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

Orchestrator Implementer Judge Loop

by danpacho in danpacho/tailwindest

Strict orchestration workflow for engineering tasks that must be solved one numbered problem at a time through an explicit cycle: define the current problem, build a Robust Code strategy, delegate…

MITAuto-check passedFrontend & Design

Install Orchestrator Implementer Judge Loop

skills CLI
$ npx skills add danpacho/tailwindest --skill orchestrator-implementer-judge-loop -a claude-code

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

GitHub CLI
$ gh skill install danpacho/tailwindest orchestrator-implementer-judge-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/danpacho/tailwindest.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/orchestrator-implementer-judge-loop .claude/skills/orchestrator-implementer-judge-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
orchestrator-implementer-judge-loop
GitHub stars
159
Token cost
~1.2k tokens
SKILL.md length
507 words
Files
2
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

Strict orchestration workflow for engineering tasks that must be solved one numbered problem at a time through an explicit cycle: define the current problem, build a Robust Code strategy, delegate…

  • Works in 7 steps: Define the current problem → Build the Robust Code strategy → Delegate to [OMNISCIENT IMPLEMENTER] → …
  • Codex must run a deterministic orchestrator-to-implementer-to-judge regression loop with bounded scope
  • SKILL.md covers Core Role, Mandatory Cycle, Hard Rules and Required Per-Problem Artifacts, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Orchestrator Implementer Judge Loop is an agent skill from danpacho/tailwindest. Strict orchestration workflow for engineering tasks that must be solved one numbered problem at a time through an explicit cycle: define the current problem, build a Robust Code strategy, delegate the work to an implementer with the current situation and exact solution method, send the result to a judge with the audit target and audit criteria, repeat implementation and judgment until defects are closed, then issue a final orchestrator verdict before moving to the next problem. Use when Codex must run a…

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).

It sits in Frontend & Design, covering CSS and styling. It works with Tailwind CSS and TypeScript. The repository describes itself as: Create tailwind types & Build type-safe tailwind products. The licence is MIT.

When your agent uses it

  • Codex must run a deterministic orchestrator-to-implementer-to-judge regression loop with bounded scope
  • Explicit packets

Example prompts

  • “/orchestrator-implementer-judge-loop”

Workflow steps

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

  1. Define the current problem
  2. Build the Robust Code strategy
  3. Delegate to [OMNISCIENT IMPLEMENTER]
  4. Receive the implementation result
  5. Delegate to [OMNISCIENT JUDGE]
  6. Run the defect loop
  7. Issue the final orchestrator verdict

What it can do on your machine

Read from SKILL.md and the folder at commit 665d96a. 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

Orchestrator Implementer Judge Loop loads about 1.2k tokens when it runs. Until then it costs about 167 tokens; SKILL.md has 507 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~167
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k

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 danpacho/tailwindest at commit 665d96a, republished under its MIT licence (© danpacho). 507 words, ~1,195 tokens.

Download SKILL.mdSave it as .claude/skills/orchestrator-implementer-judge-loop/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
orchestrator-implementer-judge-loop
description
Strict orchestration workflow for engineering tasks that must be solved one numbered problem at a time through an explicit cycle: define the current problem, build a Robust Code strategy, delegate the work to an implementer with the current situation and exact solution method, send the result to a judge with the audit target and audit criteria, repeat implementation and judgment until defects are closed, then issue a final orchestrator verdict before moving to the next problem. Use when Codex must run a deterministic orchestrator-to-implementer-to-judge regression loop with bounded scope, explicit packets, and no ambiguity.

Orchestrator Implementer Judge Loop

Core Role

Act as [OMNISCIENT ORCHESTRATOR]. Solve one numbered problem at a time. Finish the full cycle for the current problem before touching the next problem. Base every strategy on robust-code: explicit assumptions, minimal change, bounded scope, and verifiable success criteria. Stop and ask the user when a requirement is ambiguous, architectural, or irreversible.

Mandatory Cycle

For each numbered problem, execute the following order without skipping or merging steps.

1. Define the current problem

State the exact symptom. State the scope boundary. State the constraints. State the desired end state. State the proof required to close the problem. Split the work into the smallest task that can be implemented and audited safely.

2. Build the Robust Code strategy

Produce a short Robust Code Strategy with:

  • Current problem situation
  • Minimal fix or implementation direction
  • In-scope files or modules
  • Out-of-scope work
  • Feature-case verification
  • Complex edge-case verification
  • Rejection conditions
3. Delegate to [OMNISCIENT IMPLEMENTER]

Send the work in this exact structure:

text
[IMPLEMENTER PACKET]
Problem:
Current situation:
Goal:
Exact implementation method:
In-scope files or modules:
Out-of-scope changes:
Verification to satisfy:
Completion signal:

Require the implementer to change only what is necessary. Require the implementer to return concrete completion evidence. Do not allow the implementer to declare the task accepted.

4. Receive the implementation result

Collect the changed artifact. Collect test or verification evidence. Collect unresolved risks. Treat the result as implemented, not accepted.

5. Delegate to [OMNISCIENT JUDGE]

Send the audit in this exact structure:

text
[JUDGE PACKET]
Problem:
Audit target:
Audit criteria:
Required evidence:
Rejection rule:
Output format:

Set Output format to PASS or FAIL plus a numbered defect list. Require the judge to evaluate only against the stated criteria unless a critical defect is discovered.

6. Run the defect loop

If the judge returns FAIL, convert each defect into a precise rework order. Re-send an updated implementer packet that includes:

  • Defect number
  • Observed failure
  • Violated criterion
  • Exact correction required
  • Regression guard

Return to Step 4 after re-implementation. Repeat the implementation and judgment loop until the judge returns PASS.

Show full SKILL.md (201 more words)Show less
7. Issue the final orchestrator verdict

Re-check the accepted result yourself. Confirm that the problem is truly closed. Confirm that the required verification evidence exists. Only after the final verdict passes, move to the next numbered problem.

Hard Rules

  • Never merge strategy, implementation, and judgment into one step.
  • Never move to the next problem on a provisional pass.
  • Never send vague feedback such as improve this or clean this up.
  • Never allow the implementer to self-approve.
  • Never allow the judge to implement the fix it is auditing.
  • Never accept unrelated refactors during a defect loop.
  • Always preserve previously passing behavior while fixing defects.
  • Always make the audit criteria explicit enough that a third party can reproduce the verdict.

Required Per-Problem Artifacts

Keep the following artifacts visible for each problem:

  • Problem definition
  • Robust Code strategy
  • Implementer packet
  • Judge packet
  • Defect ledger
  • Final orchestrator verdict

Execution Mode

Use real delegation when the environment and the user request permit subagents or distinct workers. If literal delegation is unavailable, emulate the same separation in ordered sections and do not collapse the acceptance gate. Maintain role separation even in a single-thread execution.

Minimal Output Frame

Use this frame when the task needs a visible control surface:

text
[PROBLEM n]
Status: OPEN | IN-LOOP | PASSED

[ROBUST CODE STRATEGY]
...

[IMPLEMENTER PACKET]
...

[JUDGE PACKET]
...

[DEFECT LEDGER]
...

[FINAL ORCHESTRATOR VERDICT]
...

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

Files

SKILL.md and 1 other file in .agents/skills/orchestrator-implementer-judge-loop of danpacho/tailwindest.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 665d96a

Compare with similar skills

Orchestrator Implementer Judge 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.

Orchestrator Implementer Judge Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Orchestrator Implementer Judge Loop this skilldanpacho/tailwindest159—~1.2kAutomated safety check: PassMIT
Cross Platform Tauri UIifer47/markeron1.2k—~2kAutomated safety check: PassMIT
Language Supportlive-codes/livecodes1.5k—~1.6kAutomated safety check: PassMIT
Vue Componentsscalar/scalar16k—~886Automated safety check: PassMIT
Rasengan Configrasengan-dev/rasenganjs125—~1.1kAutomated safety check: PassMIT
Frontend Code ReviewProgrammerAnthony/Anything-Extract139—~957Automated safety check: PassMIT

Similar skills

  • Cross Platform Tauri UI

    ifer47/markeron

    Cross-platform UI styling for MarkerOn Tauri app (macOS WKWebView vs Windows WebView2).

    1.2k GitHub stars~2k tokensUpdated today
    Frontend & DesignAuto-check passed

  • Language Support

    live-codes/livecodes

    Work with 90+ supported languages, compilers, CSS processors, and WASM-compiled languages for markup, style, and script editors.

    1.5k GitHub stars~1.6k tokensUpdated today
    Frontend & DesignAuto-check passed

  • Vue Components

    scalar/scalar

    Build Vue 3 components with TypeScript and Tailwind using clean structure, composable logic, accessibility, and maintainable patterns.

    16k GitHub stars~886 tokensUpdated today
    Frontend & DesignAuto-check passed

  • Rasengan Config

    rasengan-dev/rasenganjs

    Project configuration and rendering mode patterns for Rasengan.js.

    125 GitHub stars~1.1k tokensUpdated yesterday
    Frontend & DesignAuto-check passed

  • Frontend Code Review

    ProgrammerAnthony/Anything-Extract

    指导在项目中对前端代码（Next.js/React/TypeScript/Tailwind 等）进行结构、可维护性、性能与一致性审查，基于既定规则清单。适用于用户请求审查 .tsx/.ts/.js/.jsx 等前端文件或前端目录下的页面与组件。不用于后端代码（如 .py）。

    139 GitHub stars~957 tokensUpdated 4 mo ago
    Frontend & DesignAuto-check passed

  • Nextjs App

    ccplugins/awesome-claude-code-plugins

    Bootstrap a new Next.js (App Router, TypeScript) web app with current packages and no deprecated APIs.

    968 GitHub stars~1.1k tokensUpdated 1 mo ago
    Frontend & DesignAuto-check: notes

Works with

Categories

Questions about Orchestrator Implementer Judge Loop

What does Orchestrator Implementer Judge Loop do?

Strict orchestration workflow for engineering tasks that must be solved one numbered problem at a time through an explicit cycle: define the current problem, build a Robust Code strategy, delegate…. Orchestrator Implementer Judge Loop is an agent skill from danpacho/tailwindest. Strict orchestration workflow for engineering tasks that must be solved one numbered problem at a time through an explicit cycle: define the current problem, build a Robust Code strategy, delegate the work to an implementer with the current situation and exact solution method, send the result to a judge with the audit target and audit criteria, repeat implementation and judgment until defects are closed, then issue a final orchestrator verdict before moving to the next problem.

When should I use Orchestrator Implementer Judge Loop?

Orchestrator Implementer Judge Loop fits situations like: Codex must run a deterministic orchestrator-to-implementer-to-judge regression loop with bounded scope; explicit packets.

How do I install Orchestrator Implementer Judge Loop in Claude Code?

Run `npx skills add danpacho/tailwindest --skill orchestrator-implementer-judge-loop -a claude-code`. Or copy the skill folder (.agents/skills/orchestrator-implementer-judge-loop in danpacho/tailwindest) into .claude/skills/orchestrator-implementer-judge-loop in your project. Claude Code loads it when a task matches its description.

How do I install Orchestrator Implementer Judge Loop in Codex?

Run `npx skills add danpacho/tailwindest --skill orchestrator-implementer-judge-loop -a codex`. Or copy the skill folder (.agents/skills/orchestrator-implementer-judge-loop in danpacho/tailwindest) into .agents/skills/orchestrator-implementer-judge-loop in your project. Codex loads it when a task matches its description.

Can I use Orchestrator Implementer Judge 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 danpacho/tailwindest --skill orchestrator-implementer-judge-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/orchestrator-implementer-judge-loop, .gemini/skills/orchestrator-implementer-judge-loop, .github/skills/orchestrator-implementer-judge-loop and .opencode/skills/orchestrator-implementer-judge-loop in your project.

What does Orchestrator Implementer Judge Loop need to run?

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

Does Orchestrator Implementer Judge 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 Orchestrator Implementer Judge 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 Orchestrator Implementer Judge Loop use?

Orchestrator Implementer Judge 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 Orchestrator Implementer Judge Loop use?

About 1.2k tokens (SKILL.md is roughly 4.8k 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 Orchestrator Implementer Judge Loop?

Skills that share tags, products or a category with Orchestrator Implementer Judge Loop: Cross Platform Tauri UI (ifer47/markeron, 1.2k stars), Language Support (live-codes/livecodes, 1.5k stars), Vue Components (scalar/scalar, 16k stars) and Rasengan Config (rasengan-dev/rasenganjs, 125 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Orchestrator Implementer Judge Loop?

danpacho (a GitHub user) maintains it in danpacho/tailwindest, which has 159 GitHub stars. The repository was last updated on August 5, 2026.

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