Skill rating
19 066 skills. The A–F grade combines safety (60%) and quality (40%); tests add a bonus. The rating refreshes automatically from open catalogs.
ManufacturingLogistics and warehouseProcurementQuality controlContact centreField serviceFinanceCustomer supportindustry shortcuts
| # | Grade | Skill | Score ▾ | Safety | Quality | Process | Tests | Popularity | Updated |
|---|---|---|---|---|---|---|---|---|---|
| 17301 | A | Manage and optimize agent workspace directory structure. Use when: (1) initializing a new agent workspace with proper structure, (2) auditing document placement to ensure files are in correct function | 100 | 77 | F will not run | — | ↓ 671 | 11 May 2026 | |
| 17302 | C | 100 | 0 | D | — | ↓ 1 204 | 11 May 2026 | ||
| 17303 | C | 100 | 0 | D | — | ↓ 786 ★ 1 | 6 Jun 2026 | ||
| 17304 | C | 100 | 0 | C | — | ↓ 1 106 | 11 May 2026 | ||
| 17305 | A | Receipt OCR, GL code mapping, policy compliance checking, and anomaly detection for business expenses. Use when you need to: (1) extract data from receipt images or PDFs via OCR, (2) map expenses to c | 100 | 76 | F will not run | — | ↓ 1 117 | 17 May 2026 | |
| 17306 | A | Multi-repo PR monitoring and triage agent. Scans GitHub repos for open PRs, prioritizes by staleness/review status/CI state, and generates a structured Markdown triage summary. Use when managing PRs a | 100 | 77 | F will not run | — | ↓ 659 | 11 May 2026 | |
| 17307 | A | Analyze data with `toxicity-structure-alert` using a reproducible workflow, explicit validation, and structured outputs for review-ready interpretation. | 100 | 77 | F will not run | — | ↓ 657 | 11 May 2026 | |
| 17308 | A | Semantic memory layer for OpenClaw agents. Use when: (1) persisting agent memories with importance scoring, (2) hierarchical memory rollups (daily→weekly→monthly→yearly), (3) queuing tasks for agents, | 98 | 78 | F will not run | — | ↓ 1 107 | 17 May 2026 | |
| 17309 | A | Run only when the user explicitly asks for a fleet-wide PostgreSQL Flexible Server health check — scans CPU, memory, storage, IOPS, disk bandwidth, and connection metrics across all servers, then deep | 100 | 78 | F will not run | — | ↓ 651 | 11 May 2026 | |
| 17310 | A | Reviews shadcn/ui components for CVA patterns, composition with asChild, accessibility states, and data-slot usage. Use when reviewing React components using shadcn/ui, Radix primitives, or Tailwind s | 100 | 78 | F will not run | — | ↓ 650 | 11 May 2026 | |
| 17311 | C | 100 | 0 | C | — | ↓ 622 ★ 1 | 11 May 2026 | ||
| 17312 | B | Detects fail-open insecure defaults (hardcoded secrets, weak auth, permissive security) that allow apps to run insecurely in production. Use when auditing security, reviewing config management, or ana | 95 | 78 | F will not run | — | ↓ 3 237 | 17 May 2026 | |
| 17313 | C | 100 | 0 | D | — | ↓ 1 031 | 11 May 2026 | ||
| 17314 | C | 100 | 0 | C | — | ↓ 1 067 | 17 May 2026 | ||
| 17315 | A | Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this | 100 | 79 | F will not run | — | ↓ 695 | 16 Jun 2026 | |
| 17316 | A | Reviews Remix v2 form code for manual fetch() mutations, native <form> misuse, wrong useNavigation/useFetcher choice, missing pending state, unbounded uploads, and intent-pattern violations. Use when | 100 | 78 | F will not run | — | ↓ 688 | 1 Jun 2026 | |
| 17317 | A | Verify mobile and landline numbers and WhatsApp registration status. Reduce invalid contacts to improve outreach for exporters, recruiters and sales teams.
Trigger: phone number validation, WhatsApp | 100 | 79 | F will not run | — | ↓ 691 | 23 d ago | |
| 17318 | C | 100 | 0 | D | — | ↓ 1 181 | 11 May 2026 | ||
| 17319 | A | Solo business management with dashboard, pipeline tracking, invoicing, and weekly reviews. Use when user mentions solo business, clients, revenue, pipeline, invoices, or priorities. Produces business | 100 | 75 | F will not run | — | ↓ 1 085 | 11 May 2026 | |
| 17320 | A | Nightly workspace audit — auto-discover file dependencies by scanning all workspace files for cross-references, manage HOT/WARM/COLD memory tiers, detect orphaned files, sync inconsistencies, and repo | 100 | 77 | F will not run | — | ↓ 654 | 18 May 2026 | |
| 17321 | A | CMMI V3.0 Certification Assistant — Helps PM and EPG teams efficiently pass CMMI certification. Core capabilities: ① Upload project documents → auto-match CMMI V3.0 Practice Areas (PA); ② Gap analysis | 100 | 81 | F will not run | — | ↓ 451 | 8 Jun 2026 | |
| 17322 | C | 100 | 0 | C | — | ↓ 1 081 | 11 May 2026 | ||
| 17323 | C | 100 | 0 | C | — | ↓ 1 059 | 17 May 2026 | ||
| 17324 | C | 100 | 0 | A | — | ↓ 1 052 | 11 May 2026 | ||
| 17325 | C | 100 | 0 | C | — | ↓ 1 076 | 11 May 2026 | ||
| 17326 | C | 100 | 0 | C | — | ↓ 1 140 | 6 d ago | ||
| 17327 | C | 100 | 0 | D | — | ↓ 1 066 | 11 May 2026 | ||
| 17328 | C | 100 | 0 | C | — | ↓ 1 166 | 11 May 2026 | ||
| 17329 | B | Compare vendors on a matrix that decides instead of decorates — the criteria weighted before the demos (so the shiny demo can't rewrite them), the evidence-based scoring with the marketing-vs-verified | 100 | 69 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17330 | B | Decide what documents to keep, for how long, and where — the personal/small-biz retention map by category (tax, legal, medical, warranties, employment), jurisdiction-flagged periods, and the destructi | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17331 | B | Review an LLM agent design and find where it will be unreliable, expensive, or unsafe. Use when asked to review an agent architecture, critique a multi-step/tool-using agent, debug an agent that loops | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17332 | B | Treat context switches as the budget line they are — the switch census (how fragmented the week really is), the batching moves that consolidate scattered same-kind work, the calendar defrag that turns | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17333 | B | expert-interview-prepAnalyzerAI and agentsOperations and projectsmohitagw15856/pm-claude-skillsAgent Skills Get the most from an hour with an expert — the do-your-homework floor (never ask what's googleable), the question arc from calibration to the frontier, the follow-up discipline that goes deep instead | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17334 | B | Evaluate a new tool before it joins the stack — the problem-first framing (tools answer needs, not demos), the trial designed with success criteria upfront, the stack-fit check (integration, overlap, | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17335 | B | Stop presenting the working deck to executives — the two-deck split (answer-first exec cut vs. exploration-rich working deck), the compression rules from 40 slides to 8, and the appendix strategy that | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17336 | B | Clean up a shared drive nobody owns — the ownership-first move, the top-down audit that finds the 80% (stale projects, duplicates, ex-employee folders), the archive-don't-delete discipline for shared | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17337 | B | Install the weekly review that keeps work from managing you — the 30-minute Friday ritual: close the week's loops, sweep the capture points, choose next week's big three before the calendar chooses fo | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17338 | B | Fix slides that are documents in landscape mode — the one-point-per-slide rule, the projection-vs-reading fork that decides density, the text diet (headlines and evidence, prose to notes), and the gla | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17339 | B | Give a deck a spine the room can follow — the situation-complication-resolution arc, the tension that makes the recommendation feel necessary, the transitions that carry the thread between slides, and | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17340 | B | Outline a deck as headline sentences before opening the slide tool — each slide a claim that reads as an argument top to bottom, the audience-and-ask header, and the skim test that catches broken deck | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17341 | B | Review a deck against a rubric instead of taste — the five dimensions (argument, evidence, density, arc, honesty), the severity-sorted feedback that separates broken from suboptimal, and the review co | 100 | 69 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17342 | B | Triage an overwhelming task list into what actually gets done — the urgent/important sort applied honestly (with the two corrections the classic matrix needs), the do/schedule/delegate/drop verbs, and | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17343 | B | Decline requests without damaging relationships or your standing — the fast-clear-warm formula, the alternative-attached no, the no-to-the-boss version (tradeoffs, not refusal), and the scripts for th | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17344 | B | unblock-protocolAnalyzerAI and agentsWriting and documentsmohitagw15856/pm-claude-skillsAgent Skills Get unstuck on purpose — the stuck-type diagnosis (don't-know-how, can't-decide, waiting, avoiding, too-big), the matched unblock move for each, and the timebox that stops noble struggling before it e | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17345 | B | Know which talk you're giving — the pitch (drive one decision) vs. the teach (build understanding) — because mixing their structures fails both, and most bad presentations are one wearing the other's | 100 | 71 | F will not run | — | ★ 1 364 | 30 h ago | |
| 17346 | C | 100 | 0 | C | — | ↓ 1 030 | 11 May 2026 | ||
| 17347 | C | 100 | 0 | C | — | ↓ 1 051 | 11 May 2026 | ||
| 17348 | C | 100 | 0 | C | — | ↓ 1 093 | 11 May 2026 | ||
| 17349 | C | 100 | 0 | D | — | ↓ 1 007 | 11 May 2026 | ||
| 17350 | C | 100 | 0 | C | — | ↓ 1 006 | 11 May 2026 |