Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 28801–28830 of 32349 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| cs-writing-commonDa1yuqin/StarPaperCS 写作共享规则;适用于实证型 CS 会议论文,按当前任务加载。 | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| starpaper-figuresDa1yuqin/StarPaperCreate and refine CS paper main figures, framework diagrams, case illustrations, and quantitative charts from manuscripts and real data, with self-explanatory labels and final-size PDF checks. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| tutorial-authoringDa1yuqin/StarPaperCreate concise tutorial websites with task-oriented chapters, reusable templates, and coherent examples with matched highlights and margin notes. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| deep-read-to-deltaQZhang2111/Research-PilotUse when a project-local paper dossier should produce graph delta JSON proposals and run through the human-gated delta loop. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| delta-update-protocolQZhang2111/Research-PilotUse when a Research Pilot project graph change must be previewed, registered, accepted, rejected, parked, or revised through human-gated D* deltas. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| gap-driven-searchQZhang2111/Research-PilotUse when a graph gap or Evidence Need should become a targeted paper-search contract or candidate lead list. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| paper-discovery-intakeQZhang2111/Research-PilotUse when the user wants to add source identity from PDF, URL, arXiv, DOI, note, experiment result, manual reference, or Zotero item into a Research Pilot project. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| project-evidence-synthesisQZhang2111/Research-PilotUse when a set of sources, dossiers, graph records, or experiment notes must be synthesized into project understanding, evidence pressure, uncertainty, and optional strict-review graph proposals. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| project-experiment-proposalQZhang2111/Research-PilotUse when a Research Pilot project needs an experiment proposal from a weak or bounded project claim. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| project-gap-analysisQZhang2111/Research-PilotUse when a Research Pilot project needs read-only gap detection or Evidence Need extraction from the Project Understanding Graph. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| project-gap-discoveryQZhang2111/Research-PilotUse when the user wants papers to consider for a graph gap or missing evidence need. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| project-next-actionQZhang2111/Research-PilotUse when a Research Pilot project needs a read-only recommendation for the next workflow action. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| project-understanding-updateQZhang2111/Research-PilotUse when a research project needs normal project memory updated from human intent, sources, evidence pressure, experiment results, or direction changes; strict graph review is optional advanced mode. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| related-work-lineageQZhang2111/Research-PilotUse when the user wants a related-work survey, technical lineage, task timeline, or paper-map around a baseline paper, research task, benchmark, or project direction. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| research-pilotQZhang2111/Research-PilotUse when the user wants an agent to track, inspect, or operate Research Pilot project memory through natural chat. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| research-pilot-first-runQZhang2111/Research-PilotUse when a new user wants an agent to start Research Pilot from scratch, create or inspect a local workspace, create the first project, or begin project tracking. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| single-paper-deep-readQZhang2111/Research-PilotUse when the user wants an agent to create or update a project-local source/paper note from a PDF, URL, arXiv, DOI, manual source, or Zotero item. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| agent-integration-testingav/skillsUse when the user requests integration testing, feature validation, or test plan execution | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| annealav/skillsUse when the user wants to systematically fix AI code slop — duplicated logic, over-engineering, silent error swallowing, convention drift, cargo-cult patterns, and other LLM-introduced architectural decay — over a specified duration | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| article-factoryav/skillsProduce a researched long-form article from a topic prompt via an orchestrated pipeline - research agent (first-person sources, working-definition gate), narrative-architecture outline, writer/cold-reviewer loop with an explicit ACCEPT/REVISE verdict contract, then a catalog-deslop pass with a regression gate. The orchestrator dispatches subagents only; the writer never judges its own draft. Use when the user says "article factory", "write an article about X", "run the article pipeline", or asks for a researched long-form piece produced end-to-end. For essays and micro posts in the user's own voice without a research stage, use the prose skill instead. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| autoresearchav/skillsRuns autonomous keep/discard experiments on a codebase to optimize a single metric for a fixed duration, in the style of karpathy/autoresearch. Use when the user says "autoresearch" (optionally with a focus, e.g. "autoresearch the optimizer"), asks to run experiments on a repo overnight, to hill-climb or optimize a metric autonomously, or points at a repo with a karpathy-style program.md. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| boost-modulesav/skillsCreate custom modules for [Harbor Boost](https://github.com/av/harbor/tree/main/boost), an optimizing LLM proxy. Use when building Python modules that intercept/transform LLM chat completions—reasoning chains, prompt injection, structured outputs, artifacts, or custom workflows. Triggers on requests to create Boost modules, extend LLM behavior via proxy, or implement chat completion middleware. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| bugbashav/skillsSystematically explore and test any software project (CLI, API, Backend, Library, etc.) to find bugs, usability issues, and edge cases. Produces a structured report with full reproduction evidence (exact commands, inputs, logs, and tracebacks) for every issue. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| bughuntav/skillsFully autonomous bug hunting pipeline — discover bugs in a scoped area using parallel subagents, independently triage each finding, fix confirmed issues with subagents, then audit all fixes against repo constraints and target platforms. Runs end-to-end without user interaction. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| catalog-deslopav/skillsCatalog-then-fix slop removal on an existing prose draft. Parallel catalog subagents inventory four slop categories (theatrics, overwrought register, corrective antithesis, dramatic short sentences), fix subagents repair only what a catalog names, mechanical lint + frequency analysis bracket the run, and a regression gate (lint delta, word count, cold meaning check) decides whether the result ships. Use when the user says "deslop this draft", "catalog deslop", "strip the AI patterns from this file", or as the final stage of the article-factory and mosaic-writing skills. For writing or redrafting prose from scratch, use the prose skill instead - this skill only repairs an existing draft in place. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| disciplineav/skillsBulletproof agent operating protocol for failure prevention. Use before any task to enforce no fabrication, constraint tracking, verification, scoping, retry discipline, and concise communication. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| factual-communicationav/skillsRestate content as a flat list of atomic facts in the style of av/facts fact sheets. Use when the user says "just facts", "facts only", "as facts", "give me the facts", or replies with a bare "facts" / "facts?" to a previous message — then the scope is that message's content. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| ideateav/skillsTimeboxed ideation on a topic where lens-driven proposers generate structurally different ideas, blind critics cull them, and pairwise judges rank the survivors on a tournament ladder instead of 1-10 scores, evolving the leaders until the clock runs out. Use when the user wants to brainstorm, explore ideas, discover features, generate options, or think through possibilities for a specified duration. Triggers on requests like "brainstorm X for 30 minutes", "ideate on X", "spend an hour thinking about X", "what features should we build", "explore options for X". Not for executing a task over time (timeboxed-iterating) or optimizing a measurable metric (autoresearch). | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| improve-skillav/skillsImprove an existing agent SKILL.md through one gated cycle: select the target (default this skill), snapshot the committed baseline, diagnose against skill-design-principles plus four rubric dimensions, apply exactly one focused change, and ship only if a different agent than the author PASSes with quoted evidence. Use when the user says "improve this skill", "improve-skill", "iterate on SKILL.md", or "apply skill-design-principles to a skill". Do not use for code slop over a duration (anneal), generic timeboxed work (timeboxed-iterating), graph orchestration (workgraph), metric hill-climb on a codebase (autoresearch), or stripping slop from existing prose (catalog-deslop). | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |
| make-videoav/skillsBuild a HyperFrames video composition from a brief/script autonomously. Uses separated builder and critic subagents — builders never review their own work. Quality decisions are grounded in project context (identity, audience, goals) and established visual/motion design principles. Measurable criteria (text size, contrast, overflow) are verified with tooling, not visual judgment. Use when the user says "make this video", "implement this brief", "build this composition", or provides a video script/brief to implement. | Stars: 28 | Updated | Claude CodeCodex | Unverified | Install |