mhylle/claude-skills-collection
38 skills
$npx skills add mhylle/claude-skills-collectionSkillInstalls
adrDocument architectural decisions in standardized ADR format. This skill should be used when making significant technical decisions, choosing between…adversarial-reviewerAdversarial code review that breaks the self-review monoculture by spawning three independent subagent personas (Saboteur, New Hire, Security Auditor) in…agent-creatorCreate composable AI agent systems in NestJS projects following the "tools all the way down" architecture.brainstormcode-quality-auditRun code quality audits covering test coverage, cyclomatic complexity, module sizes, dependency structure (cycles, fan-in/out), and mutation testing.code-reviewSystematic code review for implementation phases verifying architectural principles, framework standards, ADR compliance, and code quality.codebase-auditLong-running comprehensive adversarial audit of an entire codebase.codebase-researchOrchestrates comprehensive codebase research by decomposing user queries into parallel sub-agent tasks and synthesizing findings.context-saverWrite the current session's in-flight work state to a human-readable handoff doc on disk (docs/context/CONTEXT-{topic}.md) so a future chat session — or…continuous-learningPromote valuable session learnings into reusable, triggerable skill files in ~/.claude/skills/learned/.create-planCreate detailed implementation plans through interactive research and iteration.deep-brainstormMulti-session, resumable deep brainstorming with mindmap-on-disk structure.design-languageDesign and manufacture someone's OWN reusable visual design language and save it as durable files — design tokens (css/tokens.css + a W3C design-tokens.json),…e2e-testingComprehensive E2E testing skill using Playwright MCP for systematic web application testing.eval-harnessBuild evaluation harnesses for AI-assisted implementations — capability evals, regression tests, graders (exact-match, LLM-judge, code-exec, rubric), and…grumpy-reviewerA single grumpy, nitpicky structural code reviewer that runs as an isolated subagent and treats the code as third-party work submitted by a junior programmer…implement-phaseExecute a single phase from an implementation plan with all quality gates.implement-planOrchestrate the execution of complete implementation plans, delegating each phase to implement-phase skill.iterate-planUpdate existing implementation plans through user feedback with thorough research and validation.prompt-generatorGenerate implementation prompts for phase-based project execution using an orchestration pattern.security-reviewComprehensive security audit for code changes. Use this skill when implementing authentication, authorization, user input handling, API endpoints,…ship-issueOne-command issue-to-merge pipeline orchestrator. Drives a GitHub issue through nine stages (preflight, plan, implement, review, ci, cloud_review, deploy, e2e,…skill-visualizerGenerate interactive HTML visualizations of the skills collection, codebase structure, or dependency graphs.strategic-compactSuggest context compaction at optimal logical boundaries — between phases, after a research burst, after a debugging session ends — rather than waiting for the…team-brainstormAdversarial brainstorming using agent teams for multi-perspective analysis.team-create-planTeam-based implementation planning with adversarial design review.team-implement-planExecute implementation plans with a small review team (Implementer + Reviewer + optional Integrator).team-implement-plan-fullExecute implementation plans with a full team — one implementer per phase running in parallel where the dependency graph allows, plus a shared cross-phase…tt-brainstormTasktracker-native Socratic brainstorming. Refines a raw idea into a frozen brainstorm document tree stored in tasktracker (NOT in docs/brainstorms/*.md), with…tt-create-planTasktracker-native implementation planning. Turns a frozen brainstorm (or a clear requirement) into a phased plan persisted as tasktracker phase tasks — NOT as…tt-implement-phaseTasktracker-native per-phase executor. Runs a SINGLE phase whose scope and sub-tasks live as tasktracker phase + sub-task rows (NOT in a docs/plans/*.md file).tt-implement-planTasktracker-native plan orchestrator. Drives execution of a plan whose phases are stored as tasktracker phase tasks (NOT a docs/plans/*.md file).tt-workflow-auditTasktracker-native project-wide parallel audit using the Claude Code Workflow tool (dynamic workflows).tt-workflow-buildTasktracker-native trigger for a PARALLEL build via the Claude Code Workflow tool.tt-workflow-runTasktracker-native autonomous build-loop orchestrator. Drives a first-class `workflow_run` end-to-end — create the run (Gate 1 lifecycle completeness + Gate 2…user-storyGenerate hierarchical user stories (epics, features, tasks) with formal Given/When/Then acceptance criteria. Works from brainstorm output or standalone.verification-loopComprehensive 6-check verification framework for validating implementation quality across build, types, lint, tests, security, and diff review.workflow-guideRecommend which workflow mode fits the task at hand — solo (implement-plan), small team (team-implement-plan with Implementer + Reviewer), full team…