Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Testing & quality
Use when the user asks to "improve a metric", "run labs", "leave feedback on a metric", "add to labs", "fix metric accuracy", "review metric results", "find misaligned metrics", or "iterate on metric quality". Covers the metric improvement cycle, the feedback workflow, and the labs pipeline used to refine metric accuracy over time.
Use when the user asks "what predefined metrics are available", "which built-in metrics should I use", "what does CSAT measure", "how does hallucination detection work", "what's the difference between Interruption Score and AI Interrupting User", "which metrics are free", "which metrics need audio", "configure silence threshold", "set up sentiment metric", or any question about Cekura's out-of-the-box metrics. Covers the full catalog of predefined metrics — what each does, costs, constraints, configuration options, and when to use each one.
Generates structured scaffolds (frameworks, checklists, templates) for technical work — TDD test suites, exploratory data analysis plans, statistical analysis designs, causal vs predictive modeling objectives, and validation checklists. Use when starting technical work that needs systematic planning before execution. Invoke when user mentions "write tests for", "explore this dataset", "analyze", "model", "validate", "design an A/B test", or when technical work needs scaffolding before execution.
Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does the code follow this repo's documented coding standards?) and Spec (does the code match what the originating issue/spec asked for?). Runs both reviews in parallel sub-agents and reports them side by side. Use when the user wants to review a branch, a PR, work-in-progress changes, or asks to "review since X".
Find the mistakes agents keep repeating in this repo and make each one impossible. Try architecture first, then types, then a lint whose error names the fix, then a test, and write docs last. Prove each check fails on a real past mistake. Repeat this each time the operator corrects you. Use for /correct.
Interactive debugging mode that generates hypotheses, instruments code with runtime logs, and iteratively fixes bugs via autonomous reproduce-analyze loops, with human help only as a fallback. Only for hard-to-diagnose bugs; in those cases, remind the user that debug-mode is available, and never proactively activate this skill
Production Python coding standards with automatic version detection (3.10-3.13). Use when writing, reviewing, or refactoring Python to ensure adherence to modern type syntax, LBYL exception handling, pathlib operations, ABC-based interfaces, and production-tested patterns. Not Dagster-specific - applies to any Python project.
Implements feature tasks by loading the project skills relevant to the task, reading PRD/TechSpec context, analyzing dependencies, executing the implementation with tests, and performing an automatic code review. Marks tasks as complete in tasks.md. Use when the user asks to implement a task, execute a task, or start working on a specific task number. Do not use for creating tasks, running QA, or bug fixing.
Review skills in any project using a dual-axis method: (1) deterministic code-based checks (structure, scripts, tests, execution safety) and (2) LLM deep review findings. Use when you need reproducible quality scoring for `skills/*/SKILL.md`, want to gate merges with a score threshold (for example 90+), or need concrete improvement items for low-scoring skills. Works across projects via --project-root
Rules and patterns for writing reliable Effector code and fixing bugs (events/stores/effects, sample flow control, models/factories, SSR/scopes, tests, debugging, linting). Use when implementing or reviewing Effector logic, migrating away from component state, or diagnosing Effector issues.
Verify that a developer-run feature behaved correctly by analyzing HTTP traffic captured by Fiddler Everywhere. Always use this skill when a developer asks whether their feature's HTTP calls completed correctly, wants to see what requests a feature made, needs to debug a failed API call, is checking traffic after running a feature, wants to confirm what each endpoint returned, or asks whether anything in the traffic looks wrong — even if they don't use the word "verify" or "Fiddler". Summarizes the capture by endpoint and flags likely issues such as failed calls, missing follow-up requests, retries, auth failures, timeouts, and suspicious status-code patterns. Requires Fiddler Everywhere to be running with its MCP server enabled.
Invoke when the user asks about accessibility, inclusive design, colorblind mode, remappable controls, screen reader support, EAA compliance, CVAA, difficulty options, motor accommodations, or one-handed mode. Triggers on: "accessibility", "inclusive design", "colorblind", "remappable controls", "screen reader", "EAA", "CVAA", "difficulty options", "motor accommodation", "one-handed". Do NOT invoke for general UX design (use game-ux-designer) or art direction (use game-art-director). Part of the AlterLab GameForge collection.
Structural analysis through dynamically generated cognitive lenses. Generates the optimal analytical lens for the specific code/artifact, then executes it. Finds conservation laws, structural invariants, and concrete bugs that vanilla analysis misses. Use on any code file, system design, or text artifact.
James Bach's HTSM Product Factors (SFDIPOT) analysis for comprehensive test strategy generation. Use when analyzing requirements, epics, or user stories to generate prioritized test ideas across Structure, Function, Data, Interfaces, Platform, Operations, and Time dimensions.
Evidence-based investigative code review using deductive reasoning to determine what actually happened versus what was claimed. Use when verifying implementation claims, investigating bugs, validating fixes, or conducting root cause analysis. Elementary approach to finding truth through systematic observation.
Advanced visual regression testing with pixel-perfect comparison, AI-powered diff analysis, responsive design validation, and cross-browser visual consistency. Use when detecting UI regressions, validating designs, or ensuring visual consistency
Review responsive and flexible layout for accessibility across devices, zoom levels, and orientations. Chains: responsive-accessibility, flexible-typography, information-density. Use when testing an existing interface across screen sizes and zoom levels for accessibility.
Use when reviewing/judging a finished whole-system architecture document (+ its linked ADR files) to decide if an engineer can grasp the system and place a feature's TDD within it — an acceptance gate, not authoring. Judges a single-sourced 10-condition bar: boundary + external deps + concerns; components single-responsibility at whole-system altitude (not api-spec/data-model or feature-TDD detail); diagrams ⇄ narrative agree; every significant decision a standalone LINKED, immutable ADR (one per file, index in sync, supersede not edit); decisions traced + justified; NFR targets realized + tradeoffs named; cross-cutting (resilience/security/privacy/observability) addressed; ASRs covered; nothing fabricated, claims consistent with the code; amend delta-scoped. C4/arc42/ATAM/4+1 are aids judged by outcome. Emits exactly `VERDICT: approve|revise` (no false-revise on a thin doc). Not for authoring, the PRD, api-spec/data-model, a feature's TDD, or generic design docs/RFCs/standalone-ADRs (use design-review)
Validate a Salla app on a real demo store before calling it done. Use when verifying an app end to end before publish. Install via salla_apps action=demo_stores, then verify the settings form actually SAVES, the embedded dashboard authenticates, the storefront snippet renders, and webhooks / App Functions fire from real Salla events. MCP/config success and passing endpoint tests are NOT proof the integration works — this is the live gate. Build flow → salla-app-builder; storefront UI → salla-storefront-ui; embedded UI → salla-embedded-ui.
Review Sentry Python and Django changes for bug patterns drawn from real production issues. Use when reviewing a backend diff or PR, checking Warden findings, auditing the current branch, reviewing production-error patterns, or looking for common regressions in `src/` and `tests/`.
Use when you need to audit, evaluate, govern, safely retire, or transactionally upgrade locally installed or distributed agent skills. Triggers include skill sprawl, stale, broken, or conflicting skills, local cleanup or quarantine, managed physical collections, pre-migration review, and periodic inventory checks.
Validate multi-skill workflows defined in CLAUDE.md by checking skill existence, inter-skill data contracts (JSON schema compatibility), file naming conventions, and handoff integrity. Use when adding new workflows, modifying skill outputs, or verifying pipeline health before release.
Design and run a Spec-Driven Development (SDD) pipeline for AI software factories — where structured specifications are the input, AI agents generate the code, and quality gates enforce correctness at each phase: SPECIFY → DECOMPOSE → IMPLEMENT → VERIFY → DELIVER. Use when building or refining a spec-driven pipeline any AI coding tool (Claude Code, Cursor, Hermes Agent, Devin, OpenHands, droid) can follow, or when you need spec quality gates, phase-gate verdicts, NFR encoding, or format translation. Do not use for a single small change with a clear goal (classify first via bmad), for the control-plane protocol of intent contracts, autonomy gating, and failure routing around a pipeline (bmad), or for unvalidated problems (product-discovery).
Storybook story-writing and CSF 3.0 best practices skill. Use when: (1) writing new story files (.stories.tsx, .stories.ts); (2) editing existing stories; (3) configuring Args, Decorators, Parameters; (4) working with Storybook configuration files (.storybook/); (5) tasks include keywords such as “story,” “stories,” “storybook,” or “CSF”
Technical Lead that implements code ONE FILE AT A TIME to prevent crashes. Handles code review, best practices, mentorship, implementation planning. **CRITICAL CHUNKING RULE - Large implementations (auth system = auth.ts + tests + middleware) done incrementally.** Activates for tech lead, code review, best practices, refactoring, technical debt, code quality, design patterns, SOLID principles, clean code, code standards, implementation plan, technical guidance, mentorship, code optimization, complexity analysis, technical planning, estimation, implementation strategy, code architecture.
Use when the user needs user research methodologies, persona development, journey mapping, usability testing plans, or information architecture analysis. Triggers: user says "user research", "persona", "journey map", "usability test", "card sort", "heuristic evaluation", "information architecture", "user interview", understanding user behavior.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.