一键导入
这个仓库中的 skills
Create, test, and develop swamp extensions — models, vaults, drivers, datastores, and reports. Covers Zod schemas, smoke testing, manifest.yaml, and the quality scorecard. Do NOT use for running existing models (swamp-model), using vaults (swamp-vault), workflows (swamp-workflow), debugging (swamp-troubleshooting), or publishing (swamp-extension-publish). Triggers on "create model", "custom model", "extension model", "zod schema", "build integration", "extensions/models", "implement model", "smoke test extension", "test extension", "manifest.yaml", "custom vault", "VaultProvider", "extensions/vaults", "custom driver", "ExecutionDriver", "extensions/drivers", "custom datastore", "DatastoreProvider", "extensions/datastores", "create report extension", "extensions/reports", "quality score", "scorecard", "improve my extension", "extension quality", "rubric", "fast-check", "extension grade", "symbols-docs".
Publish swamp extensions to the registry and manage post-publication lifecycle (deprecation). Enforces a state-machine checklist that verifies repo initialization, authentication, manifest validation, collective ownership, version bumping, formatting, and dry-run before allowing a push. Also covers deprecating and undeprecating published extensions. Do NOT use for creating extensions (that is swamp-extension), improving quality scores (that is swamp-extension), or smoke testing extensions before push (that is swamp-extension). Use when publishing, pushing, releasing, deprecating, or undeprecating extensions. Triggers on "publish extension", "push extension", "extension push", "publish to registry", "swamp extension push", "release extension", "prepare for publishing", "extension-publish", "deprecate extension", "undeprecate extension", "mark extension deprecated", "remove deprecation", "extension deprecated", "superseded by".
Drive the @swamp/issue-lifecycle model for interactive issue triage and plan iteration against swamp-club lab issues. Use when the user wants to triage a swamp-club issue, generate an implementation plan, or iterate on a plan with feedback. Triggers on "triage issue", "triage #", "issue plan", "review plan", "iterate plan", "approve plan", "issue lifecycle".
Manage swamp vaults for secure secret storage — create vault instances, store and retrieve secrets, list keys, and use vault expressions in workflows. Use when working with existing vault types through the CLI. Do NOT use for creating custom vault TypeScript implementations (that is swamp-extension). Triggers on "vault", "secret", "secrets", "swamp vault", "store secret", "get secret", "vault expression", "aws secrets manager", "credential storage", "vault create", "vault put", "vault read-secret", "vault list-keys", "vault migrate", "vault annotate", "vault inspect", "annotation", "annotate secret", "inspect secret".
Fetch, edit, search, and submit issues to swamp Lab — view details, edit title/body, search/list issues, file bugs/features/security reports, post ripples (comments) with close/reopen, route to extension publishers. Triggers on "bug report", "feature request", "security report", "report bug", "file bug", "submit bug", "swamp bug", "swamp feature", "feedback", "report issue", "file issue", "extension bug", "ripple", "comment on issue", "close issue", "reopen issue", "get issue", "view issue", "fetch issue", "show issue", "edit issue", "update issue", "change issue title", "search issues", "list issues", "find issue", "issue search".
Work with swamp workflows for AI-native automation — define jobs and steps in YAML, wire models together with dependencies, validate DAGs, and inspect run history. Use when searching for workflows, creating new workflows, validating workflow definitions, running workflows, or viewing run history. Triggers on "swamp workflow", "swamp workflow create", "swamp workflow run", "swamp workflow validate", "workflow YAML", "workflow DAG", "wire models together", "model_method step", "workflows/*.yaml", "swamp run history", "swamp workflow logs", "debug swamp workflow". Use ONLY for swamp's declarative YAML workflow artifacts created via swamp workflow create — NOT for the Claude Code Workflow tool, multi-step agent task lists, worktrees, or cron/scheduled agent runs.
Run, configure, and view reports for swamp models and workflows. Use when running reports via CLI, configuring report selection in definition YAML, viewing report output, or filtering reports by label. Do NOT use for creating report extensions (that is swamp-extension) or debugging report failures (that is swamp-troubleshooting). Triggers on "run report", "swamp report", "model report", "report output", "report label", "skip report", "report results", "cost report", "audit report", "workflow report", "report get", "report filtering".
Work with existing swamp models — structured automation units that define typed schemas, methods (validate, transform, enrich), and outputs for data processing. Use when searching for model types, describing schemas, creating inputs, running or executing methods, viewing outputs, or managing lifecycle (edit, delete). Do NOT use when the user wants to build, create, or implement a custom model type, Zod schema, or TypeScript model — that is swamp-extension. Do NOT use for orchestrating or chaining models in workflows — that is swamp-workflow. Triggers on "swamp model", "model type", "model schema", "create input", "type search", "type describe", "run method", "execute method", "validation method", "transform method", "enrichment model", "model validate", "model delete", "model edit", "model output", "output logs", "output format", "CEL expression".
Manage swamp repositories, datastores, extension sources, and the audit integration — initializing repos (single or multi-tool), upgrading swamp, syncing data, releasing stuck locks, loading extensions from external paths, and installing swamp in CI. Do NOT use for diagnosing health check failures or doctor command output (that is swamp-troubleshooting). Triggers on "repo", "repository", "init", "setup swamp", "upgrade swamp", ".swamp folder", "datastore", "datastore sync", "datastore lock", "stuck lock", "install swamp", "CI/CD", "extension source", ".swamp-sources.yaml", "source add", "source rm", "multi-tool repo", "multiple tools", "--tool", "enroll tool", "primary tool", "marker.tools".
Interactive getting-started walkthrough for new swamp users. Guides through understanding the user's goals, creating and running a first model, inspecting output, and choosing next steps. Uses a state-machine checklist with verification at each step. Triggers on "getting started", "get started", "new to swamp", "first time", "tutorial", "walkthrough", "onboarding", "how do I start", "what do I do first", "quickstart", "quick start", "hello world", "first model", "just installed swamp", "show me how swamp works", "intro to swamp", "new user", "set up swamp", "learn swamp".
Diagnose swamp problems and verify health through a layered diagnostic loop — health checks, error inspection, tracing, and source reading. Do NOT use for smoke testing extensions (swamp-extension) or setting up repos (swamp-repo). Triggers on "swamp error", "failing", "not working", "crash", "timeout", "bug", "debug", "troubleshoot", "root cause", "slow", "performance", "latency", "erroring", "workflow error", "step error", "is swamp working", "health check", "diagnose swamp", "audit log empty", "hooks not firing", "extension not loading", "swamp-warning", "preflight", "doctor audit", "doctor extensions", "internals", "under the hood".
Manage swamp model data — list data artifacts, view version history, delete data artifacts, run garbage collection, and query data using CEL predicates. Use when working with swamp model data lifecycle, retention policies, version cleanup, removing specific data artifacts, searching for data by field values, filtering by attributes or tags, or exploring results after running a model method. Triggers on "swamp data", "model data", "data list", "data get", "data versions", "garbage collection", "gc", "data gc", "data retention", "data lifecycle", "version history", "data cleanup", "data delete", "delete data artifact", "remove data", "purge data", "prune data", "expire data", "ephemeral data", "data query", "query data", "find data", "search data where", "filter data", "which data has", "data with", "select from data", "data.query", "context.queryData", "CEL predicate", "data predicate", "inspect results", "method output", "factory results", "browse artifacts", "what did method produce".
Terminal output design system for swamp CLI commands. Use when creating or modifying any CLI command output, render function, or presentation layer code. Ensures consistent formatting, coloring, and structure across all swamp commands in both "log" (human-readable) and "json" (structured) output modes. Triggers on output files in src/presentation/output/, render functions, writeOutput usage, OutputMode handling, or any CLI command that produces terminal output.