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: Docs & knowledge
4,502 results · page 110 of 151
- View details
push-releaseSkillDocs & knowledge
Cut a Fred release on the current release branch — write user-facing release notes for every change since the last tag, then (after developer sign-off) tag code/vX.Y.Z + chart/vX.Y.Z and push. Stops for approval before any tag is placed.
Ready to connect★ 62
- View details
red-hat-docsSkillDocs & knowledge
Draft, rewrite, or audit modular enterprise technical documentation using an independently expressed interpretation of the Red Hat supplementary style guide. Use for administration, installation, configuration, security, troubleshooting, procedures, concepts, and references that must be precise, reu
Ready to connect★ 62
- View details
retrospectiveSkillDocs & knowledge
After completing a significant task or experiment, documents what worked, what failed, and key learnings. Activates when a multi-step task finishes or when user says "done", "finished", "that worked", or asks for a summary. Failed attempts get documented first - they're read more than successes.
Ready to connect★ 62
- View details
safe-refactorSkillDocs & knowledge
When refactoring, rewriting, or migrating critical code paths, orchestrate a safe cycle: assess risks → implement → verify → document. Chains pre-mortem and prove-it with built-in implementation phase. Prevents "refactor broke production" disasters. Activates on "refactor", "rewrite", "migrate", or
Ready to connect★ 62
- View details
slangSkillDocs & knowledge
Chinese internet slang/buzzwords — look them up in real time and use them naturally. Use when the user wants to add a modern, online feel to a novel, wants to know what memes are trending on Douyin/Xiaohongshu (RedNote)/Weibo/Bilibili, asks whether a meme is still popular, or worries that 'adding me
Ready to connect★ 61
- View details
w3c-technical-reportsSkillDocs & knowledge
Draft, restructure, or audit specification-style technical reports using an independently expressed reference-only interpretation of W3C editorial guidance. Use for protocols, standards, interoperability documents, conformance requirements, and technical specifications that must separate normative r
Ready to connect★ 62
- View details
<kebab-case-skill-slug>SkillDocs & knowledge
<one sentence — the procedural / framing gap this skill closes for *this class of work* (e.g., "reviewing corporate authorization documents for a credit-facility closing across multi-entity, multi-jurisdiction guarantor groups"). Do not mention specific dollar amounts, percentages, named entities, v
Ready to connect★ 61
- View details
analyze-antitrust-hsr-strategySkillDocs & knowledge
Closes gaps in product-market separation, geographic-market framing, hot-document identification, and HSR filing strategy memo production for acquisition antitrust review.
Ready to connect★ 61
- View details
analyze-iss-antitrust-transaction-structureSkillDocs & knowledge
Closes gaps in deal-structure antitrust risk analysis including hell-or-high-water provision adequacy, reverse termination fee sufficiency, outside date feasibility, and hot-document identification.
Ready to connect★ 61
- View details
Argument Chain ConstructionSkillDocs & knowledge
Triggers when an AI agent needs to organize legal reasoning results into a complete, self-consistent, and persuasive argumentation structure. Typical trigger scenarios include but are not limited to: - drafting the argumentation sections of legal documents such as legal opinions, representation stat
Ready to connect★ 61
- View details
Case MemoSkillDocs & knowledge
Case work notes: full-process generation and management of core case working documents, integrating case facts, legal issues, to-dos, and pre-trial preparation
Ready to connect★ 61
- View details
code2patentSkillDocs & knowledge
Extracts technical implementation evidence from developed code projects, generates algorithm/software specification-style technical disclosure documents around candidate patent solutions, and then continues with a two-step approach — "claim layout card → invention patent draft" — to produce drafting
Ready to connect★ 61
- View details
comic-cross-layer-gateSkillDocs & knowledge
The ONE parameterized score-fuser for EVERY comic-author authoring gate — `--gate intent|outline|asset|storyboard|blueprint|continuity|p0_proof|compile`. A single fuser (not a per-layer split) prevents drift. It NEVER re-runs a reviewer; it collects the reviewer score-nodes already on the wiki (via
Ready to connect★ 61
- View details
comic-intent-parserSkillDocs & knowledge
Phase-1 Layer-0 of the comic-author suite — turn ANY raw idea / a locked video skeleton / an audience note into ONE schema-valid intent_spec node that fixes the logline (an editorial climax), the tagline, and the named DUAL-IDENTITY design constraint the whole comic optimizes against. Codex-as-parse
Ready to connect★ 61
- View details
compare-document-production-requests-against-redfern-scheduleSkillDocs & knowledge
Supports a gap analysis memorandum that compares document production requests against response schedules, checking both structure and substance while avoiding instance-specific conclusions.
Ready to connect★ 61
- View details
court-smsSkillDocs & knowledge
This skill should be used when the user receives a court SMS (document service, case filing notice, hearing reminder, etc.). It automatically extracts the case number, parties, and download links, downloads the documents, and archives them in the corresponding case directory.
Ready to connect★ 61
- View details
cv-center-z-slice-selectionSkillDocs & knowledge
Select a fixed number of Z-slices centered around the volume midpoint for memory-efficient 2.5D input from 3D CT/MRI stacks
Ready to connect★ 61
- View details
cv-histopathology-image-inversionSkillDocs & knowledge
Inverts whole slide image pixel values (1 - x) so white background becomes zero, enabling standard zero-padding and making tissue regions the active signal.
Ready to connect★ 61
- View details
cv-mixed-precision-trainingSkillDocs & knowledge
Uses PyTorch AMP autocast and GradScaler for FP16 training, halving memory usage and speeding up training on modern GPUs.
Ready to connect★ 61
- View details
cv-slice-as-channel-2d-cnnSkillDocs & knowledge
Resample a 3D medical volume to a fixed depth N (e.g. 32) and feed the N slices as input *channels* to a 2D CNN with `in_chans=N` instead of using a 3D conv backbone — gets the volumetric context for a fraction of the memory and lets you use any timm 2D pretrained model
Ready to connect★ 61
- View details
Data Compliance AI R&DSkillDocs & knowledge
Supports R&D work on the fixed project “数据合规AI项目 / 数据合规与AI应用探讨” (Data Compliance AI Project / Data Compliance and AI Application Discussion): driving progress, narrowing scope, knowledge base design, workflow prototyping, validation criteria, consolidating meeting conclusions, and syncing notes with
Ready to connect★ 61
- View details
Deductive ReasoningSkillDocs & knowledge
Performs rigorous legal deductive reasoning based on formal logic, used to verify the formal validity of legal arguments. Invoke when the user explicitly asks to 'analyze case logic', 'verify legal reasoning', 'extract syllogisms', or 'assess the validity of a legal argument'. Note: this skill outpu
Ready to connect★ 61
- View details
draft-antitrust-competition-pre-notificationSkillDocs & knowledge
Supports pre-notification briefing papers for cross-border merger control by structuring multi-jurisdiction filing analysis, vertical foreclosure review, gun-jumping risk screening, and privilege-aware document handling.
Ready to connect★ 61
- View details
draft-antitrust-complaintSkillDocs & knowledge
Draft a federal antitrust complaint by pleading plausible facts, tying allegations to source documents at a categorical level, organizing claims by theory of liability, and requesting appropriate relief.
Ready to connect★ 61
- View details
draft-expert-report-on-construction-delay-and-damagesSkillDocs & knowledge
Ensures a construction delay expert report conducts a proper concurrency analysis, applies the relevant home office overhead methodology correctly, resolves float ownership under the contract, and logs all cross-document inconsistencies.
Ready to connect★ 61
- View details
draft-market-definition-analysis-memorandumSkillDocs & knowledge
Closes gaps in narrow vs. broad product market analysis, buyer-side harm, and hot-document identification in strategic planning market definition memos.
Ready to connect★ 61
- View details
draft-objections-to-document-production-requestSkillDocs & knowledge
Ensures document production objections in a fund-related arbitration address confidentiality concerns with nuance, identify possible open-records exposure for certain institutional investors, and avoid blanket refusals by pairing each objection with a counter-proposal.
Ready to connect★ 61
- View details
draft-response-to-investigative-subpoenaSkillDocs & knowledge
Closes gaps in the three-deliverable structure, objection framework, sensitive document flagging, and complete privilege log format requirements for a government investigative subpoena response.
Ready to connect★ 61
- View details
draft-response-to-second-request-for-informationSkillDocs & knowledge
Closes gaps in market-concentration analysis, hot-document identification with mandatory internal-document production, serial-acquisition risk analysis, spoliation assessment, and timing-model review.
Ready to connect★ 61
- View details
Evidence-Argument ChainSkillDocs & knowledge
Triggers when multiple pieces of evidence in a case need to be systematically mapped to legal argumentation claims. Typical trigger scenarios include: building a complete evidence-to-claim correspondence when drafting litigation documents (complaints, statements of defense, representation opinions);
Ready to connect★ 61
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.
53,789 of the 54,221 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.