一键导入
ai-loop
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.
AI-powered presentation generation via the 2slides API — create slides from text, match a reference image style, summarize documents into decks, add AI voice narration, and export pages/audio. Use for any "make slides", "create a deck", or "slides from this document" request.
Structured guide for setting up A/B tests with mandatory gates for hypothesis, metrics, and execution readiness.
When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this,"...
Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use `scan` for a full audit with no diffing.
Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL alongside their parent app.
| name | ai-loop |
| description | Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work. |
| category | workflow |
| risk | safe |
| source | community |
| date_added | 2026-06-27 |
| tags | ["agent-workflow","specification","implementation","review","verification","feedback-loop"] |
| tools | ["claude","cursor","codex","gemini"] |
The ai-loop skill structures a bounded development cycle for agentic workflows. By dividing the process into distinct planning (Spec), implementation (Build), and validation (Review) phases, it helps an agent build and correct scoped code changes while keeping requirements, risk gates, and stop conditions explicit.
This skill executes a controlled development loop composed of three phases: Spec, Build, and Review. When invoked, the agent moves through those phases until the scoped requirements pass verification, a stop condition is reached, or human approval is needed.
Before starting, define:
specs/<feature-name>.md.specs/<feature-name>.md.specs/<feature-name>.md.User:
I want to add a utility for calculating basic statistics (mean, median, mode) of an array of numbers.
Agent (Phase 1 - Spec):
I can help with that. To get started, what programming language should this statistics calculator be implemented in? Also, how should empty arrays or invalid inputs be handled?
User:
JavaScript. If the array is empty, return null. If there are non-numbers, ignore them.
Agent (Phase 1 - Spec):
Thank you. I have created the specification file at
specs/stats-calculator.mdwith the requirements we discussed. Now, I will start implementing it.
Agent (Phase 2 - Build):
(Creates
stats_calculator.jsand implementsmean,median, andmodematching the spec exactly) I have finished implementing the calculator. I will now verify the implementation.
Agent (Phase 3 - Review):
Checking implementation against
specs/stats-calculator.md:
- Requirement: mean calculation -> PASS
- Requirement: median calculation -> PASS
- Requirement: mode calculation -> PASS
- Requirement: empty array returns null -> PASS
- Requirement: non-numbers are ignored -> FAIL (I noticed
modedoesn't filter out non-numbers).I will now loop back to Phase 2 to fix the
modefunction.
Agent (Phase 2 - Build Loop-Back):
(Fixes
modeto filter out non-numbers) I have updated the implementation. Let's re-verify.
Agent (Phase 3 - Review):
- Requirement: mode filters non-numbers -> PASS
All requirements passed! The statistics calculator is complete and verified.
specs/<feature-name>.md before writing any code.ai-loop to small, modular features. Break larger systems into multiple independent loops.@plan-writing - For writing more detailed implementation plans for larger projects.@ask-questions-if-underspecified - For standard guidelines on interviewing the user.