MLOps
模型部署、评估与运维
earnings-product-pipeline
OctagonAI
Extract product development and pipeline updates from earnings calls, including clinical trial progress, regulatory submissions, and launch timelines.
Skill: training-stability-monitor
strikersam
Loss curves should be logged at every step, not averaged over epochs, for this skill to work
business-model-auditor
shipshitdev
Use this skill when users need to stress test their business model, identify scale limitations, find bottlenecks, determine if they're trading time for money, or evaluate unit economics. Activates for "can this scale," "what breaks at 10x," or business model viability questions.
business-operator
shipshitdev
Use this skill when users manage multiple businesses, need help prioritizing across ventures, want a business health check, or ask "which business should I focus on." Activates for multi-business orchestration, portfolio management, and cross-venture resource allocation.
context-degradation
shipshitdev
Recognize, diagnose, and mitigate patterns of context degradation in agent systems. Use when context grows large, agent performance degrades unexpectedly, or debugging agent failures.
analysis-planner
smestern
Creates step-by-step analysis plans for scientific data — designs the pipeline, specifies parameters, anticipates risks, and defines success criteria before any code is executed.
advanced-evaluation
shipshitdev
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.
ux-kano-model
geekatron
"Kano model feature classification and prioritization sub-skill for the /user-experience parent skill. Classifies product features into Must-be (M), Performance (O), Attractive (A), Indifferent (I), and Reverse (R) categories using the functional/dysfunctional questionnaire pair methodology (Kano et al., 1984). Computes Customer Satisfaction (CS) coefficients (Better/Worse) for priority matrix visualization. Produces feature classification reports, priority matrices, and survey design templates. Sample size awareness: 5-8 respondents yields directional classification only (MEDIUM confidence); 20+ respondents required for statistical classification (Berger et al., 1993). Invoked by ux-orchestrator during Wave 4 lifecycle-stage routing or when user intent is \"Need to prioritize features\" at any lifecycle stage. Triggers: Kano, must-be, attractive, one-dimensional, performance feature, satisfaction, feature classification, delighter, feature prioritization, CS coefficient."
gemini
jdrhyne
Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.
codex
jdrhyne
Use when the user asks to run Codex CLI (codex exec, codex resume) or references OpenAI Codex for code analysis, refactoring, or automated editing. Uses GPT-5.2 by default for state-of-the-art software engineering.
odoo-security
ahmed-lakosha
"Comprehensive Odoo security auditor for model access rules, HTTP route authentication, sudo() usage, SQL injection risks, and record rule completeness across Odoo 14-19."
tasks
agenticnotetaking
View and manage the task stack and processing queue. Shows pending work, active tasks, completed items, and queue state. Triggers on "/tasks", "show tasks", "what's pending", "task list", "queue status".
Skill: lr-schedule-advisor
strikersam
Pairs with insights to compare schedule experiments across runs
pytm
AgentSecOps
Python-based threat modeling using pytm library for programmatic STRIDE analysis, data flow diagram generation, and automated security threat identification. Use when: (1) Creating threat models programmatically using Python code, (2) Generating data flow diagrams (DFDs) with automatic STRIDE threat identification, (3) Integrating threat modeling into CI/CD pipelines and shift-left security practices, (4) Analyzing system architecture for security threats across trust boundaries, (5) Producing threat reports with STRIDE categories and mitigation recommendations, (6) Maintaining threat models as code for version control and automation.
Skill: data-quality-audit
strikersam
Re-run after any tokenizer change — fertility and special token checks are tokenizer-dependent
sec-business-desc-analysis
OctagonAI
Extract and analyze business descriptions and competitive landscape from SEC filings using Octagon MCP. Use when researching company business models, market positioning, competitive advantages, industry dynamics, and strategic focus areas from Item 1 disclosures.
sag
EthanAlgoX
ElevenLabs text-to-speech with mac-style say UX.
model-usage
EthanAlgoX
Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.
openai-whisper
EthanAlgoX
Local speech-to-text with the Whisper CLI (no API key).
openai-image-gen
EthanAlgoX
Batch-generate images via OpenAI Images API. Random prompt sampler + index.html gallery.
sherpa-onnx-tts
EthanAlgoX
Local text-to-speech via sherpa-onnx (offline, no cloud)
load-topology
nicholasf
Read the local system topology to discover available machines and models. Triggers on "load topology", "what models are available", "which machines are running", "start a model", "show me the topology", "sync topology", "refresh topology", "benchmark llm", "benchmark model", "test llm", "run benchmark", "help", "show help", "list subcommands".
eld-model-term-card
CAPHTECH
Deprecated: /eld-spec-card term を使用してください。 このスキルは後方互換のためのエイリアスです。すべての呼び出しは /eld-spec-card term に転送されます。
worktree
HikaruEgashira
Planが承認/完了した直後に自律的に呼び出す必要があるスキルです。 Trigger: plan approved, plan completed, taskを開始します