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: AI & models
9,019 results · page 61 of 301
- View details
hephaestus-networkSkillAI & models
Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit
Ready to connect★ 1k
- View details
llm-runtime-architectureSkillAI & models
Use when designing how one canonical agent core runs across Codex, Claude Code, Gemini CLI, Cursor, and AGENTS.md-compatible tools.
Ready to connect★ 1k
- View details
public-plugin-packagingSkillAI & models
Use when packaging this meta-agent for public Codex plugin registration, Claude Code installation, GitHub release, one-line terminal install, or open-source distribution.
Ready to connect★ 1k
- View details
routing-card-authoringSkillAI & models
Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leak
Ready to connect★ 1k
- View details
runtime-adaptersSkillAI & models
Use when creating Codex, Claude Code, Gemini CLI, Cursor, or AGENTS.md runtime adapters from one canonical agent core. Use whenever a generated repo needs multiple AI runtimes without duplicating instructions.
Ready to connect★ 1k
- View details
self-evolving-single-agentSkillAI & models
Use when generating a single installable agent that should keep learning, track sources, refresh research, propose repairs, or improve itself over time without becoming a multi-agent team.
Ready to connect★ 1k
- View details
session-agent-builderSkillAI & models
Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit terminal and automation runs.
Ready to connect★ 1k
- View details
aamas-related-workSkillAI & models
Use when positioning an AAMAS submission against multiagent, game-theory, and reinforcement-learning literature spread across AAMAS, AAAI, IJCAI, NeurIPS, ICML, EC, and JAAMAS, including arXiv and workshop versions, concurrent submissions, prior conference versions, and the cross-community citation
Ready to connect★ 1k
- View details
aamas-reproducibilitySkillAI & models
Use when strengthening AAMAS reproducibility evidence for interaction claims, including proofs and game definitions, opponent and population sets, self-play protocols, random seeds, compute, uncertainty on strategic outcomes, baselines, and consistency between what the paper claims about agents and
Ready to connect★ 1k
- View details
aamas-supplementarySkillAI & models
Use when preparing AAMAS supplementary material - proofs, extended game and mechanism definitions, extra multiagent experiments, opponent-set details, and the anonymized artifact zip - under the size cap, anonymity, and reviewer-discretion limits, including how to split a game-theory-plus-experiment
Ready to connect★ 1k
- View details
aamas-topic-selectionSkillAI & models
Use when deciding whether a project is a strong AAMAS fit, comparing AAMAS with AAAI, IJCAI, NeurIPS, ICML, EC, and the JAAMAS journal, identifying whether the agents are truly the research object, naming the interaction primitive (solution concept, mechanism, coordination, negotiation), and sharpen
Ready to connect★ 1k
- View details
aamas-writing-styleSkillAI & models
Use when revising an AAMAS paper so the interaction contribution leads the first page, the solution concept or incentive property is named, the game and agents are legible, claims are paired with proofs or multiagent experiments, the argument fits eight two-column pages plus references, and the word
Ready to connect★ 1k
- View details
acl-related-workSkillAI & models
Use when positioning an ACL submission against the NLP literature, covering ACL Anthology citation practice, arXiv-versus-published version citation, concurrent LLM-era preprints, prior-cycle ARR resubmission overlap, anonymity-preserving self-citation, and the fast-moving baseline problem in comput
Ready to connect★ 1k
- View details
acl-reproducibilitySkillAI & models
Use when strengthening reproducibility evidence for an ACL paper reviewed through ACL Rolling Review, covering the Responsible NLP checklist end to end, hyperparameter and compute reporting, prompt and decoding disclosure for LLM experiments, data contamination auditing, variance across runs, and ch
Ready to connect★ 1k
- View details
aeja-robustnessSkillAI & models
Use when an American Economic Journal: Applied Economics (AEJ: Applied) manuscript's headline estimate must be shown to survive specification, sample, and inference choices before submission or in an R&R. Builds the robustness suite a sophisticated referee expects; it does not establish the primary
Ready to connect★ 1k
- View details
aejmac-rebuttalSkillAI & models
Use when an American Economic Journal: Macroeconomics (AEJ: Macro) decision letter has arrived (R&R or reject-with-comments) and you need a response-letter strategy and revision plan. Plans the rebuttal and revision; it does not run new identification, model, or robustness work itself (route to thos
Ready to connect★ 1k
- View details
aejmac-tables-figuresSkillAI & models
Use when building or revising exhibits for an American Economic Journal: Macroeconomics (AEJ: Macro) manuscript — impulse-response figures, fan charts, model-fit overlays, and regression/moment tables — to AEA house standards and macro conventions. Formatting and clarity; it does not generate the un
Ready to connect★ 1k
- View details
aejmac-theory-modelSkillAI & models
Use when the quantitative model is the bottleneck for an American Economic Journal: Macroeconomics (AEJ: Macro) manuscript — DSGE, New Keynesian, heterogeneous-agent (HANK / Aiyagari-Bewley), or structural estimation — and calibration, parameter identification, solution accuracy, or counterfactual v
Ready to connect★ 1k
- View details
aejmac-writing-styleSkillAI & models
Use when revising prose, the abstract, or the introduction of an American Economic Journal: Macroeconomics (AEJ: Macro) manuscript for AEA house style and the broad-interest macro arc. Late-stage polish on framing and clarity; it does not fix identification, the model, or exhibits.
Ready to connect★ 1k
- View details
aejmic-literature-positioningSkillAI & models
Use when the contribution of an American Economic Journal: Microeconomics (AEJ: Micro) manuscript is fuzzy or oversold relative to the closest existing results. Stakes the theorem-relative delta against the nearest theory; it does not build the model (see aejmic-theory-model) or frame the prose (see
Ready to connect★ 1k
- View details
aejmic-rebuttalSkillAI & models
Use when drafting the response letter and revision plan after an American Economic Journal: Microeconomics (AEJ: Micro) R&R. Structures the reply to theory referees (correctness, generality, exposition) and editor; it does not re-derive the result (see aejmic-theory-model).
Ready to connect★ 1k
- View details
aejmic-tables-figuresSkillAI & models
Use when presenting results for an American Economic Journal: Microeconomics (AEJ: Micro) manuscript — propositions, numerical examples, schematic theory figures, and empirical/experimental tables. Builds exhibits to AEA house norms; it does not derive the results (see aejmic-theory-model).
Ready to connect★ 1k
- View details
aejmic-theory-modelSkillAI & models
Use when the model setup, equilibrium concept, or proof architecture is the bottleneck for an American Economic Journal: Microeconomics (AEJ: Micro) manuscript — the central skill for a theory-first paper. Builds the model to the AEJ: Micro bar (clean, general, well-motivated result); it does not ch
Ready to connect★ 1k
- View details
aejmic-topic-selectionSkillAI & models
Use when deciding whether a microeconomics project fits the American Economic Journal: Microeconomics (AEJ: Micro) rather than JET, GEB, Theoretical Economics, Econometrica, or AEJ: Applied. Tests scope and broad-interest fit; it does not develop the model (see aejmic-theory-model).
Ready to connect★ 1k
- View details
aejmic-writing-styleSkillAI & models
Use when prose buries the result or the abstract/intro do not land for an American Economic Journal: Microeconomics (AEJ: Micro) manuscript. Applies AEA house style and the theory-paper intro arc; it does not produce the result (see aejmic-theory-model) or build exhibits (see aejmic-tables-figures).
Ready to connect★ 1k
- View details
aejpol-theory-modelSkillAI & models
Use when an AEJ: Economic Policy manuscript needs a framework that maps reduced-form estimates into a welfare, cost-benefit, or distributional policy object — sufficient statistics, MVPF, optimal-policy, or a small applied model. Builds the estimate-to-welfare bridge and states its assumptions; it d
Ready to connect★ 1k
- View details
aeri-referee-strategySkillAI & models
Use when calibrating expectations for the fast, decisive American Economic Review: Insights (AER: Insights) review process — conditional-accept-or-reject decisions, the single-round model, and pre-empting the objections a short paper cannot afford. Explains the process and stress-tests the paper; it
Ready to connect★ 1k
- View details
aeri-theory-modelSkillAI & models
Use when a model — a full theory paper's argument or the structural/conceptual scaffolding behind an empirical AER: Insights short-format manuscript — needs to be made minimal, so it carries the single insight in a few pages. Keeps only what the insight requires; it does not develop a general framew
Ready to connect★ 1k
- View details
ase-reproducibilitySkillAI & models
Use when building the open-science and reproducibility story for an ASE (IEEE/ACM Automated Software Engineering) submission, covering the mandatory Data Availability Statement, anonymized-but-runnable tools, tool and subject-system provenance pinning, cached LLM outputs, and staging for the ACM Ava
Ready to connect★ 1k
- View details
ai-model-wechatSkillAI & models
Use this skill for WeChat Mini Program AI via wx.cloud.extend.AI (小程序, 企业微信小程序, wx.cloud apps). Features generateText and streamText with callbacks (onText, onEvent, onFinish). Models via wx.cloud.extend.AI.createModel with groups hunyuan-exp (小程序成长计划), cloudbase (main managed), or custom-*. Model I
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.
54,764 of the 55,196 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.