New: 97,000+ 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

Design Loop

by DanMcInerney in DanMcInerney/orchflows

Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.

MITAuto-check passedAgent Workflows

Install Design Loop

skills CLI
$ npx skills add DanMcInerney/orchflows --skill design-loop -a claude-code

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

GitHub CLI
$ gh skill install DanMcInerney/orchflows design-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/DanMcInerney/orchflows.git skills-src && mkdir -p .claude/skills && cp -r skills-src/example-workflows/design-loop/skills/design-loop .claude/skills/design-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
design-loop
GitHub stars
117
Token cost
~870 tokens
SKILL.md length
417 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.

  • Works in 5 steps: Establish or resume the checkpoint,… → Record a new attempt before work, or… → Create an isolated baseline copy; apply… → …
  • Tasks that involve Brainstorming
  • SKILL.md covers Bounds, Run, Failure and resumption and Return
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Design Loop is an agent skill from DanMcInerney/orchflows. Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.

Its SKILL.md is about 870 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 Agent Workflows, covering Brainstorming. The repository describes itself as: 2 skills, composable into workflows, which can then be built into more complex workflows. The licence is MIT.

When your agent uses it

  • Tasks that involve Brainstorming

Example prompts

  • “/design-loop”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Establish or resume the checkpoint, state N and bounds, and preserve the initial baseline. Start each cycle from the last accepted state…
  2. Record a new attempt before work, or resume the active one. Apply brainstorm-research with request, baseline and observations, then…
  3. Create an isolated baseline copy; apply implement-increment with the design. Freeze the returned candidate; pass it, the baseline and…
  4. Apply analyze-iteration to all cycle evidence, including failures/gaps. Check its recommendation; record adopt/retain, exact accepted…
  5. Stop at the bound or declared early-stop condition. Further work requires a new or extended caller request.

What it can do on your machine

Read from SKILL.md and the folder at commit 8d16eb3. 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

Design Loop loads about 870 tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 417 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
~870

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 DanMcInerney/orchflows at commit 8d16eb3, republished under its MIT licence (© DanMcInerney). 417 words, ~870 tokens.

Download SKILL.mdSave it as .claude/skills/design-loop/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
design-loop
description
Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.
disable-model-invocation
true

Use the handoff contract. Inputs: endgoal, starting workspace/artifacts, output directory and optional N, criteria, constraints, domains and scoped model/effort choices. Reuse context and extend it for new work.

Bounds

N caps attempted cycles, including the first PoC and failures. Require a positive integer; default to 3 and state it. Apply core's iteration bounds; brainstorming is a cycle's first work. Run through N unless the caller stops, a resource bound is reached, required capability or authorization is missing, or explicit stop-on-goal applies. Goal attainment alone does not shorten the run.

Choose stage assignments under core execution rules, preserving dependencies, independent testing and caller limits.

Run

  1. Establish or resume the checkpoint, state N and bounds, and preserve the initial baseline. Start each cycle from the last accepted state. Target the smallest working PoC first; later cycles use accumulated decisions and observations, including failures.
  2. Record a new attempt before work, or resume the active one. Apply brainstorm-research with request, baseline and observations, then design-increment to its result.
  3. Create an isolated baseline copy; apply implement-increment with the design. Freeze the returned candidate; pass it, the baseline and evaluation plan to test-increment.
  4. Apply analyze-iteration to all cycle evidence, including failures/gaps. Check its recommendation; record adopt/retain, exact accepted state and next-cycle observations. Checkpoint each returned stage; use the rules below for incomplete stages.
  5. Stop at the bound or declared early-stop condition. Further work requires a new or extended caller request.

Brainstorm-research calls two leaves; testing supplies one independent comparison round. There is no additional final review or repair loop.

Show full SKILL.md (159 more words)Show less

Failure and resumption

On failure, retain evidence and mark dependent stages unexecuted. Run scheduled analysis on the partial handoff if possible; otherwise record missing analysis and retain the baseline. Failed attempts count. Continue only if another bounded cycle can progress; persistent capability/authorization blocks end the run with a gap. Corrections belong to later cycles within N.

For no justified change, mark implementation/testing inapplicable, analyze the evidence and record retain. The attempt counts; normal early-stop rules apply.

To resume, read checkpoint and attempt-start records and verify state/artifact identities. Continue the same attempt's first unfinished stage, reusing valid work and rejoining live assignments before replacements. Changed inputs make affected downstream evidence stale; repeating completed stages requires a new or extended caller run.

Return

Return exact accepted state, usage, initial-to-final changes/evidence, completed/attempted counts, decisions, gaps and checkpoint path. Keep retained candidates as evidence. For requested integration, verify the checkout still matches its preserved starting state; report conflicts instead of overwriting newer work.

© DanMcInerney, 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 example-workflows/design-loop/skills/design-loop of DanMcInerney/orchflows.

  • SKILL.md
  • agents/openai.yaml

Open the folder on GitHubat commit 8d16eb3

Compare with similar skills

Design 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.

Design Loop compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Design Loop this skillDanMcInerney/orchflows117—~870Automated safety check: PassMIT
Brainstormingxpinjection/test-driven-spring-boot11254 repos~2.6kAutomated safety check: PassMIT
LLM Councilgcpdev/llm-council-skill4611 repos~1kAutomated safety check: NotesMIT
Typesafe AIOpenAgentsInc/openagents4559 repos~2.5kAutomated safety check: PassMIT
Yao Meta Skillyaojingang/yao-meta-skill2.7k—~768Automated safety check: PassMIT
Trellis StartROYIANS/foliq-print-template-designer1356 repos~646Automated safety check: PassMIT

Similar skills

  • Brainstorming

    xpinjection/test-driven-spring-boot

    You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior.

    112 GitHub starsUsed in 54 repos~2.6k tokens
    Agent WorkflowsAuto-check passed

  • LLM Council

    gcpdev/llm-council-skill

    Multi-LLM collaborative brainstorming and planning. An agent skill from gcpdev/llm-council-skill.

    461 GitHub starsUsed in 1 repo~1k tokens
    Agent WorkflowsAuto-check: notes

  • Typesafe AI

    OpenAgentsInc/openagents

    Build AI-powered software with TypeSafe: small units of AI intelligence you can use like programming primitives.

    455 GitHub starsUsed in 9 repos~2.5k tokens
    Agent WorkflowsAuto-check passed

  • Yao Meta Skill

    yaojingang/yao-meta-skill

    Create, improve, or evaluate an existing skill from workflows, prompts, SOPs, scripts.

    2.7k GitHub stars~768 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

  • Trellis Start

    ROYIANS/foliq-print-template-designer

    Initializes an AI development session by reading workflow guides, developer identity, git status, active tasks, and project guidelines from .trellis/.

    135 GitHub starsUsed in 6 repos~646 tokens
    Agent WorkflowsAuto-check passed

  • Brainstorming Before Building

    jnMetaCode/superpowers-zh

    Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.

    8.3k GitHub stars~1.8k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

More from DanMcInerney/orchflows

All 12 skills in this repo

  • Evolve

    DanMcInerney/orchflows

    Iteratively improve any artifact and its improvement harness, inventing evaluation when needed; supports bounded runs, tournaments and continuous resumable search.

    117 GitHub stars~805 tokensUpdated 3 days ago
    Auto-check passed

  • Benchmaker

    DanMcInerney/orchflows

    Build benchmarks of realistic, hard agent tasks, researched from real work, admitting only verified, shortcut-resistant, calibrated tasks and reporting how well the suite separates systems.

    117 GitHub stars~2k tokensUpdated 3 days ago
    Auto-check passed

  • 3D Browser Game

    DanMcInerney/orchflows

    Build a complete Three.js game or bounded production phase through mechanics experiments, Blender assets, QA and independent playtests.

    117 GitHub stars~1.5k tokensUpdated 3 days ago
    Auto-check passed

  • Export Workflow

    DanMcInerney/orchflows

    Export an Orchflows workflow as a standalone native skill with a portability report and bounded trial.

    117 GitHub stars~674 tokensUpdated 3 days ago
    Auto-check passed

  • Gauntlet Loop

    DanMcInerney/orchflows

    Drive an ambitious goal past a real-world quality bar by splitting it into pieces, each looped through a builder and a fresh, harsh, blind critic until ours reaches the bar or the caller stops.

    117 GitHub stars~1.2k tokensUpdated 3 days ago
    Auto-check passed

  • Orchflows Review

    DanMcInerney/orchflows

    Review Orchflows against its purpose and design principles (architecture, workflow design, wording and bugs) and apply reviewed improvements on unmerged branches.

    117 GitHub stars~1k tokensUpdated 3 days ago
    Auto-check passed

Categories

Questions about Design Loop

What does Design Loop do?

Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis. Design Loop is an agent skill from DanMcInerney/orchflows. Develop a project endgoal through N bounded cycles of brainstorm and research, design, implementation, comparison testing and analysis.

When should I use Design Loop?

Design Loop fits situations like: tasks that involve Brainstorming.

How do I install Design Loop in Claude Code?

Run `npx skills add DanMcInerney/orchflows --skill design-loop -a claude-code`. Or copy the skill folder (example-workflows/design-loop/skills/design-loop in DanMcInerney/orchflows) into .claude/skills/design-loop in your project. Claude Code loads it when a task matches its description.

How do I install Design Loop in Codex?

Run `npx skills add DanMcInerney/orchflows --skill design-loop -a codex`. Or copy the skill folder (example-workflows/design-loop/skills/design-loop in DanMcInerney/orchflows) into .agents/skills/design-loop in your project. Codex loads it when a task matches its description.

Can I use Design 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 DanMcInerney/orchflows --skill design-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/design-loop, .gemini/skills/design-loop, .github/skills/design-loop and .opencode/skills/design-loop in your project.

What does Design Loop need to run?

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

Does Design 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 Design 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 Design Loop use?

Design 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 Design Loop use?

About 870 tokens (SKILL.md is roughly 3.5k 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 Design Loop?

Skills that share tags, products or a category with Design Loop: Brainstorming (xpinjection/test-driven-spring-boot, 112 stars), LLM Council (gcpdev/llm-council-skill, 461 stars), Typesafe AI (OpenAgentsInc/openagents, 455 stars) and Yao Meta Skill (yaojingang/yao-meta-skill, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Design Loop?

DanMcInerney (a GitHub user) maintains it in DanMcInerney/orchflows, which has 117 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 4, 2026.

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