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

Iterate

by sharpdeveye in sharpdeveye/maestro

A skill your agent uses when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.

MITAuto-check passedAgent Workflows

Install Iterate

skills CLI
$ npx skills add sharpdeveye/maestro --skill iterate -a claude-code

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

GitHub CLI
$ gh skill install sharpdeveye/maestro iterate --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/sharpdeveye/maestro.git skills-src && mkdir -p .claude/skills && cp -r skills-src/source/skills/iterate .claude/skills/iterate && 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
iterate
GitHub stars
592
Token cost
~851 tokens
SKILL.md length
372 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.

  • Works in 5 steps: Define Quality Criteria → Choose Evaluator Type → Design the Correction Loop → …
  • The workflow needs to self-correct
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Improve over time

What it does

Iterate is an agent skill from sharpdeveye/maestro. Use when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.

Its SKILL.md is about 850 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. The repository describes itself as: Workflow fluency for AI coding agents. 1 core skill · 25 commands · 7 domain references · memory layer · audit trail — works across Cursor, Claude Code, Gemini CLI, Copilot, and… The licence is MIT.

When your agent uses it

  • The workflow needs to self-correct
  • Improve over time
  • Establish feedback loops and evaluation cycles

Example prompts

  • “/iterate”

Workflow steps

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

  1. Define Quality Criteria
  2. Choose Evaluator Type
  3. Design the Correction Loop
  4. Set Up Regression Detection
  5. Continuous Monitoring

What it can do on your machine

Read from SKILL.md and the folder at commit 00f9115. 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

Iterate loads about 851 tokens when it runs. Until then it costs about 31 tokens; SKILL.md has 372 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~31
When it runs · the whole SKILL.md, loaded when a task matches
~851

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 sharpdeveye/maestro at commit 00f9115, republished under its MIT licence (© sharpdeveye). 372 words, ~851 tokens.

Download SKILL.mdSave it as .claude/skills/iterate/SKILL.md (or your agent's skills folder).
name
iterate
description
Use when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.
argument-hint
[target area]
category
enhancement
version
2.0.0
user-invocable
true

MANDATORY PREPARATION

Invoke /agent-workflow — it contains workflow principles, anti-patterns, and the Context Gathering Protocol. Follow the protocol before proceeding — if no workflow context exists yet, you MUST run /teach-maestro first.

Consult the feedback-loops reference in the agent-workflow skill for evaluation patterns and self-correction strategies.

Set up feedback loops that make workflows self-correcting and continuously improving. Iteration transforms one-shot gambles into convergent, reliable systems.

Feedback Loop Design
Step 1: Define Quality Criteria

What does "good output" look like? Score dimensions:

DimensionWeightThresholdMeasurement
Accuracy0.4≥ 0.8Factual correctness check
Completeness0.3≥ 0.7Required fields present
Format0.2≥ 0.9Schema compliance
Tone0.1≥ 0.6Appropriate for audience
Step 2: Choose Evaluator Type

Match evaluator to requirements:

  • Rule-based: Schema validation, field presence, value ranges (fast, free)
  • Self-check: Same model evaluates own output (fast, cheap, less reliable)
  • Cross-model: Different model evaluates (slower, more reliable)
  • Human-in-the-loop: Human review (slowest, most reliable, doesn't scale)
  • Hybrid: Rules first, then model check for what rules can't catch
Step 3: Design the Correction Loop
text
generate(input) → evaluate(output) → score
  if score ≥ threshold → return output
  if score < threshold AND attempts < max →
    enrich input with evaluator feedback
    generate again (with feedback)
  if attempts ≥ max → fallback or escalate

Critical: The retry input MUST be different from the original. Include:

  • The evaluator's specific feedback
  • What was wrong and why
  • A suggestion for how to fix it
Step 4: Set Up Regression Detection

When changing prompts, models, or tools:

  1. Run golden test set with OLD config → baseline scores
  2. Run golden test set with NEW config → new scores
  3. Compare: improvement ≥ 5% → accept; regression ≥ 5% → reject
Show full SKILL.md (139 more words)Show less
Step 5: Continuous Monitoring

For production workflows:

  • Sample 1-5% of outputs for automated evaluation
  • Track quality scores over time
  • Alert on downward trends
  • A/B test changes before full rollout
Iteration Checklist
  • Quality criteria defined with weights and thresholds
  • Evaluator selected and configured
  • Correction loop has max attempts limit
  • Feedback is injected into retries (not identical retry)
  • Golden test set exists with ≥ 10 cases
  • Regression detection configured for changes
  • Production monitoring in place

After setting up feedback loops, run /evaluate to validate the loop with real scenarios, then /refine for final polish.

NEVER:

  • Retry with the exact same input (definition of insanity)
  • Use the same weak model to both generate and evaluate
  • Skip the max attempts limit (infinite loops are real)
  • Deploy changes without regression testing against golden set
  • Monitor only errors — track quality scores over time

© sharpdeveye, 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 source/skills/iterate of sharpdeveye/maestro.

Open the folder on GitHubat commit 00f9115

Compare with similar skills

Iterate 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.

Iterate compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Iterate this skillsharpdeveye/maestro592—~851Automated safety check: PassMIT
MCP Server Builderanthropics/skills180k64 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k11 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k35 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers296k2 repos~5.1kAutomated safety check: PassMIT
Claude Code Agent Developmentanthropics/claude-plugins-official38k8 repos~2.8kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 64 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 11 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes

  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 35 repos~1.4k tokens
    Agent WorkflowsAuto-check passed

  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    296k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed

  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 8 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    795 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed

More from sharpdeveye/maestro

All 25 skills in this repo

  • Accelerate

    sharpdeveye/maestro

    A skill your agent uses when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.

    592 GitHub stars~745 tokensUpdated 5 mo ago
    Auto-check passed

  • Chain

    sharpdeveye/maestro

    A skill your agent uses when the workflow needs multi-step processing with sequential, parallel, or conditional tool compositions and proper data flow.

    592 GitHub stars~607 tokensUpdated 5 mo ago
    Auto-check passed

  • Compose

    sharpdeveye/maestro

    A skill your agent uses when a single agent demonstrably cannot handle the task and multi-agent coordination is justified.

    592 GitHub stars~720 tokensUpdated 5 mo ago
    Auto-check passed

  • Diagnose

    sharpdeveye/maestro

    A skill your agent uses when the user wants to find problems, audit workflow quality, or get a comprehensive health check on their AI workflow.

    592 GitHub stars~1.5k tokensUpdated 5 mo ago
    Auto-check passed

  • Extract Pattern

    sharpdeveye/maestro

    A skill your agent uses when the user wants to create templates, extract reusable patterns, document solutions, or build a pattern library from working workflows.

    592 GitHub stars~664 tokensUpdated 5 mo ago
    Auto-check passed

  • Fortify

    sharpdeveye/maestro

    A skill your agent uses when the workflow lacks error handling, has been failing in production, or needs retry logic, fallback strategies, and circuit breakers.

    592 GitHub stars~688 tokensUpdated 5 mo ago
    Auto-check passed

Categories

Questions about Iterate

What does Iterate do?

A skill your agent uses when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles. Iterate is an agent skill from sharpdeveye/maestro. Use when the workflow needs to self-correct, improve over time, or establish feedback loops and evaluation cycles.

When should I use Iterate?

Iterate fits situations like: the workflow needs to self-correct; improve over time; establish feedback loops and evaluation cycles.

How do I install Iterate in Claude Code?

Run `npx skills add sharpdeveye/maestro --skill iterate -a claude-code`. Or copy the skill folder (source/skills/iterate in sharpdeveye/maestro) into .claude/skills/iterate in your project. Claude Code loads it when a task matches its description.

How do I install Iterate in Codex?

Run `npx skills add sharpdeveye/maestro --skill iterate -a codex`. Or copy the skill folder (source/skills/iterate in sharpdeveye/maestro) into .agents/skills/iterate in your project. Codex loads it when a task matches its description.

Can I use Iterate 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 sharpdeveye/maestro --skill iterate -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/iterate, .gemini/skills/iterate, .github/skills/iterate and .opencode/skills/iterate in your project.

What does Iterate need to run?

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

Does Iterate 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 Iterate 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 Iterate use?

Iterate 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 Iterate use?

About 851 tokens (SKILL.md is roughly 3.4k 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 Iterate?

Skills that share tags, products or a category with Iterate: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 296k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Iterate?

sharpdeveye (a GitHub user) maintains it in sharpdeveye/maestro, which has 592 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on April 29, 2026.

Source: sharpdeveye/maestro on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.