Discover and install skills, docs, and rules to enhance your AI agent's capabilities.
| Name | Contains | Score |
|---|---|---|
v1.2.21 Use whenever an Electron desktop app needs end-to-end tests, or a Spectron suite must be migrated: Playwright's _electron.launch, renderer windows as Pages, main-process checks via electronApp.evaluate, and IPC and DOM assertions from one suite. Contains: electron-playwright Use whenever an Electron desktop app needs end-to-end tests, or a Spectron suite must be migrated: Playwright's _electron.launch, renderer windows as Pages, main-process checks via electronApp.evaluate, and IPC and DOM assertions from one suite. | Skills | |
Use whenever data validation uses Great Expectations (GX Core) on Pandas, SQL or Spark: ExpectationSuites, ValidationDefinitions and Checkpoints, running validations on batches and reading the JSON result to gate CI. Contains: great-expectations Use whenever data validation uses Great Expectations (GX Core) on Pandas, SQL or Spark: ExpectationSuites, ValidationDefinitions and Checkpoints, running validations on batches and reading the JSON result to gate CI. | Skills | |
Use when a deploy should be blocked by any incompatible API contract across protocols. Combines Pact can-i-deploy, oasdiff for OpenAPI, graphql-inspector for GraphQL and buf breaking for Protobuf into one go/no-go CI step with severity thresholds and a reason per finding. Contains: contract-compatibility-gate Use when a deploy should be blocked by any incompatible API contract across protocols. Combines Pact can-i-deploy, oasdiff for OpenAPI, graphql-inspector for GraphQL and buf breaking for Protobuf into one go/no-go CI step with severity thresholds and a reason per finding. | Skills | |
Use when preparing for a SOC 2 Type II audit or any audit that needs evidence packages from automated tests: per-criterion artifacts (CC1-CC9 and optional categories), collection from CI, audit and access logs and change records, Vanta, Drata or Secureframe formats, and observation-period sampling. Contains: soc2-evidence-collector Use when preparing for a SOC 2 Type II audit or any audit that needs evidence packages from automated tests: per-criterion artifacts (CC1-CC9 and optional categories), collection from CI, audit and access logs and change records, Vanta, Drata or Secureframe formats, and observation-period sampling. | Skills | |
Use when cross-browser tests must run on a self-hosted Selenium Grid 4 for data residency or cost: standalone or hub-and-node, the Docker images, node registration, session queue tuning and observability. Managed grids are cloud-grid-e2e; choosing browsers is browser-matrix-strategy-reference. Contains: selenium-grid-4-runner Use when cross-browser tests must run on a self-hosted Selenium Grid 4 for data residency or cost: standalone or hub-and-node, the Docker images, node registration, session queue tuning and observability. Managed grids are cloud-grid-e2e; choosing browsers is browser-matrix-strategy-reference. | Skills | |
v1.1.11 Use when the code under test is a PowerShell script, function, cmdlet or CLI run from pwsh. Sets up Pester v5: Describe/Context/It blocks, Should assertions, Mock, setup hooks, tags, code coverage and NUnit/JUnit XML output for CI. Contains: pester-cli-testing Use when the code under test is a PowerShell script, function, cmdlet or CLI run from pwsh. Sets up Pester v5: Describe/Context/It blocks, Should assertions, Mock, setup hooks, tags, code coverage and NUnit/JUnit XML output for CI. | Skills | |
v0.1.1 Working reference for agents using the Tessl CLI — create and publish plugins/skills, install from the registry, update, lint, and run evals. Contains: tessl-agent Use when working with Tessl — publishing plugins or skills, installing from the registry, running evals, linting, bumping versions, running reviews, launching skills, managing workspaces, or any Tessl CLI or MCP operation. Triggers on: "publish this skill", "push to the registry", "create a tessl plugin", "install a skill", "run evals", "bump the version", "update the plugin", "lint the skill", "run a review", "launch a skill with an agent", "check tessl status", "what tessl tools are available". | Skills | |
The default Tessl review rubric. An agentic reviewer that reads a SKILL.md and scores it against rubrics for its description and its content, the same reviewer tessl review uses out of the box. Use it as the reference reviewer to score skills, or as the base to fork a custom rubric from. Contains: skill-reviewer Evaluate a SKILL.md for quality. An agent that dynamically discovers the rubric files and scores the skill against each, producing one result per rubric. Use when running a skill review workflow or testing skill quality against configurable rubrics. | Skills | |
Tools to maintain and improve CLAUDE.md files - audit quality, capture session learnings, and keep project memory current. Contains: claude-md-improver Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization". | Skills | |
v0.1.0 Interview the user relentlessly about a plan or design, resolving every branch of the decision tree before producing supporting docs. Specialised for the Tessl monorepo stack. Use when user says "grill me", "interview me about this plan", "help me think through this design", or similar. Contains: grill-me Interview the user relentlessly about a plan or design, resolving every branch of the decision tree before producing supporting docs. Specialised for the Tessl monorepo stack. Use when user says "grill me", "interview me about this plan", "help me think through this design", or similar. | Skills | |
investigate flaky, intermittent, non-reproducible, or ci-only python pytest failures by leading with retrace capture and deterministic replay. use when a user reports flaky pytest tests, random failures, tests that pass locally but fail in ci, async/threading/timing flakes, pytest-xdist issues, fixture leakage, monkeypatch leakage, test isolation failures, dependency/environment-sensitive failures, pytest timeouts, or ai-generated code that breaks tests intermittently. guide the agent to preserve the failed execution as a retrace trace, replay it, inspect runtime state, and use ordinary pytest/source/log checks only as supporting triage. Contains: flaky-pytest-investigator investigate flaky, intermittent, non-reproducible, or ci-only python pytest failures by leading with retrace capture and deterministic replay. use when a user reports flaky pytest tests, random failures, tests that pass locally but fail in ci, async/threading/timing flakes, pytest-xdist issues, fixture leakage, monkeypatch leakage, test isolation failures, dependency/environment-sensitive failures, pytest timeouts, or ai-generated code that breaks tests intermittently. guide the agent to preserve the failed execution as a retrace trace, replay it, inspect runtime state, and use ordinary pytest/source/log checks only as supporting triage. | Skills | |
v0.1.0 Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine. Contains: exa-search Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search engine. | Skills | |
Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma). Contains: documentation-lookup Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup questions, API references, code examples, or when the user names a framework (e.g. React, Next.js, Prisma). | Skills | |
Create context files (plans, justifications, scratches) in .context/ directory with unique three-word IDs and frontmatter Contains: create-context-file Creates structured context files (plans, justifications, scratches) in the .context/ directory with unique three-word IDs and frontmatter metadata. Use when starting a new task and needing to document a plan or task breakdown, when recording decision rationale or architectural choices as a justification, when saving temporary notes or exploratory thinking as a scratch, or when the user asks to "create a plan", "document my thinking", "save context", "track decisions", or "keep notes" in a structured project context directory. | Skills | |
Review and structure blog articles for the Tessl blog (tessl.io/blog). Use this skill whenever someone asks to review, edit, improve, structure, or give feedback on an article or blog draft. Also use when someone wants to write a new article from scratch, needs help with an article outline, or asks about SEO optimization for Tessl content. Triggers include any mention of blog posts, articles, content review, editorial feedback, SEO for articles, or writing guidance for Tessl or AI Native Dev content. Contains: tessl-article-reviewer Review and structure blog articles for the Tessl blog (tessl.io/blog). Use this skill whenever someone asks to review, edit, improve, structure, or give feedback on an article or blog draft. Also use when someone wants to write a new article from scratch, needs help with an article outline, or asks about SEO optimization for Tessl content. Triggers include any mention of blog posts, articles, content review, editorial feedback, SEO for articles, or writing guidance for Tessl or AI Native Dev content. | Skills | |
Review and structure blog articles for the Tessl blog (tessl.io/blog). Use this skill whenever someone asks to review, edit, improve, structure, or give feedback on an article or blog draft. Also use when someone wants to write a new article from scratch, needs help with an article outline, or asks about SEO optimization for Tessl content. Triggers include any mention of blog posts, articles, content review, editorial feedback, SEO for articles, or writing guidance for Tessl or AI Native Dev content. Contains: tessl-article-reviewer Review and structure blog articles for the Tessl blog (tessl.io/blog). Use this skill whenever someone asks to review, edit, improve, structure, or give feedback on an article or blog draft. Also use when someone wants to write a new article from scratch, needs help with an article outline, or asks about SEO optimization for Tessl content. Triggers include any mention of blog posts, articles, content review, editorial feedback, SEO for articles, or writing guidance for Tessl or AI Native Dev content. | Skills | |
Review and structure blog articles for the Tessl blog (tessl.io/blog). Use this skill whenever someone asks to review, edit, improve, structure, or give feedback on an article or blog draft. Also use when someone wants to write a new article from scratch, needs help with an article outline, or asks about SEO optimization for Tessl content. Triggers include any mention of blog posts, articles, content review, editorial feedback, SEO for articles, or writing guidance for Tessl or AI Native Dev content. Contains: tessl-article-reviewer Review and structure blog articles for the Tessl blog (tessl.io/blog). Use this skill whenever someone asks to review, edit, improve, structure, or give feedback on an article or blog draft. Also use when someone wants to write a new article from scratch, needs help with an article outline, or asks about SEO optimization for Tessl content. Triggers include any mention of blog posts, articles, content review, editorial feedback, SEO for articles, or writing guidance for Tessl or AI Native Dev content. | Skills | |
v0.4.0 22 Agent Skills for Amazon sellers and advertisers: Sponsored Products and Brands audits, search-term mining, budget pacing, DSP and Amazon Marketing Cloud, reporting, listing optimization and compliance, product images, repricing, FBA inbound, stockout, refunds, buyer messaging, and profitability. Built for Kuudo's hosted Amazon Ads and Selling Partner MCP servers; price, budget, listing, and shipment writes are previewed and wait for explicit approval. Contains: amazon-ads-accounts Use when Amazon Ads work requires distinguishing advertiser accounts, profiles, entity IDs, DSP advertiser IDs, or manager accounts; listing accessible accounts; choosing a marketplace profile; or tracing account relationships. amazon-ads-budget-pacing Use when an Amazon Ads advertiser needs to pace sponsored-ads campaign budgets against a monthly spend plan, calculate or review a daily budget change set, reforecast remaining spend, or explain account-level pacing variance. Do not use for general performance reporting, campaign creation, or account selection without a pacing objective. amazon-ads-create-dsp-campaign Create and launch an Amazon DSP Performance+ (P+) or Brand+ (B+) campaign end-to-end using this amazon-ads-mcp server's allv1_* tools. Drives the full setup: gather user inputs, query the advertiser account to resolve the DSP account ID, create the DSP campaign in PAUSED state, attach ASIN conversion tracking, query eligible automated targeting tactics, create one ad group per (inventoryType, tactic) combination, optionally create ads and ad-group associations, then activate everything in strict parent-first order with verification reads between writes. Supports P+ tactics (CUSTOMER_ACQUISITION, REMARKETING, RETENTION, MAXIMIZE_PERFORMANCE) and B+ tactics (PROSPECTING) across DISPLAY, VIDEO_OLV, VIDEO_STV, AUDIO, and LIVE_EVENTS inventory. Trigger whenever the user mentions creating a DSP P+ or B+ campaign, launching automated DSP targeting, setting up Performance+ or Brand+ ad groups, or any variant like 'spin up a P+ campaign', 'launch Brand+ prospecting', 'create DSP automated targeting'. amazon-ads-creative-assets Build and ship Amazon Ads creative assets end to end: generate compliant images (custom and lifestyle images, brand logos, display banners) and ad copy, then register them through the Amazon Ads MCP creative assets API. IF the user wants ad creative for Sponsored Brands, Sponsored Display, Amazon DSP, or eCommerce display — asks what size or file format an ad image must be, wants a lifestyle image for an ad, needs one image resized into square/wide/tall, asks whether text or a logo may appear in the creative, wants ad headline copy inside Amazon's limits, or has a rejected ad — OR wants to upload, register, version, search, or check the status of a creative asset (assetId, assetSubType, failedSpecChecks, PROCESSING, upload URL, creative asset library) — THEN invoke this skill. DO NOT invoke for retail product listing photos on a detail page (that is the amazon-product-image skill), or for campaign structure, bidding, budgets, or reporting. amazon-ads-marketing-cloud Use whenever the user works with Amazon Marketing Cloud (AMC): SQL, workflows, audiences (rule-based or lookalike), playbooks (frequency, off-Amazon conversions, keyword clustering, lookalikes, programmatic audience framework, enhanced scoring, CLTV), custom attribution (first/last-touch, linear, position-based), first-party data uploads, ad-product filtering, AMC sandbox, cross-channel overlap, reach, frequency, or NTB analysis. Triggers: "AMC", "Amazon Marketing Cloud", "AMC SQL", "AMC workflow", "AMC audience", "AMC query", "AMC playbook", DSP audiences, attribution model, path-to-conversion, ad frequency, NTB, DOOH, Sponsored TV incremental reach, Sponsored Brands, Brand Store insights, Events Manager / CAPI, Audience Segment Insights, Amazon Your Garage, or SQL referencing tables like sponsored_ads_traffic, dsp_impressions, dsp_clicks, amazon_attributed_events_by_traffic_time, conversions_all, conversions_with_relevance. amazon-ads-reporting Use when requests involve Amazon Ads unified/v1 reporting, CreateReport, reproducing a familiar Sponsored Products, Sponsored Brands, or Sponsored Display report on v1, v3-to-v1 report migration, report-field compatibility, or retrieving an asynchronous v1 report. Excludes AMC, legacy-v3 execution, live entity state, and campaign mutation. amazon-ads-sb-performance-review Produce a Sponsored Brands (SB) campaign performance review from SB Campaigns Report data: portfolio summary, top and worst campaigns by efficiency, low-CTR creative signals, new-to-brand (NTB) analysis when present, placement or format splits if columns exist, and actionable recommendations. Use when users ask for Sponsored Brands audits, SB headline/video/store spotlight reviews, brand awareness efficiency, NTB share, SB CTR vs benchmarks, or SB campaign deep-dives. The agent must fetch and parse the report for the user’s environment — do not assume a global variable, fixed file path, or stable Amazon export schema; write loader and column-mapping code after inspecting the actual artifact. amazon-ads-sp-campaign-auditor Use when auditing Sponsored Products campaign portfolio structure through Amazon Ads MCP, including spend concentration, budget utilization, delivery gaps, low-engagement campaigns, targeting-type mix, or campaign naming hygiene. amazon-ads-sp-search-term-explorer Mine Sponsored Products search terms end-to-end via the Amazon Ads MCP: generate the SP Search Term report via allv1_AdsApiv1CreateReport using v1 dotted field IDs (searchTerm.value, metric.totalCost, metric.sales, budgetCurrency.value — not legacy Console headers), pre-flight validate with report_fields before CreateReport, filter adProduct.value SPONSORED_PRODUCTS, download CSV and parse with the v1 DictReader pattern, partition PAT ASINs in searchTerm.value, elicit brand markers and thresholds, segment into generic and branded gold tables, surface negatives, sufficiency-gated rising stars, and PAT stream. Never use metric.cost / metric.spend or legacy CSV column names. Trigger on: SP search term mining, search term gold, search term negatives, search term report, PAT vs keyword, brand vs generic split, rising stars, exact-match harvest, attribution window questions, or any variant of "find me wasted spend / scale-worthy keywords / branded defenders" via the Amazon Ads MCP. amazon-product-image Use when creating, editing, auditing, or troubleshooting Amazon listing images, including main images, alternate images, infographics, lifestyle imagery, size and scale, comparison, and what's-in-the-box images, fashion photography, multipacks, swatches, suppression, or image error 100239. Also use when planning which images a listing needs and in what order. amazon-profitability-calculator Calculate Amazon per-unit margin, break-even or target-margin price, affordable ad spend, and period P&L waterfalls. Use for ASIN profitability, unit economics, contribution or channel margin, landed cost, COGS, TACoS, fee and return impact, settlement reconciliation, or period-over-period margin movement. Excludes live repricing, return-reason diagnosis, and ad campaign reporting. amazon-sp-fba-inbound Create, run, and manage Amazon FBA inbound shipments with the SP-API Fulfillment Inbound v2024-03-20 workflow: build an inbound plan, pack, pick placement and carrier, confirm delivery windows, get labels, add tracking, check status, edit, or cancel. Pauses at every fee-charging or irreversible step for the seller's explicit choice and confirms each async operation before moving on. Use whenever a seller wants to send or ship inventory to Amazon or FBA, create or check an inbound plan or shipment, compare placement fees or partnered-carrier quotes, get FNSKU, box, or pallet labels or a bill of lading, set prep or label owners, enter tracking or PRO numbers, book an FC drop-off appointment, or cancel a shipment, even if they only say "send stock to Amazon". Do not use for replenishment forecasting or stockout risk, FBA inventory health, outbound or multi-channel orders, AWD, Vendor (1P) shipments, listings, or advertising. amazon-sp-listing-compliance Pre-flight compliance gate for Amazon Seller Central listings. Works out which Amazon listing requirements and regulatory rules (FDA, EPA, CPSC, FCC, FTC, required disclosures, GTIN, category gating) apply to a product, checks whether the seller is gated or ineligible on the ASIN, asks the seller once for the facts only they know, and returns a met/unmet checklist with a go or hold. Never writes a listing itself. Use whenever a seller asks "can I list this", "what do I need to sell X", "is this compliant", or about restricted or gated categories, certificates, or required labels, and before any listing edit that adds or changes a product claim (antimicrobial, FDA approved, organic, bamboo), ingredients, category, condition, or identifiers. Do not use for fixing listing errors, copy optimization, or buyability (amazon-sp-listing-optimizer), account-health or policy questions unrelated to a specific product, or legal advice. amazon-sp-listing-optimizer Audit, optimize, fix, and edit Amazon Seller Central listings and A+ Content through an SP-API MCP server, for one listing or a whole catalog. Use whenever the user asks to review, audit, optimize, edit, fix, rewrite, or "look at" a listing — titles, item highlights, bullets, descriptions, search terms, browse nodes, attributes, images, variations, brand, A+ modules, or Brand Story. Also use to diagnose why a listing is suppressed, shows errors or warnings, isn't in search, or can't be bought (inactive, no offer), and for submission error codes such as 90057, 99001, 99010, or 97779. Trigger even when the user just names an ASIN or SKU and says "check it", "clean it up", or "what's wrong with it". Also use to regenerate listing images from existing product photos with an image model (Gemini/OpenAI), then validate and patch them. Do not use for "can I sell this product" compliance pre-checks (amazon-sp-listing-compliance), restock planning, or price-level strategy (amazon-sp-repricing). amazon-sp-messaging-api Send order-scoped messages from an Amazon seller to a buyer with the SP-API Messaging API: check which message types an order allows, pick the right one, draft the text in the buyer's language within Amazon's content rules, attach invoices, warranties, or legally required documents, and send only after the seller approves an exact preview. Handles one order or a batch. Use whenever a seller wants to contact, notify, or message a buyer about an order: a delay or unexpected problem, confirming customization, delivery scheduling, an order question before shipping, a Home Services visit, a digital access key, or sending an invoice, warranty, or legal disclosure, even if they only say "let the customer know" or "email the buyer". Do not use for requesting reviews or seller feedback (Solicitations API), reading or replying to the buyer-seller inbox, marketing or promotional messages, A-to-z claims, returns, refunds, or Vendor (1P) orders. amazon-sp-refund-return-monitor Analyze Amazon FBA customer returns and seller-fulfilled return requests from Seller Central or SP-API exports. Use for return volume, high-return ASINs or SKUs, return-rate calculations, reason and disposition analysis, customer-comment themes, prior-period comparisons, damaged-versus-reimbursed review candidates, or client-ready Amazon returns reporting. Do not use for general Amazon Ads reporting, listing optimization without returns evidence, or financial refund totals without transaction data. amazon-sp-repricing Design and run an Amazon repricing strategy from live SP-API data: compute per-SKU floors from real fee estimates, diagnose why the Featured Offer (Buy Box) is being lost, segment the catalog, write rules and guardrails, and produce a reviewable price change-set. IF the user is losing the Buy Box, asks what price to set, wants a repricing strategy or repricing rules, is in a price war or being undercut, needs a floor or break-even price, asks about Automate Pricing or a third-party repricer, or mentions ANY_OFFER_CHANGED, featured offer expected price, getCompetitivePricing, or Buy Box percentage — THEN invoke this skill. It proposes price changes and validates them before any write, and never applies prices unattended. DO NOT invoke for advertising bids or ad budgets (that is amazon-budget-pacing), listing copy or images, inventory forecasting, or returns analysis. amazon-sp-sales-traffic-analyzer Use when analyzing Amazon Seller Central Sales & Traffic Business Reports or GET_SALES_AND_TRAFFIC_REPORT data for traffic, conversion, ordered sales, ASIN performance, daily trends, or optional Amazon Business B2B segmentation. amazon-sp-sqp-asin-ngram ASIN-level Amazon SQP / organic search diagnostics tied to search queries and n-gram themes: impression/click/purchase share, conversion index, funnel gaps, shipping and price friction, variant cannibalization, and lift-aware opportunity ranking. Use when users analyze Search Query Performance per ASIN, need SKU-specific SEO/PDP/ops recommendations from SQP, want RankScore-style prioritization, report QA badges for findings, stop-word hygiene for n-grams, or ASIN+query decision records alongside ngram-keyword-framework query-level rules. Not a substitute for Ads-only n-gram bid rules — use ngram-keyword-framework for sponsored search-term rollups. amazon-sp-stockout-prevention Find FBA SKUs at risk of stocking out and whether inbound shipments will land in time. Reads live FBA inventory and FBA sales velocity, uses Amazon's own days-of-supply and recommended ship-in quantity and date when available, ranks SKUs by risk, and checks each at-risk SKU against its inbound shipments' arrival windows. Read-only. Use whenever a seller asks "am I going to run out", about stockout risk, days of cover or supply, FBA stock levels, restock or replenishment timing, what to send in next, or whether a shipment will arrive before a SKU sells out, even if they just ask "how's my inventory looking". Do not use for creating or managing inbound shipments (amazon-sp-fba-inbound), price changes or repricing (amazon-sp-repricing), stranded or aged-inventory fees, inventory ledger reconciliation, AWD, listings, or advertising. connect-to-kuudo Use when an AI agent needs to connect to a human's Kuudo account before calling any Kuudo capability — checking whether the session already exposes the Agent Auth MCP tools, registering a delegated connection with them, presenting the human's approval link, and reading account/organization data once approved. Covers the connect/approve/execute flow, approval timeouts and expiry, and the one-installation-per-human rule. Do not use to configure an MCP server, edit client configuration, or install packages — point the human to Kuudo's own connection guide instead. Do not use to design or modify the Agent Auth protocol itself, to request capabilities beyond read_account and read_organization, or to approve, deny, or sign in on the human's behalf. using-kuudo Use at the start of Amazon commerce work involving Amazon Ads, Seller Central, or Vendor Central when Kuudo skills are installed. | Skills | |
microsoft/skills Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills. | Skills | |
ruvnet/ruflo Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus | Skills |
Can't find what you're looking for? Evaluate a missing skill.