- 📄 examples.md
- 📄 reference.md
- 📄 SKILL.md
Performs GPU kernel correctness and performance evaluation and LLM inference benchmarking with Magpie. Analyzes single or multiple kernels (HIP/CUDA/PyTorch), compares kernel implementations, runs vLLM/SGLang benchmarks with profiling and TraceLens, and runs gap analysis on torch traces. Creates kernel config YAMLs, discovers kernels in a project, and queries GPU specs. Use when the user mentions Magpie, kernel analyze or compare, HIP/CUDA kernel evaluation, vLLM/SGLang benchmark, gap analysis, TraceLens, creating kernel configs, or discovering GPU kernels.
- 📁 bin/
- 📁 docs/
- 📁 evaluations/
- 📄 .gitignore
- 📄 EVALUATION.md
- 📄 LICENSE
Structured B2B software vendor evaluation for buyers. Researches your company, asks domain-expert questions, engages vendor AI agents via the Salespeak Frontdoor API, scores vendors across 7 dimensions, and produces a comparative recommendation with evidence transparency. Use when asked to evaluate, compare, or research B2B software vendors.
- 📄 autoresearch_helper.py
- 📄 SKILL.md
Autonomous experiment loop for optimization research. Use when the user wants to: - Optimize a metric through systematic experimentation (ML training loss, test speed, bundle size, build time, etc.) - Run an automated research loop: try an idea, measure it, keep improvements, revert regressions, repeat - Set up autoresearch for any codebase with a measurable optimization target Implements the autoresearch pattern with MAD-based confidence scoring, git branch isolation, and structured experiment logging. --- # Autoresearch
Guide for writing the abstract of an academic economics paper. Use this skill whenever the user asks for help writing, drafting, revising, or structuring an abstract for an economics paper - whether empirical micro, development economics, applied economics, or related fields. Also trigger when the user mentions "abstract," "paper summary," or asks how to compress their findings into a short description. This skill synthesizes best practices from David Evans (CGDev), Marc Bellemare, and patterns observed in top economics journals (AER, QJE, AEJ: Applied, etc.). --- # How to Write the Abstract of an Economics Paper A lot of people will read no further than the abstract of your paper to decide whether it is worth reading, sharing, or citing. Some will not even get past the title. The abstract is your most compressed sales pitch: it must tell the reader what you did and what you found, clearly and fast. This skill is based primarily on David Evans' analysis of abstracts in top economics journals, supplemented by Marc Bellemare's writing advice, empirical research on abstract readability, and common patterns from AER, QJE, and AEJ: Applied papers. ## The Evidence on What Works Before getting to structure, two empirical facts worth knowing: **Readability predicts citations.** Dowling and others examined abstracts in Economics Letters and found that abstracts with simpler words and shorter sentences were associated with more citations. As Bellemare puts it: do not confuse lack of intelligibility with intellectual rigor. **Accessibility expands your audience.** Bellemare's rule of thumb: if your title is not repellent and your abstract is intelligible to people outside your narrow subfield, you have expanded the scope of your citations tenfold - because many people cite papers they have only read the abstract of. --- ## The Core Structure Abstracts in top economics journals follow a compressed version of the introduction formula. Evans identifies five ingredients of a good
Fetch, classify, and summarize papers from multiple sources (arXiv, etc.) with AI-powered multi-language summaries and email delivery.
- 📁 references/
- 📁 scripts/
- 📄 README.md
- 📄 SKILL.md
Amazon seller data analysis tool. Features: market research, product selection, competitor analysis, ASIN evaluation, pricing reference, category research. Uses scripts/apiclaw.py to call APIClaw API, requires APICLAW_API_KEY. --- # APIClaw — Amazon Seller Data Analysis > AI-powered Amazon product research. Respond in user's language. ## Files | File | Purpose | |------|---------| | `scripts/apiclaw.py` | **Execute** for all API calls (run `--help` for params) | | `references/reference.md` | Load when you need exact field names or filter details | ## Credential
Answer research questions using a local vector DB and online literature search, with auto-ingest for new papers. Use when you need to find relevant academic work or verify if an idea is novel.
Manage ad campaigns across Google Ads, Meta Ads, LinkedIn Ads, and TikTok Ads. Use when the user wants to analyze campaign performance, research keywords, create campaigns, optimize budgets, or manage ad accounts via the Adspirer MCP server.
Use when creating, updating, reviewing, or merging a PR in this repo. Covers first-push rebases, review and simplification passes, benchmark baseline requirements, and post-merge `$postmortem` runs.
Bump the FutureSearch SDK version across all files. Use when releasing a new SDK version, updating version numbers, or the user says bump version, release, version bump.
- 📁 scripts/
- 📄 .gitignore
- 📄 config.example.yaml
- 📄 LICENSE
OpenClaw personalized paper recommendation skill. When the user invokes /aminer-rec5 or /skill aminer-rec5 in Feishu, immediately run the local pipeline under {baseDir}/scripts/, accept aminer_user_id, scholar hints, seed paper titles, papers_file, or free-form topic text, build a unified ResearchProfile, retrieve papers, enrich with AMiner, dispatch Feishu cards, and return NO_REPLY.
Use when preparing to engage a target account, researching a company before outreach, or building pre-call intelligence. Triggers: 'research this company', 'account brief for [company]', 'company research', 'what do I need to know about [company]', 'pre-outreach research'.
