laurigates/claude-plugins
50 skills · 1,181 total installs
$npx skills add laurigates/claude-pluginsSkillInstalls
api-testingHTTP API testing with Supertest (TS) and httpx/pytest (Python).design-tokensDesign tokens and CSS custom properties: theme systems, dark mode, component libraries.custom-agent-definitionsWrite and configure custom agent definitions in Claude Code agents/ directory.accessibility-implementationWCAG 2.1/2.2 compliance, ARIA patterns, keyboard nav, focus management, a11y testing.blueprint-claude-mdGenerate or update CLAUDE.md from blueprint artifacts. Use when adding team instructions, converting inline content to @imports, or setting up CLAUDE.local.md.blueprint-derive-rulesDerive Claude rules from git commit history. Use when extracting implicit decisions from commits or codifying code-style, testing, and API-design rules.blueprint-developmentGenerate project-specific rules from PRDs for Blueprint Development. Use when generating architecture, testing, or quality rules from requirements documents.blueprint-feature-tracker-syncSync feature tracker with TODO.md, taskwarrior sidecars, and PRDs. Use when reconciling TODO.md vs tracker, draining WO entries, or recalculating stats.meta-auditAudit Claude subagent configs for completeness, security, and best practices.blueprint-adr-listList ADRs as a markdown table with title, status, date, domain. Use when generating an ADR index, auditing ADR status, or reviewing all architecture decisions.blueprint-feature-tracker-statusDisplay feature tracker stats, phase progress, and completion summary.blueprint-derive-plansDerive PRDs, ADRs, PRPs from git history, docs, and codebase. Use when onboarding a project to blueprint, generating a PRD or ADRs retroactively, or extracting…blueprint-docs-listList blueprint documents (ADRs, PRDs, PRPs) with frontmatter metadata.agents-analyzeAudit plugins for sub-agent opportunities — verbose skills, coverage gaps, over-permissions.blueprint-curate-docsCurate library gotchas and project patterns into .claude/rules/ entries for AI context. Use when documenting library knowledge for PRP reuse.blueprint-adr-validateValidate ADR relationships, domain consistency, and duplicate ADR numbers.blueprint-executeBlueprint meta command: determine and execute the next logical action.meta-assimilateCopy, generalize, or merge a project's .claude/{agents,commands} into user-scoped configuration.bevy-ecs-patternsAdvanced Bevy ECS: complex queries, system scheduling, change detection, and performance tuning.bevy-game-engineBevy game engine: ECS, rendering, input, and asset management.adr-relationshipsDomain analysis, conflict detection, and relationship validation for Architecture Decision Records. Use when creating or validating ADRs to ensure consistency.adversarial-reviewAdversarial second-pass review that tries to break code, designs, plans, or ADRs. Use when stakes are high and a normal review already ran.agent-teamsConfigure Claude Code agent teams (implicit team, SendMessage, TaskUpdate).blog-postCreate a blog post via guided prompts with git context auto-populated. Use when writing a quick update, retrospective, tutorial, deep dive, or devlog entry.blog-post-writingStyle guide for technical blog posts — updates, retrospectives, tutorials, deep dives.blueprint-autonomy-level3Install blueprint autonomy level 3 (ADR-0020): scheduled-autorun + approved-work-order-execution GitHub workflows.blueprint-autopilotRun due blueprint maintenance ambiently at autonomy level 2+. Use when a drift nudge reports blueprint tasks due or suggests /blueprint:autopilot.blueprint-derive-testsDerive test regression plans from git history by finding commits lacking tests.blueprint-docs-currencyEnforce same-commit landing of code and docs (APIs, formats, ADRs).cc-only-skillConfigure Claude Code hooks in settings.json. Use when authoring PreToolUse hooks.cold-read-gateGate outward-bound text (upstream issues, docs, PR bodies) through isolated haiku fresh-reader critique before publishing.docs-refreshRefresh plugin catalog docs (README, PLUGIN-MAP, d2 diagram) so per-plugin skill/agent counts match disk. Use when fixing count drift or after adding skills.exclusive-lock-dispatchPre-dump-then-dispatch for tools holding an exclusive lock (Ghidra, migrations, single-writer caches).execution-grounded-reviewExecution-grounded review: run tests first, trace each acceptance criterion to execution evidence. Use when verifying an implementation meets spec.expose-tunable-knobExpose a live-adjustable control instead of guessing a magic constant for a parameter the agent cannot itself perceive.folded-descriptionRender architecture diagrams from text sources. Use when documenting system topology.mcp-code-executionScaffold the code execution pattern for MCP-based agents. Use when agents call many MCP tools, intermediate data exceeds context, you need loops, or PII must…mcp-managementInstall and configure MCP servers for Claude Code. Use when adding/enabling servers, updating .mcp.json, managing OAuth remote servers, or troubleshooting…mcp-server-authoringFastMCP authoring for Python MCP servers — tools, resources, prompts, TDD, release-please.meta-context-dietAudit CLAUDE.md and .claude/rules for always-loaded content that should become an on-demand skill.meta-promotePromote rules, skills, or agents from project scope to parent or user-global scope.multi-model-delegationMulti-model design consults via PAL (kimi, glm, gemini, gpt). Use when asking other models to brainstorm a design or reconciling their split answers.no-descriptionno-nameInspect JSON payloads and extract nested fields. Use when parsing API responses.normal-skillCommit staged changes with a conventional message. Use when saving work to git history.parallel-agent-dispatchDispatch contract for spawning parallel agents covering worktree collisions, scope overflow, and silent exits.plugin-settingsConfigure per-project plugin settings via .claude/plugin-name.local.md files.quoted-descriptionDebug HTTP APIs: trace requests, inspect headers. Use when a request fails: check status first.verify-before-planVerify orchestrator premises (file counts, build state, artefact presence) before dispatching parallel subagents.wave-based-dispatchSequential-wave dispatch for WO chains where output of one feeds the next, shared locks, or shared files prevent fan-out.