Results for “loop”

Score and iteratively improve marketing content with an expert panel until 90+. Use for content quality gates, expert panel reviews, editorial scoring, or when another skill needs a content QA loop.

Route goalflow (wanmol/goal-flow) work — a LangGraph framework that combines workflow graphs with agent loops — into exactly one mode: fit check, transpiling a Dify DSL export into runnable LangGraph Python, authoring workflow nodes and edges, building an `agent_kit` loop with middleware and a harness, wiring the serving layer (data adapters, SSE streaming, HITL, Redis/MySQL, API-key registration), or running the pre-publish security gate. Use when the user wants Dify's visual design without Dify's runtime, a graph node that hosts an agent loop, an OpenAI-compatible wire protocol over their own workflows, or prompt-injected `SKILL.md` capabilities. Triggers on: goalflow, goal-flow, dify to langgraph, dify transpiler, dify DSL export, BaseWorkflow, agent_kit, AgentBaseNode, DataAdapter, chunk processor, HITL interrupt, dify2langgraph. Route plain graph-API questions to `langgraph-fundamentals` and `langgraph-workflow`.

Default execution rhythm — inspect → act → verify → checkpoint — applied iteratively until the task is done or a clear blocker emerges. Use when working through a known plan, draining a queue (PRs, issues, dependency bumps), or executing a multi-step recipe where each step's output informs the next. Each iteration must produce a concrete artifact (commit, comment, decision) and a one-line state update. Stop on first unrecoverable error rather than retrying blindly. Pair with `ship` for merge-bound work and `handoff` if budget runs out mid-loop.

Convert browser-use (Python) browser-automation scripts to Stagehand v3 (TypeScript) on Browserbase, replacing opaque agent loops with deterministic pipelines where possible.

Design MVPs, validated learning experiments, and pivot-or-persevere decisions using the Build-Measure-Learn loop and innovation accounting.

Runs an autonomous optimization loop that iteratively improves an artifact against an objective and evaluator using Hypothesis Tree Refinement, with subagent executors in isolated git worktrees.

Implements a continual learning loop for AI coding agents using hooks, two-tier memory (global and local), and automatic pattern detection to persist and apply learnings across sessions.

Enforces output quality, intellectual honesty, and continuous improvement across security analysis agents with anti-rationalization guards, self-critique loops, retry protocols, and quality gates.

Establishes a two-party working posture where the user directs and the agent executes, surfacing every genuine fork as a batched single-select question with a recommended default.

Write bash scripts for automation, system administration, and command-line productivity, covering variables, conditionals, loops, functions, argument parsing, error handling, and text processing with awk, sed, find, and xargs.

Implements AI safety guardrails including input validation, output filtering, robustness testing, human oversight, and monitoring to prevent harmful outputs and ensure system reliability.

Build multi-agent conversation systems with AutoGen, including two-agent chats, group chats, function calling, and nested conversations with code execution and human-in-the-loop options.

Access Google's most advanced AI models using the Gemini API in Agent Platform (formerly Vertex AI) with SDK installation, authentication, and code examples.

Provides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving agents, optimizing agent prompts and skills against benchmarks, or implementing automated agent evaluation loops.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Diverga Dashboard - Live configuration status and feature overview. 24 specialized agents across 9 categories for social science research. VS methodology prevents mode collapse. Human checkpoints enforce human-in-the-loop decisions. Triggers: /diverga, diverga dashboard, diverga status

Close the gap between "you corrected me" and "it never happens again." Scan a work session for the corrections you made, the things you approved, and the patterns that held up, then propose specific edits to your skills, playbooks, and docs, high-confidence corrections separated from medium-confidence patterns, with nothing changed until you approve. Trigger on "learn from this session", "what should we update", "turn this into a rule", "close the loop", "improve the playbook", or the end of any session where you corrected or approved the work.

Runs a multi-phase verification pipeline including build, type-check, lint, tests, security scan, and diff review to ensure code quality before creating a PR.

Automates repeated rounds of Copilot code review on GitHub pull requests: triggers review, triages threads, dispatches parallel fix agents, commits, replies, and loops until convergence.

Reviews and repairs risky or unclear code with minimal validated changes, running a fixed-point loop until the diff is clean across two consecutive review cycles.

Plan a huge chunk of work — more than one agent session can hold — as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.

Use when profiling, diagnosing, or improving Three.js or WebGL game performance without regressing gameplay—frame-time drops, CPU/GPU pressure, draw calls, texture/geometry budgets, animation loops, adaptive quality, mobile performance, and browser performance verification.

Building interactive experiences that engage, challenge, and delight playersUse when "game, gamedev, game development, phaser, unity, unreal, godot, gameplay, game loop, sprites, collision, physics, player, level, tilemap, games, gamedev, interactive, gameplay, physics, engines, performance, player-experience" mentioned.

PASS/FAIL eval rubrics and alignment loops for Sid Orchestra. Use when the user says sid evals, @sid-evals, grade this, eval gate, alignment score, or wants to stop AI slop with evaluation gates.

Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.

Build automated AI workflows combining multiple models and services for batch processing, scheduled tasks, event-driven pipelines, and agent loops using the inference.sh CLI.

Generate an interactive bash wizard that walks a human through a manual procedure — third-party setup, a one-off migration, an A→B state transition — opening URLs, capturing values, confirming each step, and writing .env files and GitHub Actions secrets.

Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.

This skill should be used when building the async job workflow, implementing polling loops, handling job status transitions, processing rich data, managing conversation threads, or understanding the full submit-poll-complete lifecycle of the Bankr Agent API.

Close the PDCA loop on this session's diff. Headed playwright-cli, fix as you go. Use when "test my changes", "PDCA this". Pixel diffs → test-visual-regression. Story CRUD → test-qa. Monkey / guest vs logged-in → test-exploratory.

Enforces an algorithm-first discipline: state Big-O, data structure, and algorithm family before writing loops, queries, or recursion to catch O(n²), N+1, and brute-force defaults.

Easy debugging skill pack for Content Factory. Use when the user says debug skills, @debug-skills, something is broken, failed pipeline, or bug pack. Auto-loads systematic-debugging, cf-orchestrator, debugging-loop, and bug-fixing workflow.