Browse Secure Claude Skills
Search verified agent skills and review security grades before installing · full A–Z index
- Threadify Daily Posts HeartbeatStart locally from confirmed facts and supplied sources without a Threadify account. Honor an existing connection choice. Offer a connection only when an available hosted capability would help; explain the benefit and obtain approval for the exact provider action.Votes: 0GitHub stars: 2
- Threadify Crosspost X After ThreadsStart locally from confirmed facts and supplied sources without a Threadify account. Honor an existing connection choice. Offer a connection only when an available hosted capability would help; explain the benefit and obtain approval for the exact provider action.Votes: 0GitHub stars: 2
- Threadify Content Brain RepairAudit an approved creator context packet, propose a small Threadify Brain repair, and compare the same prompt before and after verified approved changes. The episode 20 workflow.Votes: 0GitHub stars: 2
- Threadify Choose Your First OfferCompare an intensive, cohort or community lab, and self-serve kit with one evidence-bound scorecard, then choose the fastest truthful first offer to validate and create its Proof Loop Map and inactive validation page. Use when a creator knows their niche or audience but is unsure what delivery model to sell first.Votes: 0GitHub stars: 2
- Threadify Buyer Questions To ContentTurn supplied buyer questions into deidentified local content with honest single-or-repeated evidence labels. Use when the owner wants a draft or brief grounded in conversation evidence.Votes: 0GitHub stars: 2
- Threadify Anti Spam Lead DeskTurn current public Threads comments or a bounded cold-research fallback into a five-card anti-spam Lead Desk and one unsent public-reply draft. Use when the owner wants to find warm signals without automated outreach.Votes: 0GitHub stars: 2
- Threadify Ai Content ForensicsReverse-engineer a bounded creator corpus into evidence-linked content rules, copyable templates, and one validated ten-post thread. Use for AI Content Forensics or creator-content pattern analysis.Votes: 0GitHub stars: 2
- Threadify Agree Next StepPrepare and review one explicit next step from an active buyer conversation. Use when the owner wants exact wording, destination, permission checks and a recorded result.Votes: 0GitHub stars: 2
- Write EvalWrite a live eval for new or changed runner/agent behavior using red/green TDD plus a falsification check that proves the eval fails when the behavior is broken. Use whenever you add or modify behavior that should be covered by an eval, when asked to "write an eval", "add an eval", "cover this with an eval", or after landing a feature that needs end-to-end proof it works.Votes: 0GitHub stars: 46
- ReleaseIncrement the package version, commit the release, create a matching version tag, and push main plus the tag. Use when releasing this repo, publishing the package, bumping the version, tagging a release, or when the user asks to "release", "bump ver", "tag", or "push tags".Votes: 0GitHub stars: 46
- Debug MemoryReproduce observational-memory bugs (reflection, recall, observer, freshness, eviction) by dumping the live `~/.duet/memory.db` into a fixture and driving an eval against it. Use whenever the agent's memory misbehaves — wrong observations, bad reflections, missing recall, runaway tokens — or whenever the user asks to debug, repro, audit, or tune memory.Votes: 0GitHub stars: 46
- Vllm Vs Atom Decode Trace ComparisonCompare decode-phase kernel implementations of vLLM vs ATOM (ROCm/ATOM) running the same model with the same config, using torch profiler Chrome-trace JSONs from both engines. Samples one decode step, extracts one layer per layer type, produces per-layer-type comparison tables (which kernels each engine uses, fused or split, multi-stream, quantization differences, timing), derives a vLLM optimization TODO list, and writes a Markdown report (Chinese by default, English, or both) to the skill's...Votes: 0GitHub stars: 19
- Vllm Test GeneratorGenerate test cases for the vllm-project/vllm repository (https://github.com/vllm-project/vllm). Use this skill when the user wants to write unit tests or integration/e2e tests for vllm code, functions, classes, or features. Triggered by requests like "帮我写XXX的测试用例", "生成XXX的单元测试", "为XXX功能写测试", "generate tests for XXX in vllm", "write a test for XXX vllm function". Do NOT use for vllm-ascend — use vllm-ascend-ut-generator instead.Votes: 0GitHub stars: 19
- Vllm Technical Blog WriterWrite or complete Chinese vLLM technical blog posts in the author's established Zhihu style. Use when the user provides a vLLM feature, model, architecture, optimization, or other topic and asks for a full blog post, or provides an existing Markdown outline/draft plus references and asks to research current vllm-project/vllm code and finish the missing sections. Produces concise technical diagrams and stores each new article with its images under this skill's outputs directory.Votes: 0GitHub stars: 19
- UpstreamAI code review for ATOM PRs. ATOM consumes aiter kernels and integrates with vLLM/SGLang plugins. Reviews check perf claims, aiter cross-repo deps, model coverage, dispatch correctness, and AI-generated code patterns. Invoke with a PR number.Votes: 0GitHub stars: 19
- UpstreamAI code review for aiter PRs. Catches perf regressions, silent correctness bugs, dispatch gate holes, and AI-generated code patterns. Invoke with a PR number; works through fetch → semantic understanding → rule checklist → verdict. Add new rules here as patterns emerge from real reviews.Votes: 0GitHub stars: 19
- Vllm Rocm Pr ReviewReview AMD/ROCm-related pull requests from the vllm-project/vllm GitHub repository and produce a single combined Chinese report: a detailed PR summary (summary, background & motivation, code-change analysis with Mermaid diagrams, technical principles, discussion highlights, risk table) followed by severity-sorted, type-categorized ROCm review findings, a verdict, and copy-paste English review comments with file + diff line numbers ready for GitHub PR review. Use when the user provides a vllm ...Votes: 0GitHub stars: 19
- Vllm Rfc GeneratorGenerate a vLLM-style RFC (Request for Comments) document based on user input. Use when the user wants to create an RFC for a major architectural change or design decision in vLLM. Triggered by requests like "帮我生成一个vLLM RFC", "create a vLLM RFC for ...", "写一个RFC关于...", "生成RFC文档".Votes: 0GitHub stars: 19
- Vllm Pr SummaryFetch and analyze a Pull Request from the vllm-project/vllm GitHub repository, then generate a comprehensive Markdown report covering PR overview, code change analysis (with Mermaid architecture/flow diagrams), technical principles, discussion highlights, and risk assessment. Use when the user provides a vllm PR number and asks to summarize, analyze, review, or understand it. Triggered by requests like "帮我分析vllm的PR 12345", "总结一下vllm PR 10000", "vllm PR 9999 做了什么", "analyze vllm PR 12345".Votes: 0GitHub stars: 19
- Vllm Pr Desc GeneratorGenerate a vLLM-style PR description (Purpose / Test Plan / Test Result) from a GitHub PR's code changes. Use when the user provides a vLLM PR link or number and asks to generate, write, or draft a PR description. Triggered by requests like "帮我生成PR描述", "generate PR description for vllm PR 12345", "帮我写vllm PR的描述", "draft a PR desc for https://github.com/vllm-project/vllm/pull/12345".Votes: 0GitHub stars: 19