openspec-managerStaff Strategic Orchestrator for Spec-Driven Development (SDD). Proactively leads the lifecycle of a change, ensuring strategic alignment, technical rigor, and cross-disciplinary excellence.getting-openspec-artifact-instructionsOutputs enriched instructions for creating an artifact or applying tasks for an OpenSpec change. Use when the agent needs guidance on how to write a spec, design, or implement tasks.archiving-openspec-changeArchives a completed OpenSpec change and updates the main specifications. Use when implementation is finished and verified.checking-openspec-statusDisplays the completion status of artifacts for an OpenSpec change. Use to track progress of proposal, specs, design, and tasks.creating-openspec-changeCreates a new OpenSpec change directory and initial structure. Use when starting a new feature, bugfix, or refactor.initializing-openspecInitializes OpenSpec in a project directory. Use when starting a new project or adding OpenSpec to an existing one.listing-openspec-itemsLists OpenSpec items such as active change proposals and specifications. Use to discover what changes are in progress or what specs exist.updating-openspec-instructionsUpdates OpenSpec instruction files in a project. Use when OpenSpec is already initialized but instructions need refreshing or the CLI was updated.
저장소 탐색
yu-iskw · 저장소와 대표 skills - 2페이지
49개 GitHub 저장소에서 수집된 340개 skills를 저장소 단위로 보여줍니다.
build-and-fixBuild the project and automatically fix any build errors, compilation failures, or type mismatches. Use when the project fails to build, shows "broken" states, or after making significant changes.check-directory-structureInspect repository layout with tree and find, compare to AGENTS.md conventions, and fix misplaced or overly flat generated files. Use when auditing folder structure, after scaffolding or bulk file generation, when output looks flat, or when asked where…codeql-fixRun CodeQL security/quality analysis and fix findings. Use when the user asks to run CodeQL, security scan, static analysis, or fix CodeQL findings.improve-claude-configSelf-improvement skill for evolving Claude Code configuration. Use when you notice repeated mistakes, want to add new workflows, or optimize the development experience.lint-and-fixRun linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.node-upgradeSafely upgrade Node.js dependencies in pnpm workspaces. Use when asked to "upgrade dependencies", "update packages", "check for updates", or fix version mismatches.security-scanScan for vulnerable dependencies and CVEs via pnpm lint:security (Trunk Trivy/OSV-scanner), optional pnpm security:grype or pnpm lint:all (Trunk-all plus Grype). Use for dependency CVE checks, security-scoped lint, or post-bump verification.security-vulnerability-auditWorkflow for auditing security vulnerabilities using Trunk (Trivy and OSV-scanner). Use when checking for project vulnerabilities, hard-coded secrets, or repairing security flaws.
manage-adrManage Architecture Decision Records (ADRs) using adr-tools. Use this to initialize, create, list, and link ADRs to document architectural evolution.dbt-helpers-plugin-scaffoldScaffold and standardize new dbt-helpers plugins (Warehouse, Tool, or Schema). Use when starting a new plugin implementation or updating plugin discovery configuration.implement-agent-skillsComprehensive workflow for creating, implementing, and validating Agent Skills. Use when asked to "create a new skill", "author a skill", "add a capability", or when standardizing project-specific workflows. Support for platform detection (Cursor, Claude…setup-dev-envSet up the development environment for the project. Use when starting work on the project, when dependencies are out of sync, or to fix environment setup failures.dbt-helpers-golden-e2eImplement and run End-to-End tests using golden output comparison. Use when verifying CLI behavior, plan generation, or full project execution.dbt-helpers-integration-testcontainersSet up and run integration tests using Testcontainers. Use when testing warehouse adapters against real database engines or verifying filesystem-dependent operations.dbt-helpers-nullable-testingImplement and use Nullable Infrastructure adapters for mock-free testing. Use when writing unit tests for core logic, implementing infrastructure adapters, or setting up test fixtures.dbt-helpers-path-policyManage and enforce path templating and naming conventions in dbt-helpers. Use when implementing PathPolicy, defining template variables, or configuring warehouse-specific defaults.
general-security-auditWorkflow for auditing security vulnerabilities using trivy, osv-scanner, and trunk.implement-agent-skillsComprehensive workflow for creating, implementing, and validating Agent Skills. Use when asked to "create a new skill", "author a skill", "add a capability", or when standardizing project-specific workflows. Support for platform detection (Cursor, Claude…manage-adrManage Architecture Decision Records (ADRs) using adr-tools. Use this to initialize, create, list, and link ADRs to document architectural evolution.manage-changelogManage changelogs using Changie. Provides tools to initialize, add change fragments, batch releases, and merge version notes.security-vulnerability-auditWorkflow for auditing security vulnerabilities using trivy, osv-scanner, and trunk.update-readmeUpdate README.md to reflect changes in project structure, skills, and agents. Use when new components are added or architecture changes.implement-agent-skillCentral meta-skill for creating and unifying all Agent Skills. Orchestrates specialized meta-skills for analysis, workflows, tools, and scaffolding.node-upgrade-workflowStep-by-step workflow for safely upgrading Node.js dependencies across npm, pnpm, yarn, and bun.
mend-agent-skillsVerifies and updates the commands within existing Agent Skills to ensure they match the current codebase state.mend-subagentsSynchronizes Subagents with available Agent Skills, suggesting bindings and removing broken links.meta-agent-skillsProactively analyzes the codebase and generates specialized subagents and skills to standardize agentic workflows.add-agent-templatesAdd new Agent templates to the meta-agent-skills framework.add-skill-templatesAdd new Agent Skill templates to the meta-agent-skills framework.mend-agent-templatesMaintain and synchronize agent templates with their associated skill templates.lint-fixIteratively run linters, apply auto-fixes, and resolve remaining issues using Trunk.mend-agent-rulesSynchronize CLAUDE.md and AGENTS.md with available agents and skills.
bumpup-versionsConsistently bump and synchronize versions across all packages in the monorepo using pnpm. Use this to ensure the root and all workspace packages share the same version number.test-integration-dockerRun comprehensive integration tests using real skills (Vercel, Anthropic, Expo) in a Docker container. Managed via Makefile for standard lifecycle control.sync-readmeSynchronize technical sections in README.md and CONTRIBUTING.md with the actual project state.lint-and-fixRun linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.fix-issueFix a GitHub issue end-to-end. Use when given an issue number to fix, implementing bug fixes, or addressing reported problems.improve-claude-configSelf-improvement skill for evolving Claude Code configuration. Use when you notice repeated mistakes, want to add new workflows, or optimize the development experience.manage-adrManage Architecture Decision Records (ADRs). Use this to initialize, create, list, and link ADRs to document architectural evolution. Requires 'adr-tools' to be installed.manage-changelogManage changelogs using Changie. Provides tools to initialize, add change fragments, batch releases, and merge version notes. Requires 'changie' to be installed.
generate-openapi-typesGenerate or refresh TypeScript types from the Lightdash OpenAPI spec. Use this skill whenever the user asks to regenerate API types, update types from Lightdash, sync types with the swagger spec, or when types are out of date—even if they phrase it loosely…sync-openapi-typesRegenerate the Lightdash OpenAPI TypeScript types from the upstream swagger.json, then build and run tests to verify nothing regressed. Use when Lightdash releases new API versions, when type errors reference missing or changed endpoints, or when the…develop-mcp-server-tsStandardized workflow for building MCP servers in TypeScript. Use when building or extending an MCP server with the official TypeScript SDK (tools, resources, prompts), adding tool annotations (title, readOnlyHint, etc.), choosing Stdio vs Streamable HTTP…gen-mcp-toolScaffold a new Lightdash MCP tool module following the project's established patterns. Use when adding a new domain tool file to packages/mcp/src/tools/ and wiring it into profile mounts. Provide the resource name (e.g. "validations", "ai-agents") and the…lint-and-fixRun linters and fix violations, formatting errors, or style mismatches using Trunk. Use when code quality checks fail, before submitting PRs, or to repair "broken" linting states.setup-dev-envSet up the development environment for the project. Use when starting work on the project, when dependencies are out of sync, or to fix environment setup failures.manage-adrManage Architecture Decision Records (ADRs). Use this to initialize, create, list, and link ADRs to document architectural evolution. Requires 'adr-tools' to be installed.manage-package-versionsConsistently manage package versions across the monorepo using pnpm and changie. Use when bumping versions, preparing releases, or syncing versions.
createCreate a new Agent Skill from a short or incomplete request via intent compilation, architecture, deterministic validation, evaluation, and one bounded repair. Use when the user asks Skill Lab to design or generate a Skill.evaluateEvaluate an existing Agent Skill for package validity, trigger fit, and output quality without modifying it. Use when the user asks Skill Lab to score or diagnose a Skill.minimalMinimal portable Agent Skill template. Replace this description with what the skill does and when to use it.rigorousRigorous Agent Skill template for high-risk or high-value workflows with scripts, references, fixtures, and evals.standardStandard Agent Skill template with references and eval stubs. Replace with a concrete purpose and trigger guidance.normalize-configUse when a simple .env-style configuration needs deterministic normalization for comparison or review.propose-deploy-stopUse when asked to plan or prepare a deployment where irreversible deploy, release, or infrastructure actions might be tempting.technical-notes-to-articleUse when rough technical notes need to become an evidence-preserving article for readers outside the original project context.
setupInitialize or upgrade a Git-native OKF second-brain repository for governed knowledge maintenance.ingestProcess immutable raw sources into a provenance-aware OKF knowledge bundle with independent verification.lintProduce a read-only health report for the OKF second-brain knowledge bundle.maintainRun bounded, automation-safe second-brain maintenance across ingestion, linting, and safe repair.queryAnswer questions from the maintained OKF knowledge bundle with explicit provenance and uncertainty.repairApply explicitly approved safe repairs from a second-brain lint report and verify the result.statusSummarize second-brain health, processing state, and pending review work without modifying the repository.synthesizeCreate or refresh a cross-source synthesis page with explicit evidence, disagreement, and verification.
gh-auth-securityCheck GitHub CLI authentication and scopes for security alert APIs. Use when gh api security endpoints return 403/404 or before fetching Dependabot, code scanning, or secret scanning alerts.aggregate-security-reportMerge normalized envelopes from fetch-dependabot-alerts, fetch-code-scanning-alerts, and fetch-secret-scanning-alerts into one JSON summary and Markdown report. Use after fetch skills complete. Does not call gh.fetch-code-scanning-alertsList and normalize code scanning alerts (CodeQL, SARIF) for a GitHub organization or repository using gh api. Use when the user asks for code scanning, SAST, or CodeQL alerts for an org or repo.fetch-dependabot-alertsList and normalize Dependabot alerts for a GitHub organization or repository using gh api. Use when the user asks for dependency vulnerabilities, Dependabot alerts, GHSA, or CVE data for an org or repo.fetch-secret-scanning-alertsList and normalize secret scanning alerts for a GitHub organization or repository using gh api. Use when the user asks for leaked secrets, secret scanning, or token exposure for an org or repo.security-authCheck gh auth and org access before security fetches. Use when gh returns 403/404 or before first report on an org.security-repo-reportSecurity report for one repository (all three alert types). Use when the user names owner/repo.security-reportFull org security report (Dependabot, code scanning, secret scanning). Use when the user wants an organization security overview or open-alert summary.
sqlfluff-ci-rolloutUse when adding SQLFluff to CI or making SQLFluff PR checks manageable for a large SQL or dbt-style project.sqlfluff-lint-triageUse when running SQLFluff lint on SQL or dbt-style projects and summarizing violations without immediately editing files.sqlfluff-parse-debugUse when SQLFluff cannot parse rendered SQL and the dialect, grammar, or parse tree needs diagnosis.sqlfluff-project-onboardingUse when onboarding to a SQL or dbt-style project and determining the right SQLFluff dialect, templater, config, and baseline lint commands.sqlfluff-rules-configUse when designing, reviewing, or changing SQLFluff rules and configuration policy for a SQL or dbt-style project.sqlfluff-safe-fixUse when formatting or fixing SQLFluff violations safely in SQL or dbt-style projects while minimizing risky rewrites.sqlfluff-template-debugUse when SQLFluff linting fails on Jinja or dbt-style templating and the rendered SQL or templater configuration must be diagnosed.
test-and-fixAutonomously run tests, analyze failures, and fix them for this dbt package (Postgres Jinja engine, nested integration_tests). Use make run-unit-tests and make run-integration-tests from the repo root unless the user specifies otherwise.dbt-version-upgradeBump supported dbt-core versions in this package—update pyproject.toml dependency groups, noxfile_core.py session matrix, GitHub Actions CI matrix, and dbt_project.yml requires-dbt-version. Use when adding support for a new dbt-core minor release or dropping…implement-dbt-macroImplement or refactor dbt Jinja macros for macro-first dbt packages (e.g. dbt-package-template with Postgres/DuckDB, ubie-oss/dbt-data-privacy). Document public macros for dbt docs in macros/properties.yml. Use when adding adapter-dispatched macros, codegen…implement-dbt-macro-unit-testAdd or update macro-runner unit tests in nested integration_tests projects (mirrored paths under macros/tests/ in dbt-package-template), test_<macro>() files, aggregator registration, and verification via make run-unit-tests or dbt run-operation. Use when…implement-dbt-package-featureImplement or extend features in a macro-first dbt package (e.g. dbt-package-template), including public macro surfaces, docs, nested integration_tests, and verification via make run-unit-tests / make run-integration-tests. Use when a change spans more than a…initialize-dbt-packageRename the dbt package identity after copying dbt-package-template—dbt_project.yml name, adapter.dispatch macro_namespace, Jinja refs, integration_tests project, Docker/CI defaults, docs, and skill examples. Use when forking the template, initializing a new…