scg-review
codexSimplification, secret scanning and four-lane review of the exact staged Git tree.
4 skills · 1 agent
Subagent coordination, model selection, router-model workers and evidence refresh.
Plugin scg-subagents in software-combined/SC_AI_Router. Commands read from the repo's manifest — 13 days ago.
csm-subagentDelegate bounded customer-success work (health summaries, onboarding docs, renewal-risk analysis, expansion notes) with the right model and guardrails. Read with the optimal-subagents skill, which owns model selection.
finance-subagentDelegate bounded finance analysis (journal review, reconciliation summaries, variance analysis, report drafting) with the right model and guardrails. Read with the optimal-subagents skill, which owns model selection.
operations-subagentDelegate bounded operations work (process docs, IT and HR drafts, data cleanup, HR comms) with the right model and guardrails. Read with the optimal-subagents skill, which owns model selection.
optimal-subagentsChoose the right model and coordinate subagents for research, coding, documents, analysis and independent plan review before action. Covers delegation, model evidence, workload-specific comparisons and refreshing recommendations as models change.
router-workersRun a bounded task on a router model (the SCG Router's OpenRouter models, such as DeepSeek, GLM, MiMo, Muse, Kimi, Qwen, Gemini, Grok or the GPT twins) as an isolated headless Claude Code worker with shell and file tools. Only for a Claude desktop Code session in the subscription profile (the first-
sales-subagentDelegate bounded sales work (lead enrichment, outbound drafts, CRM cleanup, company research) with the right model and guardrails. Read with the optimal-subagents skill, which owns model selection.
support-subagentDelegate bounded support work (ticket triage, first-response drafts, log extraction, playbook lookup) with the right model and guardrails. Read with the optimal-subagents skill, which owns model selection.
Simplification, secret scanning and four-lane review of the exact staged Git tree.
4 skills · 1 agent
AI Agent Factory Method for persistent project agents, clear area ownership and temporary helpers.
1 skill
Write and maintain documentation that stays readable for readers at any technical level.
1 skill
Finance-director grade analysis grounded in the organisation's accounting data, whatever system it lives in.
1 skill
Measure and improve local testing and CI pipelines while preserving required verification and release gates.
1 skill
Choose the simplest complete, correct solution for coding tasks.
1 skill
Talk like caveman. Cut filler. Keep technical details explicit.
22 skills · 1 command · 3 agents · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.
1 skill
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Package any website or local web build into a lightweight desktop app with Pake CLI.
1 skill
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.