Àmbit jurídic
Generació de documents jurídics i suport al compliment normatiu
rlm-mem
zenchantlive
Use when an agent needs persistent, policy-scoped memory with strict verification gates and a single canonical package path.
negotiated-decision-framework
kimasplund
Multi-stakeholder coordination for decisions involving competing interests, different value systems, or organizational politics. Use when multiple parties must agree, when power dynamics affect decisions, or when consensus is required but perspectives diverge. Unlike DR (resolves conceptual tensions), NDF resolves stakeholder tensions.
whop-app-integration
Jpkovas
End-to-end implementation guide for adding Whop licensing to apps with a secure backend, activation flow, and webhook synchronization. Use when tasks involve Whop checkout setup, membership/license activation, validate_license integration, webhook signature verification, revocation handling, device-binding policies, or periodic license checks in Node.js, Python, iOS, or macOS apps.
expo-build-preflight
marcelocanovas
Pre-build validation for Expo and React Native apps. Use before running 'eas build --profile production' to ensure compliance with 2026 store rules (Android 15, iOS Privacy Manifests, 16KB Page Size), validate auto-increment, check environment variables, and verify Firebase/Sentry configs.
improve
widoriezebos
Chase a measured improvement goal against a benchmark or evaluation, raising a primary metric without regressing guard metrics. Use when the task is to improve something an on-demand evaluation can measure (benchmark scores, quality evals, latency or cost budgets). Do not use when no runnable evaluation exists (building one is then the first deliverable), for behavior-preserving restructuring (refactor), or for diagnosing failures (take-a-step-back).
telegram-react
paulo20223
Telegram reaction tags in replies. Use when composing any Telegram reply — add [react:<emoji>] to express a reaction to the user's message. Natural use, not just on explicit request.
compliance-automation-specialist
YPYT1
Use this agent when you need to automate compliance processes for SOC 2, ISO 27001, GDPR, HIPAA, and other enterprise regulatory requirements. This agent specializes in compliance automation, audit...
quality-manager-qmr
nimeshgurung
Senior Quality Manager Responsible Person (QMR) for HealthTech and MedTech companies. Provides overall quality system responsibility, regulatory compliance oversight, management accountability, and strategic quality leadership. Use for quality system governance, regulatory compliance oversight, management responsibility, and quality strategic planning.
briefcraft
aysegulbilgen
Turn messy inputs into structured briefs that help teams work smoothly with Marketing, and help Marketing brief agencies and designers clearly. Detect the right mode, ask missing questions, then output a Notion-style one-pager plus a Slack-ready summary.
search-first
flext-sh
"owner discovery, reusable code, architecture research"
Solana Incident Response Skill
Stan-lee13
The Solana AI Kit skill that no one wants to need — and everyone needs to have. Complete incident response lifecycle for Solana protocols.
anti-hardcode
flext-sh
"configuration ownership, portable policy, hardcode removal"
minecraft-blockbench-geckolib
Gustavaopere
Use when creating, editing, exporting, or reviewing Blockbench models, UVs, rigs, animations, or GeckoLib-backed Minecraft assets for the NeoForge 1.21.1 project.
search-first
flext-sh
"owner discovery, reusable code, architecture research"
domain-modeling
lexijamesesq
Build and sharpen a project's domain model — pin down terminology, challenge fuzzy language, record architectural decisions. Works for engineering, strategy, research, and design domains.
anti-hardcode
flext-sh
'configuration ownership, portable policy, hardcode removal'
documentation-authoring
hackycy
从已完成的代码框架、配置和工程资料建立、新增、补充或重构技术文档的信息架构、内容边界与表达方式。
architecture-finding-verifier
qingye-lab
Independently verifies candidate architecture findings against current code and repository evidence. Use after any project, AI-agent, mobile, or portfolio architecture audit; when a finding may be based on weak heuristics; or before remediation and quality gates. Filters false positives, deduplicates findings, recalibrates severity and confidence, and preserves an auditable decision trail without changing code.
gonol-build
The-Interdependency
Cross-repository construction, review, replay, and continuation discipline for gonols. Load this when realizing gonol or affixiation geometry in UCNS; when constructing character, word, morphology, definition, punctuation-function, or recursive gonols in English Gonol Construction; when deciding whether a relation belongs inside a gonol; or when promoting a completed gonol to atomic participation at another scale. Do not load for unrelated geometry, ordinary prose editing, or EDCM measurement that consumes already-closed gonols without changing their construction. Resolve METAPAT semantic authority, UCNS geometric authority, and English Gonol text-domain authority separately; never restore historical gonal-morphology, omega/phi/psi, bone/flesh, or carrier-LCM language rules.
security-review
flext-sh
"security findings, attack surfaces, dependency risk"
in-your-own-words
yotamleo-org
"Restate in your own words what you think the user's goals are and what problem they're trying to solve. Use for /in-your-own-words."
circuit-brief-rules
VibeBB
Path rule — design-brief and intake contract reminders injected whenever a .brief.json or .intake.json file is touched.
extermination-mode
flext-sh
'zero residue, contract removal, consumer rewiring'
rar-cowork-cookbook-d365-concept-to-market
kody-w
"A Dynamics 365 Finance & Supply Chain Management expert scoped to the Concept to market end-to-end process - covers 6 L2 areas and 31 L3 processes from the Microsoft Business Process Catalog."