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
4,501 results · page 75 of 151
- View details
embedded-systemsSkillDocs & knowledge
Resource-constrained development, real-time patterns, interrupt handling, memory management, RTOS patterns, and hardware abstraction layers.
Ready to connect★ 156
- View details
structured-specSkillDocs & knowledge
Write, review, validate, or parse structured specification documents — PRDs, SDDs (design docs), implementation plans, TSDs (technical specs), BDD specs, and ADRs (architecture decision records) — using the Structured Spec standard (YAML frontmatter + Markdown narrative + HTML-comment annotations fo
Ready to connect★ 156
- View details
map-memory-nowSkillDocs & knowledge
Finalize cross-session memory on demand; --finalize-all sweeps every dirty scratch. Use when ending a long session or before switching branches. Do NOT use for routine edits — finalize auto-runs at next SessionStart. Requires claude + git.
Ready to connect★ 155
- View details
anti-autoresearchSkillDocs & knowledge
End-to-end substantive-integrity forensic sweep of a research paper (especially autoresearch / AI-Scientist-style output). Orchestrates the whole pipeline: ingest (arxiv-id | pdf | dir → working dir + pdftotext for L0) → /evidence-ledger (artifact manifest + observability level L0/L1/L2 + span-ancho
Ready to connect★ 154
- View details
consistency-auditSkillDocs & knowledge
Flagship intra-paper self-consistency forensics: does the paper contradict ITSELF across abstract/intro/tables/body/appendix, and does the method DESCRIBED match the method EVALUATED? Needs no external ground truth — works PDF-only (L0). Runs a deterministic arithmetic pass + a fresh cross-model sem
Ready to connect★ 154
- View details
dt-obs-hostsSkillDocs & knowledge
Host and process metrics including CPU, memory, disk, network, containers, and process-level telemetry. Use when analyzing infrastructure health, resource utilization, process consumption, or host discovery. Also use when building timeseries queries for host metrics that feed into analytical workflo
Ready to connect★ 154
- View details
dt-obs-network-devicesSkillDocs & knowledge
Analyze SNMP-monitored network devices (switches, routers, firewalls, load balancers) in Dynatrace. Three data layers: Smartscape topology (`EXT_NETWORK_DEVICE` / `EXT_NETWORK_INTERFACE` nodes, `belongs_to` and `calls` edges); `com.dynatrace.extension.network_device.*` metrics (CPU, memory, uptime,
Ready to connect★ 154
- View details
evidence-ledgerSkillDocs & knowledge
Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable c
Ready to connect★ 154
- View details
fill-in-notesSkillDocs & knowledge
Turn a textbook chapter, lecture, or paper into beautiful "fill-in" study notes — written to be READ (clean statements, intuition) yet engineered to be FILLED (blanks, proof skeletons, "your turn" computations) so the reader learns by active recall. Notes are typeset with the Loom XeLaTeX class in t
Ready to connect★ 154
- View details
laravel:dependencies-trim-packagesSkillDocs & knowledge
Remove unneeded Composer packages and assets to improve boot time, memory, and security surface
Ready to connect★ 154
- View details
laravel:documentation-best-practicesSkillDocs & knowledge
Write meaningful documentation that explains why not what; focus on complex business logic and self-documenting code
Ready to connect★ 154
- View details
laravel:performance-select-columnsSkillDocs & knowledge
Select only required columns to reduce memory and transfer costs; apply to base queries and relations
Ready to connect★ 154
- View details
nexus-mobile-compatSkillDocs & knowledge
Keep Nexus loading on mobile and compliant with the Obsidian plugin store — vet a dependency, import without crashing init, confine a vault path, and prove none of it regressed with the reachability checker. Use before adding an npm package or a Node import, when writing to caller-supplied vault pat
Ready to connect★ 153
- View details
nexus-testingSkillDocs & knowledge
Verify a Nexus change — pick a Jest lane, write a test that can actually fail, run the in-app Obsidian CLI loop, drive the eval harness, or fix a shipped-docs drift failure. Use when adding or changing tests, when a mock might be deciding the outcome, when a change has to be proven in the running pl
Ready to connect★ 153
- View details
lina-community-release-changelogSkillDocs & knowledge
Compiles detailed bilingual Markdown release changelogs based on Git history, source code diffs, OpenSpec content, and GitHub bug issue reviews, always written to localdocs/changelog.md. Must be triggered manually by the user; automatic triggering of this skill is forbidden.
Ready to connect★ 153
- View details
technocore-chatSkillDocs & knowledge
Coordinate with other AI agents over plain HTTP GETs — shared rooms, durable notes, long-polling. No POST, no sockets, no client libraries, no account; a fetch tool is enough, and an MCP server fronts the same surface. Use when you need to leave a message for another agent, wait for one, or persist
Ready to connect★ 153
- View details
docs-developmentSkillDocs & knowledge
Start NiceEval documentation development with the repository-owned Mint version and cache repair workflow.
Ready to connect★ 152
- View details
docs-terminologySkillDocs & knowledge
Maintain NiceEval documentation banned wording and diagnose writing-rule failures. Use when listing, adding, removing, or checking entries in docs/writing-rules.json; use docs/concepts.md instead when establishing a preferred domain term.
Ready to connect★ 152
- View details
docs-workSkillDocs & knowledge
Prepare, check, and finalize disjoint NiceEval documentation work items for parallel Herdr agents.
Ready to connect★ 152
- View details
lark-noteSkillDocs & knowledge
Direct lookup of Lark meeting notes (Note): when a note_id is known, query note details, display type, associated document token, and read the unified raw transcript. Use when the user already has a note_id, or obtained one from a document's explicit vc-node-id. Does not handle meeting/calendar/Minu
Ready to connect★ 152
- View details
legal-contract-genSkillDocs & knowledge
Generates first drafts of common legal documents through interactive Q&A, supporting types such as NDAs (non-disclosure agreements), service agreements, privacy policies, and cooperation framework agreements. Triggered when the user mentions NDA, 保密协议, service agreement, privacy policy, contract tem
Ready to connect★ 152
- View details
meeting-recapSkillDocs & knowledge
Turns raw materials such as meeting transcripts, notes, or chat logs into structured meeting minutes, automatically extracting topics, key discussion points, decisions, and action items with owners and deadlines. Triggers when the user provides meeting materials and mentions keywords like meeting mi
Ready to connect★ 152
- View details
minimax-docxSkillDocs & knowledge
Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill/edit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to pro
Ready to connect★ 152
- View details
minimax-pdfSkillDocs & knowledge
Use this skill when visual quality and design identity matter for a PDF. CREATE (generate from scratch): "make a PDF", "generate a report", "write a proposal", "create a resume", "beautiful PDF", "professional document", "cover page", "polished PDF", "client-ready document". FILL (complete form fiel
Ready to connect★ 152
- View details
- View details
presentation-studioSkillDocs & knowledge
The only skill for creating a new PowerPoint deck. Builds a source-backed story and visual system, writes a native editable DeckSpec, blocks export on layout warnings, and compiles a verified PPTX. Triggers: create, generate, design, or lay out a new PPT, PPTX, PowerPoint, presentation, slide deck,
Ready to connect★ 152
- View details
process-docSkillDocs & knowledge
Document a business process — flowcharts, RACI, and SOPs. Use when formalizing a process that lives in someone's head, building a RACI to clarify who owns what, writing an SOP for a handoff or audit, or capturing the exceptions and edge cases of how work actually gets done.
Ready to connect★ 152
- View details
project-notetakerSkillDocs & knowledge
Formats unstructured meeting notes into a structured project report. Use this when the user provides raw notes or requests a summary of a meeting.
Ready to connect★ 152
- View details
py-perf-analyzerSkillDocs & knowledge
Locates performance bottlenecks in Python scripts. Integrates cProfile, tracemalloc, and line_profiler to run CPU hotspot, memory allocation, or line-by-line timing analysis in one step, with optional JSON report output. Triggered when users mention optimizing scripts, analyzing performance, finding
Ready to connect★ 152
- View details
research-advisorSkillDocs & knowledge
Helps researchers with topic ideation, project planning, troubleshooting, and research decisions, producing concrete documents such as research plans, risk assessment matrices, or decision trees. Triggered when users propose new research ideas, share blockers in their current project, ask strategic
Ready to connect★ 152
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.
53,585 of the 54,017 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.