Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: Dev tools
17,418 results · page 101 of 581
- View details
aris-result-to-claimSkillDev tools
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or runni
Ready to connect★ 1k
- View details
aris-vast-gpuSkillDev tools
Rent, manage, and destroy GPU instances on vast.ai. Use when user says \"rent gpu\", \"vast.ai\", \"rent a server\", \"cloud gpu\", or needs on-demand GPU without owning hardware.
Ready to connect★ 1k
- View details
drclawSkillDev tools
Dr. Claw workspace skill for project lookup, session inspection, TaskMaster progress, OpenClaw structured schema, and event-driven reporting
Ready to connect★ 1k
- View details
ds-analysis-campaignSkillDev tools
Use when a quest needs one or more follow-up runs such as ablations, robustness checks, error analysis, or failure analysis after a main experiment.
Ready to connect★ 1k
- View details
ds-decisionSkillDev tools
Use when the quest needs an explicit go, stop, branch, reuse-baseline, write, finalize, reset, or user-decision transition with reasons and evidence.
Ready to connect★ 1k
- View details
ds-experimentSkillDev tools
Use when a quest is ready for a concrete implementation pass or a main experiment run tied to a selected idea and an accepted baseline.
Ready to connect★ 1k
- View details
ds-finalizeSkillDev tools
Use when the quest is ready to consolidate final claims, limitations, recommendations, summary state, and graph exports before stopping or archiving.
Ready to connect★ 1k
- View details
ds-full-pipelineSkillDev tools
Full DeepScientist research pipeline: scout → baseline → idea → experiment → analysis → optimize → write → review → finalize. End-to-end autonomous research lifecycle.
Ready to connect★ 1k
- View details
ds-ideaSkillDev tools
Use when a quest needs concrete hypotheses, limitation analysis, candidate directions, or a selected idea relative to the active baseline.
Ready to connect★ 1k
- View details
ds-reviewSkillDev tools
Use when a draft, paper, or paper-like report is substantial enough for an independent skeptical audit before finalization, rebuttal, or revision routing.
Ready to connect★ 1k
- View details
ds-writeSkillDev tools
Use when a quest has enough evidence to draft or refine a paper, report, or research summary without inventing missing support.
Ready to connect★ 1k
- View details
inno-code-surveySkillDev tools
Acquires missing code repositories for the selected idea (Phase A) and conducts comprehensive code survey mapping academic concepts to implementations (Phase B). Outputs acquired_code_repos, updated_prepare_res, and model_survey for downstream use by inno-implementation-plan.
Ready to connect★ 1k
- View details
inno-experiment-devSkillDev tools
Creates implementation plan, writes project code with judge feedback loop, and submits final experiment run. Use after code-survey in both Idea and Plan branches.
Ready to connect★ 1k
- View details
inno-grant-proposalSkillDev tools
Help professors and researchers write, revise, adapt, and polish grant proposals for US agencies (NSF, NIH, DOE, DARPA, NASA) and Chinese agencies (NSFC 国自然). Use this skill whenever the user mentions grants, proposals, funding applications, 基金申请, 本子, R01, R21, CAREER, 面上, 青年基金, specific aims, 立项依据,
Ready to connect★ 1k
- View details
inno-idea-evalSkillDev tools
Multi-persona idea evaluation with quality gate. Evaluates ideas across 5 InnoEval dimensions (Clarity, Novelty, Validity, Feasibility, Significance) using 3 reviewer personas and a meta-review. Sits between inno-idea-generation and inno-code-survey in the Idea branch. Use after inno-idea-generation
Ready to connect★ 1k
- View details
inno-idea-generationSkillDev tools
Facilitates structured brainstorming sessions, conducts comprehensive research, and generates creative solutions using proven frameworks. Trigger keywords - brainstorm, ideate, research, SCAMPER, SWOT, mind map, creative, explore ideas, market research, competitive analysis, innovation, problem solv
Ready to connect★ 1k
- View details
inno-paper-reviewerSkillDev tools
Structured manuscript/grant review with checklist-based evaluation. Use when writing formal peer reviews with specific criteria methodology assessment, statistical validity, reporting standards compliance (CONSORT/STROBE), and constructive feedback. Best for actual review writing, manuscript revisio
Ready to connect★ 1k
- View details
inno-paper-writingSkillDev tools
Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.
Ready to connect★ 1k
- View details
inno-rebuttalSkillDev tools
Drafting and refining academic rebuttals for top-tier AI/CS conferences (NeurIPS, ICML, ICLR, CVPR, ECCV, AAAI, ARR, KDD, UAI, AISTATS, TMLR, etc.). Use this skill whenever the user needs to respond to reviewer comments, write a rebuttal, handle reviewer feedback, clarify technical misunderstandings
Ready to connect★ 1k
- View details
inno-reference-auditSkillDev tools
This skill provides reference guidance for citation verification in academic writing. Use when the user asks about "citation verification best practices", "how to verify references", "preventing fake citations", or needs guidance on citation accuracy. This skill supports ml-paper-writing by providin
Ready to connect★ 1k
- View details
news-idea-briefingSkillDev tools
Read the latest news feed results (server/data/news-results-*.json), cluster items by topic, and generate grounded research idea seeds with citations. Use when the user wants to turn their daily news into actionable ideation proposals, or when invoked by the proactive research scout (Option C).
Ready to connect★ 1k
- View details
crowi-changesetsSkillDev tools
Criteria for deciding whether to add a changeset, how to choose the bump level (patch/minor/major), how to select target packages, and commands. Read this right before committing a feature or fix when wondering "do I need a changeset for this?", or when writing the text that will appear in release n
Ready to connect★ 1k
- View details
crowi-dev-portsSkillDev tools
Mechanisms and operation for dev port assignment for parallel worktrees, the dev portal (:4300), reverse proxy, tailscale serve, and DB isolation. Read this when: the port from `pnpm dev` can't be read / you want to check from a real device (e.g. iPhone) / collab or presence won't connect / you want
Ready to connect★ 1k
- View details
crowi-orchestrateSkillDev tools
Orchestration skill intended to be called one tick at a time via /loop from the main session. (A) Back up worktrees that have become ready for merge and integrate them with integrate-worktree, (B) Groom specs/ and report items ready to start, missing elements, and deletion candidates, (C) When work
Ready to connect★ 1k
- View details
crowi-pr-receivedSkillDev tools
A skill that standardizes the workflow when an external GitHub PR arrives: triage → classification → response decision → (post-approval) response/merge. Never checks out or runs scripts from others' code—triage is completed solely via remote diffs through gh, and all outward-facing operations such a
Ready to connect★ 1k
- View details
crowi-reviewSkillDev tools
A one-shot review skill that uses Codex as an adversarial reviewer to review a specified scope (worktree diff / direct work on main / area) and report findings (if main is clean, low-risk fixes are applied on the spot). Findings are reported with an unverified tag without prior full verification, an
Ready to connect★ 1k
- View details
crowi-role-managerSkillDev tools
A role-startup skill that runs once when starting/restarting a session with the manager role in crowi. It restores in a single command: agmsg actas, inbox checks, awareness of active worktrees/signals, re-establishing resident watchers, and loading the role contract. Actual work (kickoff, integrate,
Ready to connect★ 1k
- View details
card-quoteSkillDev tools
Generates 16:9 landscape quote cards and data cards suitable for sharing on Weibo, Zhihu, WeChat Official Accounts, or X/Twitter. Use when the user says "make a quote card, quote card, data card, landscape share card". For Xiaohongshu vertical knowledge cards use card-xiaohongshu; for vertical marke
Ready to connect★ 1k
- View details
infographicSkillDev tools
Turns data or text content into visual infographics, supporting both static (AntV) and animated GIF modes. Invoke when the user needs to create infographics, data visualizations, flowcharts, comparison charts, animated charts, GIF charts, mind maps, or SWOT analysis diagrams. Renders infographics/GI
Ready to connect★ 1k
- View details
post-formatterSkillDev tools
Structures topics into social media posts using classic frameworks such as PAS, AIDA, BAB, STAR, and SLAY. 200-250 words, within 20 lines, mobile-friendly formatting. Suitable for long-form posts on WeChat Official Accounts, Zhihu, Weibo, LinkedIn, etc. Use when the user says "用 PAS 写", "AIDA 框架", "
Ready to connect★ 1k
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
55,111 of the 55,543 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.