New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

AI Loop

by sickn33 in sickn33/agentic-awesome-skills

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

MITAuto-check passed

Install AI Loop

skills CLI
$ npx skills add sickn33/agentic-awesome-skills --skill ai-loop -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install sickn33/agentic-awesome-skills ai-loop --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/sickn33/agentic-awesome-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ai-loop .claude/skills/ai-loop && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
ai-loop
GitHub stars
47k
Used in
1 other repo
Token cost
~2k tokens
SKILL.md length
1,052 words
Files
1
Skills in repo
1,354
Repo updated
First seen
Licence
MIT

At a glance

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

  • Works in 3 steps: Spec (Planning) → Build (Implementation) → Review (Verification)
  • SKILL.md covers Overview, When to Use This Skill, How It Works and Examples, plus 5 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

AI Loop is an agent skill from sickn33/agentic-awesome-skills. Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

Its SKILL.md is about 2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: AAS Core is the local, agent-first control plane for complete catalog discovery, agent-owned selection, stack validation, and planning, backed by 2,400+ agentic skills. Includes… The licence is MIT.

Example prompts

  • “/ai-loop”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Spec (Planning)
  2. Build (Implementation)
  3. Review (Verification)

What it can do on your machine

Read from SKILL.md and the folder at commit ec02547. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

AI Loop loads about 2k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 1,052 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from sickn33/agentic-awesome-skills at commit ec02547, republished under its MIT licence (© sickn33). 1,052 words, ~1,952 tokens.

Download SKILL.mdSave it as .claude/skills/ai-loop/SKILL.md (or your agent's skills folder).
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

AI-Loop Skill

Overview

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.

When to Use This Skill

  • Use when you need a feature built from scratch or heavily modified, and you want the agent to handle the lifecycle (specification, implementation, and verification) inside one clearly bounded workflow.
  • Use when working with isolated components, modules, or features that have well-defined scopes and constraints.
  • Use when the user asks for a complete development pass but the work still has clear success criteria, a reasonable verification path, and no unresolved safety or product decisions.

How It Works

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:

  • The maximum number of build-review iterations.
  • The verification commands or manual checks that count as evidence.
  • The actions that require explicit approval, such as destructive commands, production changes, external service writes, or broad architectural pivots.
Phase 1: Spec (Planning)
  1. Interview the user about the feature or app they want to build. Ask one focused question at a time until you fully understand the goal, the must-have requirements, the constraints, and what "done" looks like.
  2. Do not start building yet.
  3. When you have enough information, write a clear, detailed specification and save it to specs/<feature-name>.md.
  4. The spec must include:
    • The objective
    • The exact requirements
    • Edge cases to handle
    • A concrete definition of done that someone could check the build against
    • The iteration budget, verification commands, and approval gates.
Phase 2: Build (Implementation)
  1. Read the spec you just created in specs/<feature-name>.md.
  2. Build exactly what it describes.
  3. Do not add features, do not refactor unrelated code, and do not invent requirements that aren't in the spec.
  4. Focus strictly on fulfilling the spec. List which spec requirements you covered so the review step can check them.
Phase 3: Review (Verification)
  1. Compare your implementation against specs/<feature-name>.md.
  2. Go requirement by requirement and verify if it was met. List every gap, bug, or missing piece, naming the exact spec item each one fails.
  3. If anything fails and the iteration budget is not exhausted, write the specific fixes needed and loop back to Phase 2 (Build) to address them.
  4. Stop and ask for human input when the next fix would change the spec, exceed the iteration budget, require risky operations, or depend on product decisions not captured in the spec.
  5. Only pass the build and conclude the skill execution when every requirement in the spec is fully met and the declared verification evidence has passed.

Examples

Example 1: Creating a Basic Statistics Helper

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.md with the requirements we discussed. Now, I will start implementing it.

Agent (Phase 2 - Build):

(Creates stats_calculator.js and implements mean, median, and mode matching 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 mode doesn't filter out non-numbers).

I will now loop back to Phase 2 to fix the mode function.

Agent (Phase 2 - Build Loop-Back):

(Fixes mode to 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.

Show full SKILL.md (356 more words)Show less

Best Practices

  • ✅ Do ask clarifying questions one at a time to avoid overwhelming the user during the planning phase.
  • ✅ Do document edge cases explicitly in specs/<feature-name>.md before writing any code.
  • ✅ Do stick strictly to the approved specification during the build phase.
  • ✅ Do cap the loop with a small iteration budget and report exactly what remains if the budget is exhausted.
  • ✅ Do pause for explicit approval before destructive, production, credentialed, or externally visible actions.
  • ❌ Don't implement extra features or perform unrelated refactorings that aren't specified.
  • ❌ Don't skip the review phase or pass it without verifying every single requirement.
  • ❌ Don't keep retrying the same failing fix without new evidence or a changed approach.

Limitations

  • This skill requires sufficient context about the feature to be provided during the Spec phase.
  • It is best suited for isolated features or tasks with clear boundaries, rather than open-ended architectural refactoring.
  • The review phase relies on the agent's self-assessment against the generated spec; manual review is still recommended for critical systems.
  • It is not a replacement for human approval on security-sensitive, destructive, production, compliance, or externally visible changes.
  • It should stop rather than continue if requirements conflict, tests cannot run, or verification depends on unavailable credentials or systems.

Security & Safety Notes

  • Be cautious when running or testing code generated during the Build phase. Always run tests in a safe, sandboxed environment.
  • Avoid executing arbitrary shell commands provided directly by the user without validating their safety.
  • Make sure no hardcoded secrets, keys, or credentials are added to the code or specifications.
  • Treat production deploys, data migrations, payment flows, credential changes, and external write actions as approval-gated work.

Common Pitfalls

  • Problem: The agent tries to build a huge system all at once, leading to an overcomplicated spec and incomplete implementation. Solution: Keep the scope of ai-loop to small, modular features. Break larger systems into multiple independent loops.
  • Problem: The spec is vague, causing the build phase to rely on assumptions. Solution: Spend extra time in the planning phase asking targeted questions to pin down requirements.
  • @plan-writing - For writing more detailed implementation plans for larger projects.
  • @ask-questions-if-underspecified - For standard guidelines on interviewing the user.

© sickn33, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/ai-loop of sickn33/agentic-awesome-skills.

Open the folder on GitHubat commit ec02547

Used in 1 other repository

We found 5 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in sickn33/agentic-awesome-skills, which our catalogue first saw on October 7, 2026.

Compare with similar skills

AI Loop next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

AI Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
AI Loop this skillsickn33/agentic-awesome-skills47k1 repos~2kAutomated safety check: PassMIT
Bounded Work ItemSeemSeam/claude_codex_bridge3.6k—~129Automated safety check: PassCustom licence
Boundjongwony/epistemic-protocols173—~12kAutomated safety check: PassMIT
Bounded Work ItemSeemSeam/claude_codex_bridge3.6k—~480Automated safety check: PassCustom licence
Bounded AutoresearchAgriciDaniel/claude-obsidian15k1 repos~1.6kAutomated safety check: PassMIT
Thinking Bounded Rationalitytjboudreaux/cc-thinking-skills1.6k—~703Automated safety check: PassMIT

Similar skills

  • Bounded Work Item

    SeemSeam/claude_codex_bridge

    Execute one bounded CCB work item and report evidence without changing workflow authority.

    3.6k GitHub stars~129 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Bound

    jongwony/epistemic-protocols

    The user cannot yet see what a task needs them to decide, or which decisions to keep or entrust: map the whole task first, then open each decision to the depth needed.

    173 GitHub stars~12k tokensUpdated today
    Auto-check passed

  • Bounded Work Item

    SeemSeam/claude_codex_bridge

    Execute one scoped implementation or investigation item and return evidence without changing workflow authority.

    3.6k GitHub stars~480 tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Bounded Autoresearch

    AgriciDaniel/claude-obsidian

    Runs a bounded, source-grounded research loop that drafts a cited dossier and can propose a separately reviewed merge into an Obsidian vault.

    15k GitHub starsUsed in 1 repo~1.6k tokens
    Knowledge ManagementAuto-check passed

  • Thinking Bounded Rationality

    tjboudreaux/cc-thinking-skills

    A skill your agent uses when search or investigation could run forever.

    1.6k GitHub stars~703 tokensUpdated 2 mo ago
    Auto-check passed

  • Check Bounds Safety

    r3bl-org/r3bl-open-core

    Apply type-safe bounds checking patterns using VPIndex/VPLength types instead of usize.

    485 GitHub stars~4.1k tokensUpdated today
    DevelopmentAuto-check passed

More from sickn33/agentic-awesome-skills

All 1,354 skills in this repo

  • Liuguang Banlan UI

    sickn33/agentic-awesome-skills

    Implements an interface in one of two named color modes, iridescent white or colorful black, from a parameterized starter that reports measured color intensity.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

  • User Thoughts Memory

    sickn33/agentic-awesome-skills

    Saves a user's project decisions, rules and preferences into a project-local mdbase so later sessions and other agents can recover the intent.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

  • Using LWC Memory and Graphs

    sickn33/agentic-awesome-skills

    Keeps project decisions, research and verified results available across coding-agent sessions through LWC memory, a document Wiki graph and a CodeGraph code index.

    47k GitHub starsUsed in 1 repo~2k tokens
    Auto-check passed

  • Find Complementary Founders

    sickn33/agentic-awesome-skills

    Guides an agent through assessing its own owner for cofounder fit, publishing an approved profile, and ranking complementary profiles other agents published for their owners.

    47k GitHub starsUsed in 1 repo~4.8k tokens
    Auto-check passed

  • Cline Pilot

    sickn33/agentic-awesome-skills

    Acts as a proxy for the Cline CLI, dispatching coding tasks one at a time, monitoring runs by hard evidence, relaying decisions to you and learning per-project preferences.

    47k GitHub starsUsed in 1 repo~4.6k tokens
    Auto-check passed

  • Content Creator

    sickn33/agentic-awesome-skills

    Drafts and reviews audience-specific content from supplied brand examples, with local scripts for brand voice and SEO diagnostics, channel templates and a content calendar.

    47k GitHub starsUsed in 1 repo~2.5k tokens
    Auto-check passed

Questions about AI Loop

What does AI Loop do?

Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work. AI Loop is an agent skill from sickn33/agentic-awesome-skills. Runs a bounded spec-build-review development loop with explicit scope, stop conditions, and human approval gates for risky or ambiguous work.

How do I install AI Loop in Claude Code?

Run `npx skills add sickn33/agentic-awesome-skills --skill ai-loop -a claude-code`. Or copy the skill folder (skills/ai-loop in sickn33/agentic-awesome-skills) into .claude/skills/ai-loop in your project. Claude Code loads it when a task matches its description.

How do I install AI Loop in Codex?

Run `npx skills add sickn33/agentic-awesome-skills --skill ai-loop -a codex`. Or copy the skill folder (skills/ai-loop in sickn33/agentic-awesome-skills) into .agents/skills/ai-loop in your project. Codex loads it when a task matches its description.

Can I use AI Loop in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add sickn33/agentic-awesome-skills --skill ai-loop -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ai-loop, .gemini/skills/ai-loop, .github/skills/ai-loop and .opencode/skills/ai-loop in your project.

What does AI Loop need to run?

SKILL.md names no scripts, command-line tools or credentials: AI Loop is instructions for the agent only.

Does AI Loop access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is AI Loop safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does AI Loop use?

AI Loop is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does AI Loop use?

About 2k tokens (SKILL.md is roughly 7.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to AI Loop?

Skills that share tags, products or a category with AI Loop: Bounded Work Item (SeemSeam/claude_codex_bridge, 3.6k stars), Bound (jongwony/epistemic-protocols, 173 stars), Bounded Work Item (SeemSeam/claude_codex_bridge, 3.6k stars) and Bounded Autoresearch (AgriciDaniel/claude-obsidian, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains AI Loop?

sickn33 (a GitHub user) maintains it in sickn33/agentic-awesome-skills, which has 47,343 GitHub stars. The repository holds 1,354 skills in this directory. The repository was last updated on October 7, 2026.

Source: sickn33/agentic-awesome-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.