.fyi
SkillsMCPPluginsSubagents

Browse by category

DevOps & CI/CD SkillsProductivity & Workflow SkillsOther SkillsProduct & Project Management SkillsDocumentation & Knowledge SkillsCode Review & Refactor SkillsBackend & APIs SkillsAgent Meta & Communication SkillsResearch SkillsSecurity SkillsUX UI & Design SkillsTesting & QA SkillsSee all →

Every Claude Code skill, MCP server, plugin and subagent in one directory. Searchable, comparable, and one command from installed. Live stats from GitHub, npm and PyPI.

We're on Product HuntYour agent's app storeCheck it out →
Agent SkillsMCP ServersPluginsSubagentsCoding Agents
CollectionsOfficial publishersGlossaryFAQBlogSearchSavedFeedback
PrivacyTermsllms.txtSitemap

made with ♥ · © 2026 aaaa.fyi

Independent project · real data from public registries

…/obra/clank
home/skills/obra/clank
obra avatar

obra/clank

37 skills · 263 total installs

View on GitHub
$npx skills add obra/clank
SkillInstalls
reducing-complexityManaging complexity is software's primary technical imperative - all other goals are secondary12commenting-intentComment WHY code exists and non-obvious decisions, not WHAT code does (mechanics)10keeping-routines-focusedEach routine does one thing and does it well - extract when routines have multiple responsibilities10localizing-variablesDeclare variables in smallest possible scope, initialize close to first use, minimize span and live time10naming-variablesChoose names that fully and accurately describe what the variable represents10creating-skillsTDD for process documentation - test with subagents before writing, iterate until bulletproof9designing-before-codingDesign in pseudocode first, iterate approaches, then translate to code9dispatching-parallel-agentsUse multiple Claude agents to investigate and fix independent problems concurrently9encapsulating-complexityHide implementation details behind interfaces - work at domain level (what), not implementation level (how)9executing-plansExecute detailed plans in batches with review checkpoints9gardening-skills-wikiMaintain skills wiki health - check links, naming, cross-references, and coverage9maintaining-consistent-abstractionsClass interfaces present one cohesive abstraction - don't mix domain logic with serialization, persistence, or unrelated concerns9root-cause-tracingSystematically trace bugs backward through call stack to find original trigger9testing-skills-with-subagentsRED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes9validating-inputsCheck all external inputs for validity - garbage in, nothing out, never garbage out9writing-plansCreate detailed implementation plans with bite-sized tasks for engineers with zero codebase context9condition-based-waitingReplace arbitrary timeouts with condition polling for reliable async tests8exploring-alternativesTry 2-3 different approaches before implementing - don't settle for first design you think of8finishing-a-development-branchComplete feature development with structured options for merge, PR, or cleanup8refactoring-safelyRefactor with tests first, one change at a time, never mix refactoring with bug fixes or new features8remembering-conversationsSearch previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search8requesting-code-reviewDispatch code-reviewer subagent to review implementation against plan or requirements before proceeding8simplifying-control-flowFlatten nested conditionals with early returns or table-driven methods - keep nesting depth under 3 levels8single-purpose-variablesUse each variable for exactly one purpose - no hybrid coupling or hidden meanings8subagent-driven-developmentExecute implementation plan by dispatching fresh subagent for each task, with code review between tasks8systematic-debuggingFour-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.8testing-anti-patternsNever test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.8using-git-worktreesCreate isolated git worktrees with smart directory selection and safety verification8verification-before-completionRun verification commands and confirm output before claiming success8writing-evergreen-commentsWrite comments explaining WHAT and WHY, never temporal context or history8brainstormingInteractive idea refinement using Socratic method to develop fully-formed designs—defense-in-depthValidate at every layer data passes through to make bugs impossible—getting-startedSkills wiki intro - mandatory workflows, search tool, brainstorming triggers—installing-skillsFork, clone to ~/.clank, run installer, edit CLAUDE.md—naming-by-domainName code by what it does in the domain, not how it's implemented or its history—receiving-code-reviewReceive and act on code review feedback with technical rigor, not performative agreement or blind implementation—test-driven-developmentWrite the test first, watch it fail, write minimal code to pass—