Loading...
Loading...
Found 649 Skills
Validate, lint, audit, or check Makefiles and .mk files for errors.
ALWAYS invoke this skill at the START of every session before doing any other work. Validates project health: governance rules, tool availability, memory directory, settings files, script permissions, .agents directory, and .beads/.gitignore hygiene. Remediates issues across all swain skills. Idempotent — safe to run every session.
CLI and TUI tool that explains why processes, services, and ports are running by tracing causality chains across supervisors, containers, and shells.
Create or update AgentDeploy SharedInfra and Service YAML files, validate them, deploy apps with the agentdeploy CLI and Platform API, poll status and explain output, and debug structured deployment failures. Use when a user wants to deploy, redeploy, or troubleshoot an app on an AgentDeploy installation.
GitHub data collection patterns for workflow agents. Covers search query construction by intent, date range handling, repository scope narrowing, preferences.md integration, cross-repo intelligence, parallel stream collection model, and auto-recovery for empty results. Use when building agents that search GitHub for issues, PRs, discussions, releases, security alerts, or CI status.
Discover Harbor capabilities, inspect capability details, and explain grant or secret blockers before execution. Use when asked what Harbor can do, list capabilities, inspect a capability, check whether a capability exists, or find the next safe Harbor action.
Use when the user wants to deploy and run a prepared AWS FIS experiment. Triggers on "execute FIS experiment", "run FIS experiment", "start chaos experiment", "deploy FIS template", "启动 FIS 实验", "运行混沌实验", "执行故障注入实验", "deploy and run the experiment in [directory]". Expects a prepared experiment directory (from aws-fis-experiment-prepare or manually created) containing experiment-template.json, iam-policy.json, cfn-template.yaml, and alarm configs. Deploys resources via CLI or CloudFormation, starts the experiment with strict user confirmation, monitors progress, and generates results report.
Manage Alibaba Cloud Real-Time Compute for Apache Flink instances across the full lifecycle, including create/query/scale/renew/convert, namespace operations, tagging, cleanup, and batch execution. Use this skill only when the user explicitly asks to operate Alibaba Cloud Flink instances or their direct child resources in a region; do not trigger for unrelated prompts.
Inedo Otter integration. Manage data, records, and automate workflows. Use when the user wants to interact with Inedo Otter data.
Tideways integration. Manage data, records, and automate workflows. Use when the user wants to interact with Tideways data.
Validate, lint, audit, or fix PromQL queries and alerting rules; detects anti-patterns.
Inspect, triage, approve, and merge GitHub Renovate pull requests with gh. When no repository is provided, use the default preset repository set, build a candidate execution plan, and execute only after explicit user confirmation. Use when the user asks to check, batch-handle, approve, or merge Renovate PRs.