Results for “loop”

Recognize when you're in a runaway loop and stop yourself. Use when the same tool call has repeated 3× with the same args, when the same error class has fired 3× in a turn, when you've been told the same correction twice, when "let me try one more variation" is the third small variation, or when a refinement loop is orbiting rather than converging. The right move on a trip is to switch from action to inquiry — read events.jsonl, list assumptions, look for contradictions, ask the human, file a chainlink — not to retry harder.

Turns a rough request into working software via a governed build loop: align first, plan, then iterate one task at a time with deterministic backpressure and holdout-scenario judging.

Writes Alan Hirsch's 8-week transformational course content, including video scripts, readings, case studies, reflection questions, and field experiments, in his voice with formation-over-information pedagogy.

Enforces an algorithm-first discipline: state Big-O, data structure, and algorithm family before writing loops, queries, or recursion, catching O(n^2), N+1, and brute-force defaults.

Inter-agent communication protocol for C-suite agent teams. Defines invocation syntax, loop prevention, isolation rules, and response formats. Use when C-suite agents need to query each other, coordinate cross-functional analysis, or run board meetings with multiple agent roles.

Use when a Claude Code session loops, drifts from scope, claims a fix that CI rejects, hits context, PATH, or permission walls, or fails in a way another retry will not solve and a root cause diagnosis is needed instead.

Prioritize features for an MVP or first release. Use when the team has too many ideas and needs must-have vs later vs never-for-v1 decisions tied to the core value loop, user pain, operational shortcuts, and launch feasibility.

Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.

Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker — edges as text in one file per ticket locally, or native blocking links on a real tracker.

BDD-driven test implementation: red-green loop mechanics, seams, mocking, and test quality under BDD Automation. Use when the user wants to write or improve tests during BDD implementation, needs guidance on test structure, or asks about test seams, mocking, or anti-patterns.

Executes Atomic Red Team tests mapped to MITRE ATT&CK techniques, performs coverage gap analysis, and runs detection validation loops to measure blue team visibility.

Donahoe Loop audit gate before execution. Trigger: 'audit plan', 'check plan', 'review plan', 'plan audit', 'plan check', 'before we build', 'before execution', 'validate the plan', 'is this plan solid', 'plan review'. Owns pre-execution audit intent -- fires before any foreign plan-checker.

Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers, drag handles) or an inline edit/highlight/comment annotation studio for prose & media, instead of guessing values or shipping a static comparison grid.

Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers, drag handles) or an inline edit/highlight/comment annotation studio for prose & media, instead of guessing values or shipping a static comparison grid.

Autonomously runs iterative experiment loops to optimize code against a measurable metric. Use when the user wants to improve execution time, memory usage, test pass rate, or any numeric performance goal across repeated experiments — NOT for one-shot bug fixes or simple code review.

Human-in-the-loop web studio to tune AI-generated output by eye. Stand up a local interactive studio (sliders, pickers, drag handles) or an inline edit/highlight/comment annotation studio for prose & media, instead of guessing values or shipping a static comparison grid.

Write code through a disciplined, BDD-framed Test-Driven Development loop: build a behavior test list, then drive each behavior through red-green-refactor with an enforced observed-failure gate. Use when the user wants to implement, build, or write code test-first, "do TDD", follow "red-green-refactor", drive code from tests, choose the next test by the Transformation Priority Premise (TPP) or ZOMBIES ordering, or grow a feature behavior-by-behavior with tests leading. This skill writes and changes code; it does not produce a test plan document (use automated-test-planning, or manual-test-planning for a plan a person runs by hand), review or audit existing code (use code-review), restructure existing code outside a TDD loop (use refactor), specify what a feature should do (use plan-a-feature), or find the root cause of a bug (use investigate). Runs its loop to completion without pausing for review; to review each behavior as it lands, use pairing.

Automate multi-turn adversarial conversations against LLM agents using Microsoft PyRIT, including Crescendo and Tree-of-Attacks-with-Pruning (TAP) attack chains with scorer feedback loops.

Automates PR review and CI auto-fix for GitHub and GitLab using the Composio CLI. Pulls diffs, fetches failing job logs, posts review comments, and loops fix commits until checks go green.

Generates a complete mobile test suite for Flutter, React Native, iOS, or Android apps, covering unit, widget, integration, snapshot, accessibility, and platform-specific tests, then runs them with a self-healing loop.

Autonomous GAS development skill — code, deploy, test, and fix in a self-driving loop. Uses clasp for code management, Web App + gas-run.sh for auto-deploy/execution, and gws for spreadsheet read/write. Triggers on "GAS", "Apps Script", "spreadsheet automation", "clasp", "gws sheets".

Call a DeepSeek-backed OpenCode agent as a separate critique, writing, or revision agent from Codex. Use when Codex needs to delegate adversarial research critique, novelty skepticism, method review, manuscript prose, LaTeX section drafting, academic text revision, or paper-writing feedback loops to DeepSeek.

Routes requests into the correct obsidian-mind mode: install, daily session loop, capture, review, maintenance, multi-agent wiring, or semantic search, using a ready-made Obsidian vault template for persistent agent memory.

Resolves GitHub issues using isolated worktrees and test-driven development, then delegates PR creation to /github:create-pr so the quality gate and the /github:review-pr loop always run. This skill should be used when the user asks to "resolve an issue", "fix issue

Use when making a forward-looking claim with a checkable outcome (reply within 24h, error rate will drop, this skill will see more use) — record to state/predictions.jsonl with a review horizon so reflection can grade you later. Closes the in-the-moment double-loop.

ScepticAgent internal architecture reference. Use whenever the user asks how the extension works, wants to add a new AI provider, add a new highlight category, debug communication between components, understand the agent loop or streaming, or work with provider routing and the Gemini CORS proxy.

Builds an interactive in-browser studio for tuning visual parameters (sliders, pickers, drag handles) or editing/annotating text and media, enabling real-time human-in-the-loop refinement instead of static comparisons or chat-based feedback.

Use when planning an ACL project calendar across ACL Rolling Review cycles, covering cycle selection against conference commitment windows, backward planning from an ARR deadline, the review-response-meta-review timeline, commitment decisions, resubmission loops to later cycles, and camera-ready through ACL Anthology publication.

Automates the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models, including baseline evaluation, RCA, synthetic defect generation, data mining, retraining, and deployment gating until KPI targets are met.

Knowledge-base steward in the spirit of Niklas Luhmann's Zettelkasten. Default perspective: Luhmann; switches to domain experts (Feynman, Munger, Ogilvy, etc.) by task. Enforces atomic notes, connectivity, and validation loops. Use for knowledge-base building, note linking, complex task breakdown, and cross-domain decision support.

Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a broad research direction all the way to a submission-ready paper. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.

Run Karpathy-style autonomous ML search on a real training repo: choose the right mode (setup, program.md, bounded loop, results interpretation, or constrained-hardware adaptation), preserve the immutable prepare.py / 300-second / val_bpb contract, and route prompt/skill eval work away to LangSmith, Promptfoo, Braintrust, or skill-autoresearch.

Use when Codex is building or iterating on a web game (HTML/JS) and needs a reliable development + testing loop: implement small changes, run a Playwright-based test script with short input bursts and intentional pauses, inspect screenshots/text, and review console errors with render_game_to_text.

When the user wants to create, optimize, or analyze a referral program, affiliate program, or word-of-mouth strategy. Also use when the user mentions 'referral,' 'affiliate,' 'ambassador,' 'word of mouth,' 'viral loop,' 'refer a friend,' or 'partner program.' This skill covers program design, incentive structure, and growth optimization.

Use when designing or auditing AI product human-in-the-loop — write approval, proposal accept/reject, action confirm, spend caps, run detail, memory capture, or any AI action with irreversible blast radius. Trigger on confirmation UX, undo, cost-before-act, show-the-plan, citations, or keeping the owner in control.

Router for Google Stitch design-to-code in this pack. Use when starting any Stitch workflow, choosing Stitch vs Aura vs Figma vs Claude Design, or before calling generate/edit MCP tools. Enforces ~400 Stitch credits/day. Points to phased pack skills: enhance-prompt → generate-design → extract → build → loop.