875 skills · sorted by relevance
AutoResearch-inspired self-evolution loop for ANY Claude Code skill. Finds flaws, fixes them, benchmarks against a diverse prompt pool (anti-overfitting), and uses blind A/B judging. Fully automated — no human input needed during the loop.
The English summary is being prepared. Showing the original description.
Coordinate eval, benchmark, load-test or batch campaigns on authorized SSH hosts or short-lived rented hosts, with isolated jobs, configured-path canaries, telemetry and evidence. Use manage-remote-resources for paid resource ownership and run-remote-builds for build-only offload.
The English summary is being prepared. Showing the original description.
lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).
The English summary is being prepared. Showing the original description.
Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks
The English summary is being prepared. Showing the original description.
Explore open-source GitHub repository source trees via web browsing to analyze and compare feature implementations at the code level. Supports two modes: cross-project comparison and single-project deep dive. Use when evaluating how OSS projects implement a specific feature, choosing architecture patterns, or benchmarking implementation strategies.
The English summary is being prepared. Showing the original description.
Research and compare how competing products implement a similar feature at the UX and interaction level. Provides structured comparison tables and strategic differentiation recommendations.
The English summary is being prepared. Showing the original description.
Comprehensive, measurement-driven performance optimization for latency, throughput, memory/GC, and tail behavior. Use when the user asks to optimize/speed up, reduce latency (p95/p99), increase throughput/QPS, lower CPU/memory/allocations/GC pauses, profile hot paths, or run a benchmarked perf pass (including JSONL/query-heavy code). Requires before/after measurement on a runnable workload (or an explicit `UNMEASURED` plan) plus a correctness gate.
The English summary is being prepared. Showing the original description.
Judge performance or resource claims on real hardware: benchmark design or review, latency, throughput, memory or headroom numbers, and accept-or-reject decisions on optimizations. Not for refactors with no resource claim.
The English summary is being prepared. Showing the original description.
Kova/OpenClaw validation: benchmarks, release gates, scenarios, perf reports.
The English summary is being prepared. Showing the original description.
Use Lingzao creator-content tools for Xiaohongshu/XHS, Douyin, and WeChat official-account public content. Lingzao supports XHS SEO, Xiaohongshu account analysis, benchmark account discovery, viral note breakdown, keyword research, one-stop content packages from keyword/link/image/inspiration material, title and cover optimization, hand-drawn route-map cards, city food maps, travel itinerary maps, life checklist maps, workflow manual maps, creator content workflow, note search, creator search, profile lookup, recent posts, deep profile copy/subtitle analysis, note/article detail, post comments, article stats, related articles, short-video copy extraction, and prompt-based creator image generation.
The English summary is being prepared. Showing the original description.
Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang <language> or asks to add/support a new language (e.g. Lua, Elixir, Zig, OCaml) in codegraph.
The English summary is being prepared. Showing the original description.
Use the HyperFrames CLI development loop: init, add, catalog, capture, lint, check, snapshot, compare, grade-compare, preview, play, present, beats, keyframes, single or batch render, publish, cloud, cloudrun, feedback, lambda, doctor, browser, info, upgrade, skills, compositions, docs, benchmark, telemetry, transcribe, auth, tts, and remove-background. Also use when diagnosing build or render failures. validate, inspect, and layout are deprecated aliases; use check. Covers local, HeyGen-hosted cloud, AWS Lambda, and Google Cloud Run rendering.
The English summary is being prepared. Showing the original description.
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
The English summary is being prepared. Showing the original description.
从对标账号导入 script + 数据 → 拆 pattern + 派生 base rubric 信号 → 写到 benchmark.md / script_patterns.md / rubric_notes.md。**这是工具最早期信号的来源**——cold-start 用户没自己历史时全靠对标，发过历史的用户也建议至少 1 个对标做 sanity check。触发词："学这个账号"/"拆这几个对标视频"/"learn from"/"导入对标账号"/"找对标"。
The English summary is being prepared. Showing the original description.
Run a 100xprism module's evals to check it triggers correctly and produces good output — "do my skills still trigger correctly," "did this change break a skill." Fans eval cases out to parallel subagents with Haiku-graded pass/fail scorecards. For authoring or benchmarking general-purpose skills, prefer a skill-creator plugin when present.
The English summary is being prepared. Showing the original description.
What every Ollama timing field means and the arithmetic that turns it into a claim - tokens per second, time-to-first-token, why total_duration is not latency, why a second run is faster, what changes with context length, quantization, GPU offload and parallel requests - plus the reporting rules that make a benchmark a measurement instead of an anecdote.
The English summary is being prepared. Showing the original description.
The `ollama` Python package used properly - chat and generate with streaming, embeddings, tool calling, structured outputs with a JSON Schema, the async client, keep_alive, timeouts and cancellation - and a project shape whose benchmark arithmetic is unit-tested against a fake transport while the live half skips loudly when no daemon answers.
The English summary is being prepared. Showing the original description.
Pre-breach impact analysis: inventories sensitive data (PII, PHI, PCI-DSS, credentials), traces data flows, scores exposure vectors, and produces a regulatory blast radius report with fine ranges sourced verbatim from GDPR Art. 83, CCPA § 1798.155(a), and HIPAA 45 CFR § 160.404. Cost benchmarks from IBM Cost of a Data Breach Report (annually updated). All citations in references/SOURCES.md for verification. Use when asked: "assess breach impact", "what data could be exposed", "calculate blast radius", "data exposure analysis", "how bad would a breach be", "quantify data risk", "sensitive data inventory", "data flow security audit", "pre-breach assessment", "worst-case breach scenario", "breach readiness", "data risk report", "/data-breach-blast-radius". For any stack handling user data, health records, or financial information. Output labels law-sourced figures (exact) vs heuristic estimates (planning only). Does not replace legal counsel.
The English summary is being prepared. Showing the original description.
Guides implementation of agent memory systems, compares production frameworks (Mem0, Zep/Graphiti, Letta, LangMem, Cognee), and designs persistence architectures for cross-session knowledge retention. Use when the user asks to "implement agent memory", "persist state across sessions", "build knowledge graph for agents", "track entities over time", "add long-term memory", "choose a memory framework", or mentions temporal knowledge graphs, vector stores, entity memory, adaptive memory, dynamic memory or memory benchmarks (LoCoMo, LongMemEval).
The English summary is being prepared. Showing the original description.
Use when raw SaaS numbers need turning into a health verdict — MRR, ARR, churn, CAC, LTV, payback, burn multiple, NRR. Calculates the metrics, benchmarks them against industry standards, and returns prioritized, plain-English advice as a senior SaaS CFO would.
The English summary is being prepared. Showing the original description.
Use when diagnosing agent benchmarks or runtime failures from trajectories instead of aggregate pass rates. Builds shared action-observation decision landscapes, identifies productive cores and trap regions, profiles Access/Trap/Repair behavior, and designs conservative trap-triggered recovery experiments.
The English summary is being prepared. Showing the original description.
Use when improving, evolving, benchmarking, or maintaining agent skills over time. Treats skills as long-lived structured artifacts: execute tasks, diagnose trajectory evidence, accumulate textual momentum, patch at the correct abstraction layer, test per model and harness, canary changes, and roll back regressions.
The English summary is being prepared. Showing the original description.
Improve AI application with evaluation-driven development. Define eval criteria, instrument the application, build golden datasets, observe and evaluate application runs, analyze results, and produce a concrete action plan for improvements. ALWAYS USE THIS SKILL when the user asks to set up QA, add tests, add evals, evaluate, benchmark, fix wrong behaviors, improve quality, or do quality assurance for any Python project that calls an LLM model.
The English summary is being prepared. Showing the original description.
Automated compliance checking against CIS, PCI-DSS, HIPAA, and SOC 2 benchmarks
The English summary is being prepared. Showing the original description.