Results for “mem”

Manages a long-term Markdown knowledge base for software projects, capturing architecture, decisions, and conventions in `.lore/` with commands to init, sync, query, audit, compress, and mirror to platform files.

Regenerate the cross-repo roadmap aggregate in your Claude memory directory by walking every curated repo's `docs/specs/**` frontmatter. Run at session start for cross-repo orientation or after any `spec-new`/`spec-ship` in any repo.

Use when building stateful multi-step agents, agent graphs, or workflows with LLMs. Triggers on: 'langgraph', 'state graph', 'stateful agent', 'agent workflow', 'agent loop', 'multi-step agent', 'persistent agent', 'human-in-the-loop agent', 'agent with memory', 'graph-based agent'.

API design specialist for REST, GraphQL, gRPC, versioning strategies, and developer experienceUse when "api design, rest, graphql, grpc, openapi, swagger, versioning, pagination, rate limiting, endpoint, api, rest, graphql, grpc, openapi, swagger, versioning, pagination, rate-limiting, ml-memory" mentioned.

Power management and performance optimization for Zephyr RTOS. Covers system power states (Idle, Suspend, Off), device-level power management, residency hooks, and code/data relocation for speed efficiency. Trigger when optimizing battery life, reducing latency, or managing memory constraints.

Analyzes bootkit and rootkit malware that infects MBR, VBR, or UEFI firmware for pre-OS persistence, covering boot sector analysis, UEFI module inspection, and anti-rootkit detection.

Shares memory between agents at the representation level by compacting the orchestrator's KV cache for efficient worker handoff, reducing token costs without summarization or retrieval.

Quantize large language models to 4-bit with minimal accuracy loss using GPTQ, enabling deployment of 70B+ models on consumer GPUs with 4× memory reduction and 3-4× faster inference.

Integrate Honcho memory and social cognition into existing Python or TypeScript codebases. Use when adding Honcho SDK, setting up peers, configuring sessions, implementing the dialectic chat endpoint for AI agents, or wiring Honcho into bot frameworks (nanobot, openclaw, picoclaw, etc).

Use when a research note system needs architecture, when MOCs, frontmatter standards, and retrieval patterns must be designed for years of work, or when an existing vault has outgrown its structure and must migrate without breaking years of links.

Co-author structured documents (specs, PRDs, RFCs) through a 3-stage workflow: context gathering, drafting, and reader testing. Use when writing proposals, technical specs, or similar structured content. Repo decision-memory system (INDEX.md, rejected alternatives, agent rules) → docs-adr.

Create, modify, and introspect UserDefinedEnums and UserDefinedStructs (EnumStructService). Use when the user asks to create a Blueprint enum or struct, add enum values or struct members, or inspect an enum/struct's fields. Useful for defining a DataTable row struct.

Drafts an HOA Addendum to a residential purchase agreement covering mandatory membership, financial obligations, governing documents, use restrictions, and buyer acknowledgments. Use when drafting HOA addenda, HOA disclosure forms, purchase addenda for HOA-governed properties, or CC&R disclosure documents.

Detect OS credential dumping techniques targeting LSASS memory, SAM database, NTDS.dit, and cached credentials using EDR telemetry, Sysmon process access monitoring, and Windows security event correlation.

Provides battle-tested PyTorch training recipes for LLMs, vision, diffusion, and biomedical domains, covering training loops, optimizer selection, LR scheduling, mixed precision, and debugging.

Guides users through configuring a LaRuche node by reading its live API state and providing click paths for settings, including LLM providers, messaging channels, secrets vault, MCP server, and memory.

Execute advanced evasion by injecting malicious code into the memory space of a legitimate, suspended process (Process Hollowing). This skill details techniques to bypass static and dynamic analysis by masking malicious activity behind trusted processes like svchost.exe or explorer.exe.

Analyzes Perfetto traces to find the root cause of latency, memory, or jank issues in Android apps. Use when the user provides a Perfetto trace file and asks any question, ongoing investigation, or open-ended request to analyze its contents.

Elite AI context engineering specialist mastering dynamic context management, vector databases, knowledge graphs, and intelligent memory systems. Orchestrates context across multi-agent workflows, enterprise AI systems, and long-running projects with 2024/2025 best practices. Use PROACTIVELY for complex AI orchestration.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.

Detect MITRE ATT&CK T1098 account manipulation techniques including shadow admin creation, SID history injection, group membership changes, and credential modifications using Windows Security Event Logs.

Integrate AFL++ coverage-guided fuzz testing into CI/CD pipelines to discover memory corruption, input handling, and logic vulnerabilities in C/C++ and compiled applications.

Runs before every git commit on heleni-memory. Checks: no credentials in tracked files, no oversized files, valid SKILL.md frontmatter for any new/modified skill. Triggers: "commit", "before push", "validate repo", or auto-runs as a git pre-commit hook.

Guide for the first days with a new human. Use when: the `init` memory block exists (pointing you here), you have no persona/communication blocks yet, or a human explicitly asks about setup. This skill is about having good conversations — not filling out forms.

Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fundraising materials. Use when the user needs investor-facing documents, projections, use-of-funds tables, milestone plans, or materials that must stay internally consistent across multiple fundraising assets.

Autonomously runs iterative experiment loops to optimize code against a measurable metric. Use when the user wants to improve execution time, memory usage, test pass rate, or any numeric performance goal across repeated experiments — NOT for one-shot bug fixes or simple code review.

Decide where to save any piece of information — monday.com, local file, daily notes, or MEMORY.md. Use this skill before saving anything to ensure the right destination. Prevents local clutter and ensures the owner can access all relevant content in monday.com.

Use before starting any new work to check for existing knowledge. This skill provides a systematic search and retrieval process for finding relevant knowledge from memory systems (PARA, Gigabrain, OpenStinger, existing skills) before starting work, preventing redundant effort and leveraging prior learning.

Code review specialist for quality standards, design patterns, security review, and constructive feedbackUse when "code review, pull request, PR review, code quality, refactor, technical debt, design pattern, best practice, code-review, quality, patterns, security, refactoring, best-practices, pull-request, review, ml-memory" mentioned.

Use when the user wants to create or edit forms, collect or query entries, bulk-update form data, check invoices or payment history, or manage their Jinshuju (金数据) account and team members. Also activate for keywords: 金数据, 表单, 问卷, 报名表, form_token, 数据录入, 数据查询, 批量修改.

Evaluates speech language models on beyond-semantic speech attributes such as dialect comprehension, multi-turn context memory, emotion perception, age-aware response generation, and non-verbal cue handling, reporting accuracy and judge-based scores.

This skill should be used when the user asks to "offload context to files", "implement dynamic context discovery", "use filesystem for agent memory", "reduce context window bloat", or mentions file-based context management, tool output persistence, agent scratch pads, or just-in-time context loading.