Skill rating

SAM-style feature initiation workflow — discovery through codebase analysis, architecture spec, task decomposition, validation, and context manifest. Use when a user asks to add a feature, plan a feat

Testany platform case 编写助手 - 将传统测试场景拆解为 Testany platform cases，并生成可注册的 case packages

End-to-end feature testing — browser QA, API verification, eval tests, or any combination. Covers browser interactions (via agent-browser CLI), Google Workspace operations (gws CLI), API calls, and LL

Write focused unit tests for backend and utility logic

Pause execution for a user-specified duration

Audit Claude Code agents, skills, and commands for quality and production readiness. Use when evaluating skill quality, checking production readiness scores, or comparing agents against best-practice

Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards), seeded as two faces on day one (CLAUDE.md + GLOSSARY.md) with every other surface

Reasoning-mode completion against DeepSeek's `deepseek-reasoner` model (R1) via /v1/chat/completions. Surfaces the model's chain-of-thought (`reasoning_content`) separately from the final answer (`con

One-shot chat completion against DeepSeek's `deepseek-chat` model via the OpenAI-compatible /v1/chat/completions endpoint. Reads DEEPSEEK_API_KEY from the environment; degrades gracefully (exit 0 with

Scaffold a new Claude Code plugin with proper directory structure, plugin.json, skills, commands, and agents

Trace agent execution by collecting spans and building a trace tree for a task

Run `@metaharness/darwin evolve {repo}` to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, and p

7-section repo readiness report from `metaharness genome {path}`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (A

Per-message cost breakdown within a single session. The drill-down companion to cost-anomaly — when an outlier session is flagged, this surfaces the specific expensive messages so operators can see wh

Run a GEPA learning cycle via `metaharness learn` (upstream ADR-235, metaharness@0.3.0) — optimizes a harness genome against a SWE-bench-style slice manifest. $0 dry-run by default; `--run` is the exp

5-dimension harness readiness scorecard from `metaharness score {path}`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd + scaffoldReady. Pure-

Create a new sequentially numbered database migration with up/down SQL files

Generate a cost report showing token usage and USD costs by agent and model

Inspect and audit GEPA genomes via the `@metaharness/darwin/gepa` library entry (darwin 0.8.0) — load/validate a genome (default is the shipped cand-6 promotion), render the system prompt a genome com

DEPRECATED in v0.2.0 -- use browser-extract instead; this is a thin shim for backward compatibility, kept as a shim and slated for removal in the next minor release

Burn-rate trend over time with optional drift-alert exit code. Bins session spend into buckets, surfaces window-over-window delta, and can exit 1 when latest bucket exceeds prior mean by a configurabl

One-time setup — mint a Cognitum Music personal access token and register the cogmusic MCP server with Claude Code

Build or rebuild the ADR index + dependency graph by running scripts/import.mjs (handles v3-style and plugin-style ADR formats; one Bash call vs hundreds of MCP round-trips)

Add a complete Sim integration from API docs, covering tools, block, icon, optional triggers, registrations, resolved-secret/model-input safety, and integration conventions. Use when introducing a new

Add or update a Sim knowledge base connector for syncing documents from an external source, including auth mode, config fields, pagination, document mapping, tags, and registry wiring. Use when workin

Create or update a Sim integration block with correct subBlocks, conditions, dependsOn, modes, canonicalParamId usage, outputs, and tool wiring. Use when working on `apps/sim/blocks/blocks/{service}.t

A skill that cannot be invoked by the model.

A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.

Stop. That last message did not land: re-pitch it.

A relentless interview to sharpen a plan or design.

Prove model-disabled skills stay outside the model catalog.

Stop. That last message did not land: re-pitch it.

Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润色循环", "auto improve", or wants to iterat

Generate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab).

Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent evaluates results against intended claims and route

Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wan

Fill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完',

End-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conf

Restate the last message in plain human language, with no jargon.

Evaluate acquisition channels using unit economics, customer quality, and scalability. Use when deciding whether to scale, test, or kill a growth channel.

Diagnose SaaS business health across growth, retention, efficiency, and capital. Use when preparing a business review or prioritizing urgent fixes.

Discover, connect, and verify NotFair paid-ad integrations and their actual capabilities. Use when asked to connect an ad account, configure an ads MCP, check available tools, troubleshoot access, or

Plan, validate, and safely publish Google Ads assets, including sitelinks, callouts, structured snippets, image assets, and Performance Max asset briefs. Use when asked for Google Ads assets, ad exten

Create evidence-based Meta ad creative briefs, copy angles, and testable asset concepts for Facebook and Instagram. Use when asked for Meta ad creative, Facebook ads copy, Instagram ad assets, UGC con

Create grounded paid-media creative concepts, copy angles, refresh hypotheses, and measurable test briefs across advertising platforms. Use for ad copy, creative briefs, UGC concepts, headlines, creat

Audit, diagnose, plan, and safely operate connected LinkedIn Ads accounts through the NotFair MCP, with an export-based fallback. Use for LinkedIn advertising, sponsored content, lead-generation forms

Diagnose wasted paid-ad spend, pacing, and allocation, then propose safe evidence-backed optimizations. Use for waste, negatives, budgets, bid changes, poor CPA or ROAS, underpacing, overspend, or sca

Plan and review ChatGPT Ads experiments without assuming ad inventory, account access, or platform capabilities. Use for ChatGPT advertising, OpenAI ads, conversational ad concepts, ChatGPT campaign p

Plan and review Amazon Ads with margin-aware ACoS, product, and search-term guardrails. Use for Amazon advertising, Sponsored Products, Sponsored Brands, Sponsored Display, ASIN targeting, Amazon ACoS

Plan and prepare a new paid-media campaign or cross-channel test before it can spend. Use when asked to create, launch, start, set up, or allocate budget to an advertising campaign on any supported pl