neolabhq/context-engineering-kit
106 skills · 70,208 total installs
$npx skills add neolabhq/context-engineering-kitSkillInstalls
prompt-engineeringUse this skill when you writing commands, hooks, skills for Agent, or prompts for sub agents or any other LLM interaction, including optimizing prompts, improving LLM outputs, or designing production thought-based-reasoningUse when tackling complex reasoning tasks requiring step-by-step logic, multi-step arithmetic, commonsense reasoning, symbolic manipulation, or problems where simple prompting fails - provides comprehreflectReflect on previus response and output, based on Self-refinement framework for iterative improvement with complexity triage and verificationupdate-docsUpdate and maintain project documentation for local code changes using multi-agent workflow with tech-writer agents. Covers docs/, READMEs, JSDoc, and API documentation.brainstormUse when creating or developing, before writing code or implementation plans - refines rough ideas into fully-formed designs through collaborative questioning, alternative exploration, and incrementalmulti-agent-patternsDesign multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.subagent-driven-developmentUse when executing implementation plans with independent tasks in the current session or facing 3+ independent issues that can be investigated without shared state or dependencies - dispatches fresh scritiqueComprehensive multi-perspective review using specialized judges with debate and consensus buildingmemorizeCurates insights from reflections and critiques into CLAUDE.md using Agentic Context EngineeringkaizenUse when Code implementation and refactoring, architecturing or designing systems, process and workflow improvements, error handling and validation. Provide tehniquest to avoid over-engineering and aproot-cause-tracingUse when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identifjudge-with-debateEvaluate solutions through multi-round debate between independent judges until consensusplan-taskHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.write-conciselyApply writing rules to any documentation that humans will read. Makes your writing clearer, stronger, and more professional.agent-evaluationEvaluate and improve Claude Code commands, skills, and agents. Use when testing prompt effectiveness, validating context engineering choices, or measuring improvement quality.implement-taskHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.do-in-parallelRun independent tasks concurrently across multiple files or targets using parallel sub-agents, with per-task model selection and LLM-as-a-judge verification. Use when tasks do not depend on each otherdo-in-stepsExecute one complex task as ordered, dependent steps run sequentially, passing context from each step to the next, with per-step LLM-as-a-judge verification. Use when later steps depend on the resultsadd-taskcreates draft task file in .specs/tasks/draft/ with original user intentanalyseAuto-selects best Kaizen method (Gemba Walk, Value Stream, or Muda) for targetlaunch-sub-agentLaunch an intelligent sub-agent with automatic model selection based on task complexity, specialized agent matching, Zero-shot CoT reasoning, and mandatory self-critique verificationreview-local-changesReview your local uncommitted working-tree changes (git diff plus untracked files) and return actionable improvement suggestions. Use before committing, when nothing has been pushed yet.analyse-problemComprehensive A3 one-page problem analysis with root cause and action plancreate-ideasHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.setup-serena-mcpGuide for setup Serena MCP server for semantic code retrieval and editing capabilitieswhyIterative Five Whys root cause analysis drilling from symptoms to fundamentalsfix-testsHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.write-testsHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.commitCreate well-formatted commits with conventional commit messages and emojido-and-judgeExecute a task with sub-agent implementation and LLM-as-a-judge verification with automatic retry loopjudgeLaunch a meta-judge then a judge sub-agent to evaluate results produced in the current conversationtree-of-thoughtsExecute tasks through systematic exploration, pruning, and expansion using Tree of Thoughts methodology with meta-judge evaluation specifications and multi-agent evaluationdo-competitivelyExecute tasks through competitive multi-agent generation, meta-judge evaluation specification, multi-judge evaluation, and evidence-based synthesistest-skillUse when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline witest-promptUse when creating or editing any prompt (commands, hooks, skills, subagent instructions) to verify it produces desired behavior - applies RED-GREEN-REFACTOR cycle to prompt engineering using subagentscreate-ruleUse when found gap or repetative issue, that produced by you or implemenataion agent. Esentially use it each time when you say "You absolutly right, I should have done it differently." -> need create analyze-issueAnalyze a GitHub issue and create a detailed technical specificationapply-anthropic-skill-best-practicesComprehensive guide for skill development based on Anthropic's official best practices - use for complex skills requiring detailed structureactualizeReconcile the project's FPF state with recent repository changesplan-do-check-actIterative PDCA cycle for systematic experimentation and continuous improvementreview-prReview an existing GitHub pull request and post inline review comments on its diff. Use when the changes are on an opened PR rather than your local working tree.cause-and-effectSystematic Fishbone analysis exploring problem causes across six categoriescreate-prCreate pull requests using GitHub CLI with proper templates and formattingattach-review-to-prAdd line-specific review comments to pull requests using GitHub CLI APIcreate-agentComprehensive guide for creating Claude Code agents with proper structure, triggering conditions, system prompts, and validation - combines official Anthropic best practices with proven patternscreate-commandInteractive assistant for creating new Claude commands with proper structure, patterns, and MCP tool integrationgit-worktreesUse when working on multiple branches simultaneously, context switching without stashing, reviewing PRs while developing, testing in isolation, or comparing implementations across branches - provides propose-hypothesesExecute complete FPF cycle from hypothesis generation to decisionbuild-mcpGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate externaload-issuesLoad all open issues from GitHub and save them as markdown filesdecayManage evidence freshness by identifying stale decisions and providing governance actionsquerySearch the FPF knowledge base and display hypothesis details with assurance informationresetReset the FPF reasoning cycle to start freshsetup-codemap-cliGuide for setup Codemap CLI for intelligent codebase visualization and navigationstatusDisplay the current state of the FPF knowledge basecreate-workflow-commandCreate a workflow command that orchestrates multi-step execution through sub-agents with file-based task promptssetup-arxiv-mcpGuide for setup arXiv paper search MCP server using Docker MCPsetup-context7-mcpGuide for setup Context7 MCP server to load documentation for specific technologies.git-notesUse when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc - provides git notes commands ansdd:planHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sdd:implementHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.customaize-agent:prompt-engineeringHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.code-review:review-local-changesHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sdd:brainstormHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sdd:add-taskHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sdd:create-ideasHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.tdd:test-driven-developmentHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.docs:write-conciselyHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.reflexion:reflectHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.code-review:review-prHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.reflexion:critiqueHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.docs:update-docsHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.customaize-agent:context-engineeringHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.tdd:fix-testsHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.tdd:write-testsHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.customaize-agent:thought-based-reasoningHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.kaizen:root-cause-tracingHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sadd:subagent-driven-developmentHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.reflexion:memorizeHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.customaize-agent:create-skillHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.git:commitHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.kaizen:kaizenHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.customaize-agent:apply-anthropic-skill-best-practicesHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.ddd:setup-code-formatingHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.customaize-agent:agent-evaluationHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.git:create-prHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sadd:do-in-stepsHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sadd:tree-of-thoughtsHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sadd:judge-with-debateHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.git:worktreesHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.kaizen:analyse-problemHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.customaize-agent:test-skillHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.customaize-agent:test-promptHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.git:merge-worktreeHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.mcp:setup-serena-mcpHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.kaizen:analyseHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sadd:judgeHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sadd:launch-sub-agentHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.kaizen:plan-do-check-actHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.sadd:do-in-parallelHand-crafted Claude Code Skills focused on improving agent results quality. Compatible with OpenCode, Cursor, Antigravity, Gemini CLI, and others.context-engineeringUnderstand the components, mechanics, and constraints of context in agent systems. Use when writing, editing, or optimizing commands, skills, or sub-agents prompts.create-hookCreate and configure git hooks with intelligent project analysis, suggestions, and automated testingcreate-skillGuide for creating effective skills. This command should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workload-pr-commentsUse to load open/unresolved PR review comments then aggregate them as tasks in .specs/comments/*.md for parallel agents to fix.resolve-fixed-pr-commentsVerify what PR review comments have been addressed (committed/pushed OR uncommitted local changes) and resolve the threads that are genuinely fixed or no longer relevant.traiage-reviewThis skill should be used when need prioritize what changed code in repository human must review.