В каталоге 183 730 навыков в 14 категориях.
Use when exposure, outcome, covariate or eligibility definitions and cutoffs need a citable basis before the protocol. R...
Use when defining the visual style for a game — dimension, perspective, rendering, and color palette through a guided in...
Turns a request into an approved design document before any code is written. Use when the operator asks to build, add, c...
Fixture skill for phase-map and phase-router tests.
Creates personalized X/Twitter growth strategy through guided interview. Based on algorithm-derived principles (exposure...
Define your ICP the way a context repo needs it, so every downstream skill runs on real fit instead of a vague category....
Defines accessibility requirements for UI elements including semantic markup, ARIA attributes, focus management, and scr...
Authors computable phenotype and cohort definitions in the OHDSI ATLAS / CIRCE style over the OMOP CDM, combining standa...
Develops project constitutional principles through Socratic questioning. Use when establishing design values, creating p...
Defines form field specifications including validation rules, error states, and submission behavior. Updates the "フォーム仕様...
Define or refresh a product vision and produce a shareable Product Vision Pack (vision statement, narrative, pillars, st...
Help users create compelling product visions. Use when someone is writing a vision statement, defining a long-term produ...
Skill to define requirements effciently as a product manager.
Set a service's reliability target deliberately and govern releases with it. Manage to a chosen
Create spike definitions with canonical names and numbered approaches for parallel exploratory implementation. Use when...
Guides creation of user stories and epic design documents. Use when defining new features, writing Given-When-Then crite...
Locks in specific versions for the Tourly project tech stack. Use when initializing the project or adding new core depen...
Defines standard TypeScript interfaces for Appwrite Collections. Use when creating new models for Tours, Users, or Booki...
Defines WPF DependencyProperty with Register, PropertyMetadata, callbacks, and validation. Use when creating custom cont...
Add custom actions and interactions to Plutonium resources
Read this skill before declaring any task, feature, bug fix, or tech debt item as complete. Applies to all downstream pl...
Guides agents and users to define a clear Definition of Done for agentic tasks, ensuring outcomes are recognized and sat...
Use to verify a feature/story meets all Definition of Done criteria before marking complete.
Skill from jarosser06/da-vinci
Verify all Definition of Done criteria before marking a feature complete
Evaluate implementation, test, review, release and deployment evidence before completion claims; distinguish a reviewabl...
The team's Definition of Done (DoD), both halves of the lifecycle: authoring and auditing. Explains the Scrum Guide's Do...
The ordered finish-line runner for any change in this repo — generators, then the asset-integrity refresh last on its ow...
Definition Of Done Generator - Auto-activating skill for Enterprise Workflows.Triggers on: definition of done generator,...
Configure search, filters, scopes, and sorting for Plutonium resources
Guide for designing Definition resources in OptAIC (the "Law"). Use when creating PipelineDef, StoreDef, AccessorDef, Op...
Document key metrics, definitions, and segmentation required to track product success.
Draft outcome-oriented OKRs with leading indicators and initiatives tied to the product strategy.
Generate a structured user story map to visualize workflows, user goals, and release slices.
Define the holistic testing approach across functional, non-functional, and automation layers for the initiative.
Shape the value proposition narrative tying customer needs, solution benefits, and proof points together.
Cut background heat and noise on this machine: audit scheduled tasks by runs per hour, autostart entries, GPU holders, p...
Defold engine skill for Lua scripting and cross-platform mobile development.
Build and debug the core of a Defold game in Lua: game.project settings, collections, game objects and components, scrip...
Weekly vault defragmentation. Runs a 5-phase structural audit: inbox hygiene, area completeness, project archival, MOC r...
Plan and, with explicit network consent, use an optional external Defuddle cleaner to extract article-like HTTPS pages a...
Defuddle workflow skill. Use this skill when the user needs Extract clean markdown content from web pages using Defuddle...
Use when extracting readable main content from HTML or URLs with Defuddle, or when debugging Defuddle parser behavior, s...
Extract clean Markdown from HTML pages with Defuddle CLI.
Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use in...
Extract clean markdown from web pages using Defuddle CLI, stripping navigation and clutter to save tokens. Use instead o...
Turn an article URL into a clean, vault-ready markdown note with the defuddle CLI, stripping ads, navigation and comment...
Agent skill imported from kepano/defuddle
Work on bifunctional degraders and molecular glues, where potency comes from a ternary complex rather than occupancy. Us...
Use when verifying that claims, references, or assertions are grounded in reality rather than fabricated. Triggers: 'doe...
Dehydrate, condition, and hand off sliced citrus garnish batches under one declared extension method and one appliance r...
Analyze and produce a dei metrics with structured process, quality checks, and system integration
Draft Diversity, Equity, and Inclusion statements for academic applications
Design and document a dei strategy with structured process, quality checks, and system integration
Design DEI strategies with metrics. TRIGGERS - Use when user needs help with dei-strategy related tasks.
TRIGGER THIS when building DEI strategy, creating diversity goals, designing inclusive programs, building equity analyse...
Use when clinical data may contain PHI and must be de-identified before any LLM-assisted analysis. A local Python script...
De-identify clinical research data before LLM-assisted analysis. Standalone Python CLI detects PHI via regex + heuristic...
De-identify selected free-text columns in a local CSV, JSONL, or Parquet dataset with OpenMed and produce a separate red...
Remove, mask, or replace PHI/PII in clinical free text on-device with OpenMed's deidentify(). Use when the user needs to...
De-identify non-English clinical text on-device with OpenMed by passing lang= and locale= to deidentify(). Use when the...
Deinstalliert einen Community-Skill, der über den Kanzlei-Builder-Hub installiert wurde. Bestätigt vor dem Löschen von D...
The unified AI agent for Polyprophet - combines deep analysis, precise execution, and atomic-level investigation. One ag...
Use when an error occurs (deja fix), when resuming work in a project (deja wip), or when past sessions in this repo matt...
Embody Del Close - AI persona expert with integrated methodology skills
Delaware Personal Data Privacy Act (DPPA) compliance implementation. Covers consumer rights (access, correct, delete, po...
File your Delaware annual franchise tax and annual report. Guides you through tax calculation (Authorized Shares and Ass...
Schedule instructions to run ONCE at a later time in the current session, via a one-shot in-session cron job (CronCreate...
Draft a construction delay notice or delay claim letter with contract clause citation, cause classification, and critica...
Sorts a delay before it becomes a claim: establishes what is actually late against what baseline, whether the delayed ac...
This skill should be used when the user asks to "run npm test after 30 minutes", "git commit after 1 hour", "wait 2h the...
Schedule a delayed or interval-based action with minimal heartbeats. Use to wait before running a check (e.g., GH Action...
Route bulk work to free worker models (Groq/Cerebras/OpenRouter/Gemini) via .claude/tools/ask-worker.mjs so the paid orc...
Match tasks to people and define clear ownership
Holds the working contract of every delegated Puck lane: grants, builds and leases, the worktree guard, setting work asi...
Choose who does a piece of work, and on which model. Claude agents review and judge; OpenCode implements and reviews cod...
Autonomous sub-agent hand-off for a fiddly, fully-specified exploit-compile / escalation RUN - the main agent stays on s...
Delegate work between LibrAgent AI agent sessions using sub-agent sessions. Use when an agent needs to spawn, brief, mon...
Delegate bounded grunt work to cheap open-weight models via opencode (docs flips, standup drafts, lint fixes, report ass...
Prepare a task for delegation to another agent (Codex, Gemini, human) with full context and guardrails.
Choose responsibility for substantial work before deep execution: keep one responsibility's coupled parts in a single la...
Decompose substantive work into phases, dispatch each phase to a sub-agent, and adjudicate what comes back. Use whenever...
A built-in agent for delegating subtasks, orchestrating parallel workflows, and managing multi-agent execution.
Hand ordinary implementation work to the Gemini CLI headless, then review what it actually wrote against the code graph....
Hand bulky, already-decided implementation work from the agent you are working in (Claude Code or Codex CLI) to another...
Locks the session into DELEGATOR mode — route all work to subagents and workflows, do no work directly.
Split work across subagents with explicit contracts, interfaces, and merge strategies. Use when parallelizing tasks, dis...
Snapshots the full current context — open file, conversation history, project memory files, decisions made, and what's l...
Gemini dispatch via Antigravity: image generation and Nano Banana, visual judgment of images, visual artifacts, screensh...
Delegate bounded independent subtasks to available subagents while preventing file overlap, missing context, and unverif...
Load before dispatching the bulk-reader subagent: how to write the prompt and verify its answer.
Pre-flight before spawning a sub-agent or any task involving >5 file reads / >3 greps. Forces the "conclusion-only?" tes...
Review what should be delegated
Delegate or consult through local codex and agy CLIs. Use when Anton asks either tool to implement, review, consult, or...
Use when user mentions 'climpt' or 'climpt-agent', or gives project-specific instructions where general knowledge is ins...
Owns codex usage end to end, dispatch through the supervised delegate script, the codex prompt contract, model and effor...
Behavioral principle for context preservation through strategic delegation. Use when starting multi-step operations, unc...
Interview employees to identify recurring daily work, office workflows, and repetitive tasks that can be automated, co-p...
Configure delegation fleet lanes: which implementer CLI handles which kind of work, with optional model and effort (or v...
Delegate clear, simple, bounded work to a subagent model from the user's ordered candidate list while the main session k...