branch-context
>
dedupe
Use when consolidating overlapping instruction files, auditing skills for duplicated guidance, or pruning paraphrased prose across a markdown corpus. Triggers: 'dedupe these skills', 'dedupe these instructions', 'find duplicate instructions', 'consolidate instruction files', 'find paraphrased prose', 'collapse redundant skills', 'are these saying the same thing'.
develop
|
design-exploration
Use when exploring design approaches, evaluating alternatives, or making architectural decisions. Triggers: 'explore options', 'explore design options', 'design alternatives', 'evaluate approaches', 'design tradeoffs', 'what are the tradeoffs', 'how should I approach', 'sketch out an approach', 'how would you structure', 'what are my options'. Also invoked by develop when design decisions are needed.
adversarial-review
Use when dispatching a subagent to re-check work against external feedback (PR review comments, audit findings, multi-comment review cycles, 'did I really address X' verifications). Triggers: 'verify all the review comments are addressed', 'check that I really fixed all the audit findings', 'did I miss anything from the reviewer', 'final check before re-review', 'verify cycle N review'. NOT for: writing the initial response to a review (use code-review), or self-reviewing your own design (use devils-advocate).
agent2agent
Use when the user wants two or more Claude/agent sessions to talk to each other via the filesystem. Triggers: 'your name for inter-agent chat is X', 'your a2a name is X', 'listen for messages', 'open as X', 'talk to the session named Y', 'send a message to session Y', 'check the inbox', 'reply to that session', 'inter-agent chat', 'agent2agent', 'a2a', 'agent bus', 'ask session Y'. NOT for: dispatching subagents within one session (use the Task tool), or pub-sub between non-Claude processes (use a real broker like Redis).
deckset-presentation-expert
Expert assistant for creating Deckset presentations with markdown. Helps with slide formatting, headings, lists, images, videos, presenter notes, build steps, themes, and configuration. Use when working with .md presentation files, or when user mentions Deckset, creating slides, presentations, or decks.
file-organizer
Intelligently organizes files and directories by type, project, date, or custom criteria
api-tester
Makes HTTP requests to any URL and returns the response (supports GET, POST, PUT, PATCH, DELETE)
code-review
Reviews code for best practices, bugs, security issues, and provides improvement suggestions
git-helper
Assists with git workflows, commit messages, branch strategies, and resolving common git issues
streaming-output
>
streaming-output-mcp
>
problem-definition
Guide RCCA/8D problem definition using 5W2H and IS/IS NOT analysis. Transforms scattered failure data into precise, measurable problem statements that bound investigation scope without embedding cause or solution. Use when defining problems for root cause analysis, writing D2 sections of 8D reports, analyzing nonconformances, investigating failures, or when user mentions problem definition, problem statement, RCCA, 8D, failure analysis, or corrective action.
plugin-creator
Creates plugins (skills and MCPs) by guiding through the authoring process. Use when users want to create or update (1) skills that extend Claude's capabilities with specialized knowledge and workflows, or (2) MCPs (Model Context Protocol servers) that provide tools for Claude Desktop.
speckit-generator
>
specification-refiner
>
fault-tree-analysis
Conduct Fault Tree Analysis (FTA) to systematically identify and analyze causes of system failures using Boolean logic gates. Top-down deductive method for safety and reliability engineering. Use when analyzing system failures, evaluating safety-critical designs, calculating failure probabilities, identifying minimal cut sets, assessing redundancy effectiveness, or when user mentions "fault tree", "FTA", "system failure analysis", "minimal cut sets", "safety analysis", "failure probability", "AND/OR gates", or needs to trace failure pathways from top event to basic events. Supports qualitative structure analysis and quantitative probability calculations.
fishbone-diagram
Create comprehensive Fishbone (Ishikawa/Cause-and-Effect) diagrams for structured root cause brainstorming. Guides teams through problem definition, category selection (6Ms, 8Ps, 4Ss, or custom), cause identification, sub-cause drilling, prioritization via multi-voting, and 5 Whys integration. Generates visual SVG diagrams and professional HTML reports. Use when brainstorming potential causes, conducting root cause analysis, facilitating quality improvement sessions, analyzing defects or failures, structuring team problem-solving, or when user mentions "fishbone", "Ishikawa", "cause and effect diagram", "6Ms", "cause analysis", or "brainstorming causes".
skill-tester
This skill should be used whenever the user wants to test a skill's behavior, analyze how it uses the Claude API, inspect inputs/outputs from scripts, or run security and code review audits against skill scripts. Even for casual phrases like "test my skill", "analyze this skill", "audit skill scripts", "review skill for security issues", "what does this skill actually do when it runs", "inspect API calls from skill", "run a skill through its paces", "check my skill for bugs or vulnerabilities". Also trigger when the user shows you a SKILL.md and asks you to evaluate, critique, or stress-test it.
research-opportunity-investigator
Conduct systematic research and opportunity investigation for ACP protocol integration, collaboration, and enhancement opportunities. Use when the user wants to research external projects, protocols, or tools for potential collaboration; investigate gap-filling opportunities for IDE integrations; assess compatibility between ACP and external protocols; or identify opportunities for ACP adoption. Guides through discovery, analysis, validation, and RFC generation with mandatory gates and source grounding. Outputs include comprehensive summary documents, gap analyses, and formal RFC proposals.
rcca-master
Orchestrate complete Root Cause and Corrective Action (RCCA) investigations using the 8D methodology. Guides team formation (D1) with domain-specific recommendations, problem definition (D2), containment (D3), root cause analysis (D4) with integrated tool selection (5 Whys, Fishbone, Pareto, Kepner-Tregoe, FTA), corrective action (D5-D6), prevention (D7), and closure (D8). Use when conducting RCCA, 8D, root cause analysis, corrective action, failure investigation, nonconformance analysis, quality problems, or customer complaints.
five-whys-analysis
Conduct rigorous 5 Whys root cause analysis with guided questioning, quality scoring, and professional report generation. Use when performing root cause analysis, investigating problems, conducting 5 Whys sessions, troubleshooting recurring issues, or when user mentions "5 whys", "root cause", "why did this happen", "find the cause", or needs to identify underlying causes of defects, failures, or process problems. Includes validation tests, scoring rubric, and countermeasure development.
trade-study-analysis
Conduct systematic trade study analyses using the DAU 9-Step Trade Study Process. Guides engineers through problem definition, root cause analysis (5 Whys, Fishbone), data collection from alternatives and datasheets, normalization calculations, weighted scoring, sensitivity analysis, and professional report generation with visualizations and decision matrices. Use when evaluating alternatives, comparing solutions, conducting trade-offs, or making engineering decisions.
system-dev
>
fmea-analysis
Conduct Failure Mode and Effects Analysis (FMEA) for systematic identification and risk assessment of potential failures in designs, processes, or systems. Supports DFMEA (Design), PFMEA (Process), and FMEA-MSR (Monitoring & System Response). Uses AIAG-VDA 7-step methodology with Action Priority (AP) risk assessment replacing traditional RPN. Use when analyzing product designs for potential failures, evaluating manufacturing process risks, conducting proactive risk assessment, preparing for APQP/PPAP submissions, investigating field failures, or when user mentions "FMEA", "failure mode", "DFMEA", "PFMEA", "severity occurrence detection", "RPN", "Action Priority", "design risk analysis", or needs to identify and prioritize potential failure modes with their causes and effects.
kepner-tregoe-analysis
Conduct Kepner-Tregoe (KT) Problem Solving and Decision Making (PSDM) analysis using the four rational processes - Situation Appraisal, Problem Analysis, Decision Analysis, and Potential Problem Analysis. Use when performing structured root cause analysis, making complex decisions, evaluating alternatives with weighted criteria, conducting IS/IS NOT specification analysis, anticipating implementation risks, troubleshooting complex issues, or when user mentions "Kepner-Tregoe", "KT method", "IS/IS NOT", "situation appraisal", "decision analysis", "MUSTS and WANTS", "potential problem analysis", or needs systematic problem-solving methodology. Includes specification matrices, decision scoring, quality rubrics, and professional report generation.
pareto-analysis
Conduct Pareto Analysis (80/20 Rule) to identify the vital few causes driving the majority of problems. Guides data collection, category definition, chart creation, cumulative percentage calculation, and prioritization. Generates professional Pareto charts (SVG) and HTML reports with quality scoring. Use when prioritizing defects, complaints, failures, or improvement opportunities; when user mentions "Pareto", "80/20 rule", "vital few", "trivial many", "prioritization", or needs to identify which factors contribute most to a problem.
documentation-architect
>
requirements-dev
This skill should be used when the user asks to "develop requirements", "formalize needs", "write requirements", "create a specification", "build traceability", "quality check requirements", "INCOSE requirements", "requirements development", "reqdev", or mentions requirements engineering, needs formalization, verification planning, traceability matrix, or systems engineering requirements. Even for casual phrases like "I need to write some reqs" or "let's formalize the needs", trigger this skill.
concept-dev
This skill should be used when the user asks to "develop a concept", "explore a new idea", "brainstorm a system concept", "do concept development", "create a concept document", "run Phase A", "define the problem and architecture", or mentions concept exploration, feasibility studies, concept of operations, system concept, architecture exploration, solution landscape, or NASA Phase A.
interview
Interview users in-depth about their plans using probing, non-obvious questions. Use when user says "/interview", "interview me", "question my plan", "probe my idea", "challenge my assumptions", or wants deep exploration of a plan before implementation.
humanizer
|
diataxis-documentation
Write comprehensive, user-focused documentation following the Diataxis framework. Use this skill when creating or improving tutorials, how-to guides, reference documentation, or explanatory content. Helps identify the right documentation type and apply best practices for each.
git-commit
Create logically grouped, atomic git commits with well-formatted commit messages following best practices. Use when user says "/commit", "commit changes", "create commits", asks about conventional commits format, needs to split changes into multiple commits, or wants help with git add -p partial staging.
kubernetes
Comprehensive Kubernetes (k8s) cluster management skill. Use when working with kubectl, Helm, kustomize, pods, deployments, services, configmaps, secrets, or any Kubernetes operations. Triggers on "k8s", "kubectl get", "helm install", "debug pod", "scale deployment", or cluster troubleshooting questions.
repo-explore
Clone and explore external GitHub repositories to understand how libraries, frameworks, or dependencies work. Use when user provides a GitHub URL (github.com/owner/repo), asks "how does X library work", wants to look at source code for a dependency, asks about implementation details of an external package, or says "explore", "look at", or "check out" a repository. Automatically checks out the matching version tag when the repo is a dependency in the current project.
ultraloop
Use a relentless combination of loops, sub-agents, and ultracode workflows to iteratively refine, simplify, and iterate towards an objective. You are interested in speed of light implementations, achieving your goals in the absolute smallest amount of changes possible.
technical-writing
Write clear instructional and reference prose in the style of Simplified Technical English. Use when authoring or editing a runbook, procedure, step-by-step guide, README, API reference, configuration reference, troubleshooting guide, migration guide, release notes, architecture decision record, or a long pull request description, meaning anything a reader follows or looks facts up in. Covers imperative steps, condition-before-command order, consistent terminology, noun stacks, list structure, and warnings on destructive steps. Use diataxis-documentation to choose which document type to write, and humanizer for narrative or essay prose.
gh-stack
>
novel-creator
|
design-research
Conducts user experience research and analysis to inform design decisions. Use when user says "user research", "persona", "personas", "who are our users", "target audience", "customer segments", "design principles", "user needs", "pain points", "jobs to be done", "JTBD", "user interviews", "discussion guide", "research plan", "competitive analysis", "understand the users", "user data", "analytics review", "component research", "pattern audit", "accessibility requirements for [component]", or "how do others design [component type]". Reviews first-party and third-party user data, analyzes industry trends from UX and visual design perspectives, and plans user research studies. Also conducts component-level research: auditing existing patterns, accessibility requirements, interaction best practices, and content structure analysis to inform component design within an existing design system. Creates personas, customer segments, design principles, design roadmaps, research discussion guides, and component research audits. Do NOT use when already have approved personas, in implementation/coding phase, need visual mockups (use design-concepts), or designing components (use design-components).
design-concepts
Creates conceptual designs that illustrate design strategy and approach. Use when user says "mockup", "wireframe", "concept", "mood board", "visual direction", "design options", "explore designs", "UI design", "prototype", "design this", "show me designs", "create a design", "look and feel", or "design variations". Leverages research insights and design briefs to develop UI concepts, mood boards, and interactive prototypes. Do NOT use when user needs to understand users first (use design-research), or is writing code.
design-components
Designs components and sections within an existing design system. Creates 3 composition variations that use the project's actual tokens, colors, typography, and component primitives. Use when user says "design a component", "component variations", "design a card", "design a hero", "design a section", "component options", "design within our system", "new component", "component concept", or wants to explore how a component could look using their existing design system. Also use when designing larger composed sections (dashboards, settings pages, feature panels) that build on existing primitives. Do NOT use when the project has no design system yet (use design-system-init), or when exploring entirely new visual directions (use design-concepts).
temporal-pipelines
Create, edit, run, and debug Temporal workflow pipelines — pure Python Temporal workflows (with fan-out/fan-in, child workflows, signals, reusable activities) authored via `improvado-pipeline-sdk` and executed through the Workflow Manager API. Use when user asks about Temporal pipelines, Temporal workflow pipelines, `@workflow.defn`, tenant workflows, scheduled Temporal pipelines, or the `pipeline_sdk` / `improvado-pipeline-sdk`.
sql-import
SQL import workflow - connect to MySQL/Postgres/MSSQL, pick a table or write a custom query, discover schema, preview rows, and create a scheduled extract
secure-agents
30-second basic security check for AI agents. Three plain checks any non-engineer can run — leaked credentials, prompt injection sinks, missing audit trail. Marketing-friendly report, no jargon, no false-positive noise. Works on Claude Code, Cursor, Cline, Codex, custom Python/TS agents. Triggers on "secure agents", "agent audit", "check my agent", "AI security check", or "АУДИТ", or after seeing the "If you don't give your team safe agents, they'll build unsafe ones" LinkedIn post.
recipe-qa-rules
Full data QA flow for a recipe view — discovers pipeline topology, manages QA Requirements Documents (QRDs), runs hardcoded and QRD-defined quality checks, detects JOIN fan-outs, and resolves issues with user approval.
google-meet-manager
Manage Google Meet recordings, transcripts, and Gemini Notes from Google Drive. Use when user says 'list recordings', 'find recording', 'meeting transcript', 'meeting summary', 'Gemini notes', 'show recording', 'recording from [date]', 'what meetings were recorded', 'записи встреч', 'транскрипт встречи', 'саммари встречи'.
mdg-create-and-edit
Create, edit, and manage rules -- data governance rules, compliance rules, monitoring rules, alerts, MDG rules. Use when user asks to create a rule, set up alerts, or monitor metrics.
Page 1104 of 1712 · 85559 results
