菜单
TODO: Describe what this skill does and when Copilot should load it. Include trigger phrases like "create X", "set up Y", "scaffold Z". Be specific — the description determines automatic activation.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Create or update independent vendor positioning matrix reports. Use when asked for magic quadrant style vendor comparisons, analyst-style market matrices, provider landscapes, technology shortlists, two-axis vendor charts, sourced scoring models, or PDF, Microsoft Word/DOCX, and Markdown vendor evaluation packages. Produces original, evidence-led reports with source ledgers, transparent scoring, bank/regulatory due diligence, and safeguards against Gartner or other analyst-firm imitation.
Create and edit checkpointflow workflow YAML files. Use this skill whenever the user wants to create a workflow, automate a process as a YAML pipeline, define steps that mix CLI commands with human or agent checkpoints, turn a conversation into a reusable runbook, or asks about writing cpf/checkpointflow workflows. Also use it when you see keywords like "workflow", "runbook", "approval flow", "pause and resume", or "await event" in the context of automation.
Create and improve Claude Code skills using a structured checkpointflow workflow with test-driven iteration. Use this skill whenever the user wants to create a skill, make a skill, build a skill, improve an existing skill, test a skill with evals, benchmark skill quality, optimize a skill description, or turn a conversation into a reusable skill. Also triggers on "skill for X", "automate this as a skill", "package this as a skill", and similar phrases.
Create new architecture evaluation rubrics (profiles and overlays) based on the Enterprise Architecture Rubric Operational Standard (EAROS). Use this skill whenever the user wants to "create a rubric", "add a rubric profile", "write an architecture evaluation rubric", "define scoring criteria for architecture artifacts", "create an EAROS profile", "add an overlay", "create a security overlay", "create a data overlay", "evaluate architecture artifacts", "set up architecture review criteria", "build a rubric for solution architecture", "create an ADR rubric", "create a capability map rubric", "define architecture quality criteria", or mentions "EAROS", "rubric", "architecture evaluation", "scoring profile", or "architecture review criteria" in the context of creating or extending evaluation rubrics. Also triggers when the user says "help me evaluate architecture documents", "define review criteria for our artifacts", "standardize architecture review", "create a review checklist", or any request to systematicall
Apply an EAROS rubric to an architecture artifact using the three-pass agent evaluation pattern (Extractor, Evaluator, Challenger). Use this skill whenever the user wants to "evaluate an architecture artifact", "apply a rubric", "review an architecture document", "score an architecture artifact", "run an EAROS evaluation", "assess architecture quality", "apply the solution architecture rubric", "evaluate this ADR", "review this capability map", "check this against the rubric", "run the architecture review", or mentions "evaluate", "score", "assess", "review", or "apply rubric" in the context of applying an EAROS rubric to a specific artifact. Also triggers when the user says "how does this artifact score", "is this architecture document good enough", "run the three-pass evaluation", "extract evidence from this document", or any request to systematically evaluate a specific architecture work product against defined criteria. Does NOT trigger for creating rubrics (use earos-rubric for that), general architectur
Autonomous agent-driven optimization loop inspired by Karpathy's autoresearch. Sets up and runs an iterative hill-climbing harness where subagents modify an artifact, evaluate against a single scalar metric, and keep improvements. Use this skill whenever the user wants to "optimize something iteratively", "run an autoresearch loop", "hill-climb on performance", "auto-optimize", "iterate and improve automatically", "run experiments autonomously", "autonomous optimization", or mentions "autoresearch" in any context. Also triggers when the user describes a workflow like "try variations and measure which is best", "keep tweaking until it's faster", "optimize this config", "find the best prompt", "tune hyperparameters", "benchmark variations", or any scenario where they want an agent to autonomously explore a search space against a measurable objective. Works with any domain — code performance, prompt engineering, config tuning, SQL optimization, CSS optimization, model training, build flags, or anything with a me
| name | todo-skill-name |
| description | TODO: Describe what this skill does and when Copilot should load it. Include trigger phrases like "create X", "set up Y", "scaffold Z". Be specific — the description determines automatic activation. |
Brief description of what this skill enables and why it exists.
Detailed instructions for the first step.
Detailed instructions for the second step.
How to verify the result is correct.
| Problem | Solution |
|---|---|
| TODO | TODO |
