Loading...
Loading...
Found 1,378 Skills
Implement BM25 ranking function for e-commerce product search relevance scoring. Use this skill when the user needs to build a text-based product search engine, improve search result relevance, or replace basic TF-IDF with a more robust ranking function — even if they say 'product search ranking', 'search relevance', or 'BM25 implementation'.
Independent model QA expert who audits ML and statistical models end-to-end - from documentation review and data reconstruction to replication, calibration testing, interpretability analysis, performance monitoring, and audit-grade reporting.
Replicate and validate a GitHub issue by spinning up Archon, analyzing the issue, and systematically testing all described symptoms using browser automation. Use when: User wants to reproduce a bug, validate a GitHub issue, confirm a reported problem, or investigate whether an issue is real before working on a fix. Triggers: "replicate issue", "reproduce issue", "validate issue", "confirm bug", "test issue", "can you reproduce", "try to replicate", "verify the bug". Capability: Checks out main, pulls latest, starts Archon, reads the GitHub issue, then uses agent-browser to systematically test every symptom and produce a findings report. NOT for: Fixing issues (use /archon or /exp-piv-loop:fix-issue), general UI testing (use /validate-ui).
Guide for migrating OCaml projects, libraries, modules, and test suites to idiomatic MoonBit. Use when translating OCaml code to MoonBit, planning a large OCaml-to-MoonBit port, preserving byte/string-heavy behavior, replacing OCaml variants/records/exceptions/refs/arrays, mapping OCaml APIs to MoonBit packages, or building verification and test strategy for a migration.
Adversarial due-diligence on a benchmark you envy — a founder, KOL, company, or product whose claimed success you suspect is inflated. Inline four-phase orchestration — fan-out collection, adversarial verification grading every claim L1-L4 to split marketing bubble from real signal, attribution weighting (product vs timing vs IP vs luck, what's replicable), then mapping the validated playbook onto the user's own resources. Use whenever the user wants to 尽调/对标/拆解 a competitor or role-model, 抄/偷师 someone's playbook, suspects 水分/泡沫 in their claims (Product Hunt
Use whenever you need an email address to receive something and then read or wait for it, especially during a signup or login flow. PROACTIVELY, and you can usually do this without asking the user first: a service is about to send a verification code, OTP, one-time code, 2FA or two-factor code, confirmation link, magic link, or password reset and you need to wait for it and read the value out; you are signing up for or registering with a service and must confirm an email address to continue; you need a fresh, managed, throwaway, or burner address instead of using a real one; you sent something and need to watch for what lands. REACTIVELY: the user asks "did it arrive?", "check the inbox", "what came in?", "wait for the email", or wants an address to catch replies, codes, receipts, or alerts. Provides a managed `*.primitive.email` address plus `primitive emails latest` and `primitive emails wait` to read and block for mail, and hosted Functions to run JavaScript on every inbound message. No SMTP, no DNS, no mail server. Use this when a third party sends mail TO you; to send your own message and wait for its reply, use the primitive-chat skill. Gets a free `*.primitive.email` address via `primitive agent start-agent-signup` if you do not already have one. Part of the Primitive CLI (Primitive, primitivedotdev, primitive.dev; the `primitive` or `prim` command).
Use the AgentTeam Email CLI command `at-email` to operate an agent mailbox. Use when the user wants to check mailbox status, list inbox messages, read safe message content, search mail, mark messages read, archive messages, send email, reply to email, use JSON output for automation, check CLI version/update status, or run the bundled wrapper helper when the skill is available but `at-email` is not on PATH.
Split Markdown documents into paragraph blocks with stable IDs and hashes, only replace blocks approved by the user, and output the retention ratio, modification reasons, and issue tracking report. Use when the user asks for "only modify these paragraphs", "partial modification according to review comments", "keep other content unchanged", "generate reviewable modification patch", or requests the rw-revision-patch workflow.
Use when the user wants to mine comments and replies for audience reactions, customer language, questions, objections, complaints, product ideas, buying intent, sentiment, or voice-of-customer insights from public social posts and videos.
Evidence-based assessment of whether an SAP API/interface usage scenario aligns with the SAP API Policy (v.4.2026a). Use whenever someone asks whether a way of calling SAP is allowed/compliant — e.g. Published API vs internal/private/"confidential" API status, "Documented Use", whether a third-party tool / iPaaS / middleware / RPA bot / AI agent / MCP server may call SAP APIs, agentic or generative-AI access to SAP, bulk data extraction or replication into a lake/warehouse, custom Z/Y OData or RFC/BAPI wrappers and Clean Core, ADT/developer-tooling boundaries, ODP-RFC and other "not permitted" interfaces, partner Integration Certification, or RISE integration remediation. Trigger even when the policy is not named, e.g. "are we allowed to…", "is it compliant to…", "can we connect X to SAP…", "will this break under the new API policy". Produces a sourced technical assessment with a confidence level — explicitly NOT legal advice and NOT a final SAP compliance decision.
Generate your Team Performance Dashboard from your La Growth Machine data: a head-of-sales cockpit that ranks each sender (rep) on reply rate, your success event (signups/meetings/deals) and conversion, surfaces hot leads going cold, and turns your best reps' campaigns into a coaching playbook for the rest. Pulls only YOUR live LGM data into one sortable all-KPI team table plus a value (€) layer, classifies real replies, and renders a live artifact. This is the PER-REP team view, not the per-campaign weekly-performance-advisor. Use when a head of sales, SDR manager, GTM engineer or RevOps wants per-member outbound stats, who converts best and why, which replies are unanswered, or what to clone across the team. Triggers on: 'stats by member', 'team performance dashboard', 'per-rep outbound', 'who converts best', 'weekly team performance', 'sales team cockpit', 'coach my SDRs', 'per-identity reply rate'. First run does a short setup (~10-15 min); later runs just rebuild. Maintained by La Growth Machine.
Babysit a pull request through its bot review rounds: verify, fix, reply, resolve. Use for any babysit or watch-the-PR ask.