitHubOfficialAnalyze gh-aw OpenTelemetry traces from JSONL mirrors or OTLP backends.
- Personal SquadGitHubOfficialUser-level AI agents that travel with you across projects
- Pr FinisherGitHubOfficialPrepare an open pull request for merge from a GitHub Copilot cloud agent. Drives Reviews, local validation, and Mergeable to a ready state. Does not merge, and cannot trigger CI.
- Pr Review ResponseGitHubOfficialTeaches agents to reply to PR review comment threads after fixing issues, making resolutions traceable
- Pr ScreenshotsGitHubOfficialCapture Playwright screenshots and embed them in GitHub PR descriptions
- Pr To Go LinterGitHubOfficialGenerate a new pkg/linters analyzer from a merged or open PR pattern.
- Project ConventionsGitHubOfficialCore conventions and patterns for this codebase
- Prompt Token EfficiencyGitHubOfficialRewrite prompts for minimal tokens, maximal clarity, and low ambiguity for LLM consumption.
- Ralph Two Pass ScanGitHubOfficialCuts GitHub API calls by separating lightweight list scanning from full hydration
- ReflectGitHubOfficialLearning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.
- Release ProcessGitHubOfficialPre-release validation, npm publish procedures, and post-publish verification