Loading...
Loading...
Found 1,909 Skills
Survey State-of-the-Art literature on a research topic. Use when asked to find papers, survey a field, map the research landscape, identify gaps, or build a literature matrix. First step in any research workflow.
Use for Roblox persistent data and cross-server state design: choosing between DataStoreService, OrderedDataStore, MemoryStoreService, and MessagingService; designing save and load flows, schema shape, versioning, metadata, retries, quotas, observability, and concurrency-safe coordination across servers.
Write, structure, or review a PhD/Master's research proposal. Use when drafting a research proposal, preparing for committee review, writing a thesis outline, or aligning methodology with academic requirements.
Specialized in Container diagrams (Level 2) with Infrastructure mapping. Use this skill when the user requests decomposing systems into separately deployable units, identifying the tech stack, and mapping infrastructure components (Docker, K8s).
Use when an agent needs to send outreach, reply to inbound, sign up for a service, or log into a site via the user's autark-provisioned AgentMail inbox. Everything goes through `autark mail`.
Prepare for PhD or Master's thesis defense. Use when preparing defense presentation, anticipating committee questions, practicing oral defense, or structuring defense slides.
Standardized directory structure and artifact management for agentic research. Ensures consistent data flow across all agent platforms (Gemini, Claude, Antigravity).
Write technical reports — experiment reports, system design documents, code documentation, and internal research memos. Use when documenting technical work that doesn't fit paper format.
README-first AI repo reproduction orchestrator. Use when the user wants an end-to-end minimal trustworthy reproduction flow that reads the repo, selects the smallest documented inference or evaluation target, coordinates the intake, setup, execution, and optional paper-gap sub-skills, enforces conservative patch rules, and writes the standardized `repro_outputs/` bundle. Do not use for paper summary, generic environment setup, isolated repo scanning, standalone command execution, or broad research assistance outside repository-grounded reproduction.
Run a model-diverse subagent council to investigate the same problem from multiple perspectives, compare findings, and produce a final recommendation. Use this skill whenever the user asks for a council, second opinions, multiple agents/models to evaluate one question, parallel investigation, red-team/blue-team comparison, or help deciding between competing technical approaches.
Use when the user wants to create, author, write, or design a new Agent Skill (a SKILL.md) — for OpenKnowledge or for their editors — including requests like 'help me write a skill', 'make a skill that…', 'turn this workflow into a skill', or improving an existing skill's triggering and discipline. Also use when capturing reusable agent guidance that should live as an installable skill rather than a one-off prompt. Covers choosing scope (project vs global), the SKILL.md frontmatter contract, progressive-disclosure structure, evaluating the skill, and installing it into the user's editors.
Evaluate scientific claims and evidence quality. Use for assessing experimental design validity, identifying biases and confounders, applying evidence grading frameworks (GRADE, Cochrane Risk of Bias), or teaching critical analysis. Best for understanding evidence quality, identifying flaws. For formal peer review writing use peer-review.