gpt6-astra-model-routing
Choose model and effort for GPT work and subagents in any harness, including inside codex-delegate missions. Default to GPT-6 Astra for research, writing,…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-05 00:16
Agents & models
25,663 results
lower-capability-executor-prompt
Use only when the user explicitly invokes lower-capability-executor-prompt to turn an already researched and approved plan into a bounded prompt for an…
review-panel
Review an artifact with reviewers whose contexts are separate from the authoring session, by default two from different model families such as Claude Fable and…
opencode-agents
Create and configure custom OpenCode agents (primary and subagents) with specialized prompts, tools, permissions, and models. Use when the user wants to…
relay-audit
Analyze human interventions, commands run by agents, and newly added bad patterns across repositories in recent T3 Code threads; identify per repository where humans are acting as message relays, where agents are taking shortcuts or reinventing the wheel, propose improvements, and review the effects of already-adopted improvements. Only propose suggestions; create issues only after the user adopts them. Only invoked proactively by the user.
gitbook-write
A comprehensive guide for editing GitBook documentation in external environments like Cursor, Claude Code, or other text editors. This skill provides all the…
similar-judge
Compare two texts for differences and output similarity and word-level diff JSON. Use when an agent needs to quantify the textual gap between an artifact and a target
autonomous-delivery
Runs long-lived delivery as a coordinator with parallel lanes. Sets authority and pacing dials up front, keeps lanes alive and fed, lands work through a…
autonomy-dial
Resolves how far an agent may take a change, from L0 propose to L5 release. It reads the repo's real GitHub rules (rulesets, branch protection, CODEOWNERS,…
brief
Turns a short intent, often around 20 words, into a brief that can run unattended. The brief has the user's words verbatim, an outcome owner, an observable…
find-the-loop
Before iterating on a speedup or quality problem, build the feedback loop first and write it down as a Loop Card that names the outcome, the instrument the…
steer-once
Turn a correction you keep repeating into a durable fix: mine your corrections, classify them, choose the cheapest layer that would have prevented them…
agent-roundtable
Run a multi-agent audit of a feature, PR/diff, or task spec in which Codex, Command Code (cmd), Gemini, OpenCode and Claude debate over ACP for a configurable…
background-agents
Configure and run background agents with reusable profiles for agent engines, model providers and execution backends. Use when delegating background work,…
companion
Help a person explore what matters across life, choose their own focus, update personal context, or find a useful next step. Weekly goals and agent tasks are…
lab-review
Review an agent conversation with evidence-based coaching on briefs, decisions, verification, and next practice. Use for «разбери эту сессию», «проверь мои…
pr-reviewer
Autonomous AI-powered pull request reviewer with multi-agent analysis and comprehensive feedback
qa-engineer
QA specialist agent for test planning, execution, and regression analysis
agentic-ecology-colab-cli
Provides guidelines and workflows for launching, managing, and executing workloads on remote Google Colab runtimes using the external google-colab-cli.
cxas-composite-voice-agent-optimizer
Audits, optimizes, and remediates CXAS agent configurations for Gemini Composite V1 voice naturalness, persona styling, and multi-language coverage directly in…
gcp-agent-eval-engine-runner
Boilerplate for a production evaluation runner that performs parallel inference, captures reasoning traces via SSE, and integrates with the Vertex AI Gen AI…
gcp-agent-safety-gatekeeper
Implements the "Defense-in-Depth" integration pattern in Python (intercepting prompts, parsing filter results).
gcp-agent-tool-trajectory-evaluator
Provides custom Python metrics for configuring Vertex AI Gen AI Evaluation to measure Trajectory Precision, Recall, and Order Match.
gcp-production-secret-handler
Implements the "in-memory only" secret pattern for Google Cloud production agents.