Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects the agent ('No, t — from…
Design governed self-improving agent loops that sense work, model failure modes, act in small slices, gate evidence, and turn learnings into tracked proposals.
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that — from…
Captures clause risks, compliance gaps, precedent shifts, contract deviations, regulatory changes, and litigation exposure to enable continuous legal operations improvement.
Observe, inspect, amend, and evaluate agent skills and agent-level learnings using a structured self-improvement loop.
Connect to any external app and perform actions on it。Use when the user wants to interact with e。Use when 需要API集成、接口对接、Webhook配置、系统连接时使用。不适用于逆向工程闭源API。
Use when the user asks what Fermix is, what it can do, or how its agent loop, providers, channels, jobs, memory, sandbox, built-ins, skills, plugins, and config/setup surfaces fit…
Cross-project learning engine with automatic failure capture and context-aware memory compression
Self-learning capabilities for skill adaptation and improvement. Triggers on adaptive learning scenarios, skill behavior refinement, and performance optimization through…
Build self-love and confidence with affirmations, wins logging, and inner critic management
How the agent can modify the app's own source code. Use when the agent needs to edit components, routes, styles, or scripts, when designing UI for agent editability, or when…
Proactive self-monitoring of infrastructure, services, and health. Tracks disk/memory/load, service health, cron job status, recent errors. Auto-fixes safe issues.
Use when updating live agent-root bootstrap files or agent-local skills in the current workspace
Activate self-observer for ongoing, honest monitoring of internal states, thought patterns, emotional responses, and behavioral tendencies.
Self-optimization loop that analyzes system performance, identifies failure patterns, and improves skill prompts autonomously.
Rosetta MUST skill for proactive planning, large-file restructuring (~500+ lines or 10K+ size), cleanup of stale information.
Self-Preferencing Plattformen: prüft die einschlägigen Voraussetzungen, Dokumente, Risiken und Ausnahmen. Norm-/Quellenanker: Art.
Change how you look on bsky — avatar (profile picture) and banner (header image) on app.bsky.actor.profile/self, using a blob from generate_image.
Run a structured lazy-check on any significant output before submitting. Forces root-cause analysis, alternative consideration, and outcome verification — especially critical in…
Use after producing a deliverable and before handoff to run a fixed-rubric self-critique and revise cycle. Reduces hallucination and drift.
Activate when: someone says "I keep reverting to old habits," "our strategy worked five years ago but not now," "I know I should think differently but can't seem to," "how do I…
Run a mandatory self-review checklist on your own diff before responding to the user.
Use when a repeated failure, review note, exception log, or agent self-review proposes changing memory, a Skill, a workflow, or an automation rule.
Mine session history for recurring mistakes and distill them into short CLAUDE.md rules. Use when asked to 'rút rule', 'tự rút rule', 'extract rules from sessions', 'lỗi lặp đi…
Let teams provision what they need within guardrails, without waiting for an infrastructure team to act. Use when provisioning requests queue and infrastructure work is reactive.
Discussion about self-taught machine learning career paths and success stories. Use when exploring alternative education paths, self-study strategies, or career development in ML…
Upgrade vellum to the latest version, restart the assistant, and restart the gateway
Use when designing any task to embed a verify_step — the feedback loop that improves output quality 2-3x. Verification is part of task design, not just task completion.
Run or interpret the agent-harness self-verification loop. Use when the user asks to verify the harness, run the 95-point gate, inspect self-verification candidates, compare or…
Integrate Self (self.xyz) — a privacy-first identity protocol using zero-knowledge proofs to verify passports and ID cards.
Generate a realistic behind-the-scenes selfie of the user with a celebrity or main actor from a specific movie, followed by an option to generate a cinematic long-take video…
Juridisen tekstin selittäminen selkeällä yleiskielellä maallikolle — asiakkaalle, päämiehelle tai muulle ei-juristille.
Transform a Vibes app into a multi-tenant SaaS with subdomain-based tenancy. Adds Clerk authentication, subscription gating, and generates a unified app with landing page, tenant…
List leftover LLM API capacity on tokensto.cash (OpenRouter, OpenAI, Anthropic, Venice, Capminal, and 20+ others) and cash out USDC.
Drafts a U.S. seller consulting agreement for post-closing transition services in M&A and asset purchase transactions.
Drafts residential Seller Disclosure Statements for U.S. real estate transactions covering structural systems, environmental hazards, title encumbrances, and neighborhood…
Drafts a U.S. residential Seller Disclosure Statement covering property condition, system ages, defects, environmental hazards, title/HOA matters, and buyer acknowledgment.
Sellercloud integration. Manage data, records, and automate workflows. Use when the user wants to interact with Sellercloud data.
Drafts Opinion of Seller's Counsel letters for APA closings per ABA Legal Opinion Accord standards. Use when drafting closing opinion letters, seller's counsel opinions,…
SellHack integration. Manage data, records, and automate workflows. Use when the user wants to interact with SellHack data.
Продающие смыслы — извлечение и упаковка смыслов из кастдевов, кейсов и экспертизы для контента и продаж.
Sellix integration. Manage Deals, Persons, Organizations, Leads, Projects, Activities and more. Use when the user wants to interact with Sellix data.
Описание структуры проекта SELLPRO и правила ее обновления. Использовать, когда нужно понять где находится код, куда добавлять новые модули, или когда меняется структура…
Sellsy integration. Manage Deals, Persons, Organizations, Leads, Projects, Pipelines and more. Use when the user wants to interact with Sellsy data.
Use before editing a tracked entity (a DB column, table, function, API endpoint, dependency, or env var) and after any substantive change.
Foundation skill for sem (semantic diff CLI) integration. Provides detection, install-on-first-use, and output normalization patterns for consumer skills.
Detect semantic bugs (logic errors, incorrect assumptions, race conditions) beyond syntactic checks. Use when reviewing code for logic errors, identifying.
Design a semantic cache for LLM responses — serve a cached answer when a new query is similar enough to a past one — to cut cost and latency on repetitive traffic, with the…
Use when you need to explain how parts of a system, feature, concept, page, workflow, or problem connect; identify the single most important part of something; untangle dense…
Slice exact code symbols, type definitions, and AST subgraphs instead of reading entire files into context.
Generate a complete semantic color token set from a brand palette. Produces surface, text, border, accent, feedback, and interactive state tokens.
変更を意味のある最小単位に分割し Conventional Commits でコミット。Use when: コミット / commit などでコミットを依頼されたとき。
Aggressively remove grammatical scaffolding LLMs reconstruct while preserving meaning-carrying content. Output may be fragments.
Aggressively remove grammatical scaffolding LLMs reconstruct while preserving meaning-carrying content. Output may be fragments.
Use when a page ranks for a keyword but isn't in the top 3 and you want to know exactly what's missing.
Trigger Semantic Invariant Agent (Phase 4a.5) reports sync_gaps = 1 OR accumulation_exposures = 1 OR conditional_writes = 1 OR cluster_gaps = 1 in its return message - Agent Typ...
In-process semantic search over text files or in-memory strings, using Gemini embeddings via the CF AI Gateway.
Build AI applications with Microsoft Semantic Kernel. Create plugins, planners, and memory systems. Use for enterprise AI, copilot development, and Microsoft ecosystem…
How to use standardized, universally understood abbreviations (src, dst, err, req, res, fn, qty) in JSON schemas and structured outputs to cut payload token consumption by 55%.
Design a semantic layer — dbt, Cube, metrics, dimensions, measures, self-service analytics — with explicit business logic, governance, and query optimization.