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

Open Loops Advance

by real-simple-labs in real-simple-labs/parker-brain

Turn a promoted open loop into a hypothesis — a falsifiable prediction plus the few complementary pulls that together settle it, triangulated across the ad account, reviews, and competitors as the…

Custom licenceAuto-check passed

Install Open Loops Advance

skills CLI
$ npx skills add real-simple-labs/parker-brain --skill open-loops-advance -a claude-code

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

GitHub CLI
$ gh skill install real-simple-labs/parker-brain open-loops-advance --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/real-simple-labs/parker-brain.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/open-loops-advance .claude/skills/open-loops-advance && 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
open-loops-advance
GitHub stars
102
Token cost
~2.1k tokens
SKILL.md length
1,128 words
Files
5
Skills in repo
22
Repo updated
First seen
Licence
Custom licence

At a glance

Turn a promoted open loop into a hypothesis — a falsifiable prediction plus the few complementary pulls that together settle it, triangulated across the ad account, reviews, and competitors as the…

  • Works in 6 steps: Load the canon and the brand. Read… → Take the promoted loop, do not re-grade… → Turn the question into a falsifiable… → …
  • Advancing a Tier-1 (or activated Tier-
  • SKILL.md covers Goal, What you are working from, How this skill runs and Output, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Open Loops Advance is an agent skill from real-simple-labs/parker-brain. Turn a promoted open loop into a hypothesis — a falsifiable prediction plus the few complementary pulls that together settle it, triangulated across the ad account, reviews, and competitors as the question needs and runnable with Parker's tools. Use when advancing a Tier-1 (or activated Tier-2) loop from the open-loops roll-up into the testing queue, or when the user says advance the open loops, form a hypothesis, or plan how to test a loop.

Its SKILL.md is about 2.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 5 other files (for example `processes/INDEX.md`, `processes/build-the-test-plan.md` and `processes/the-approval-gate.md`).

When your agent uses it

  • Advancing a Tier-1 (or activated Tier-
  • Loop from the open-loops roll-up into the testing queue
  • The user says advance the open loops
  • Form a hypothesis

Example prompts

  • “/open-loops-advance”

Workflow steps

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

  1. Load the canon and the brand. Read open-loops-system.md (the lifecycle and the hypothesis + validation definitions) and…
  2. Take the promoted loop, do not re-grade it. Read the loop from open-loops/promoted/[YYYY-MM]/ or the Tier-1 list of the latest…
  3. Turn the question into a falsifiable prediction. The loop's open question becomes a prediction the research can confirm or refute, stated…
  4. Design the test — triangulate the full picture, not a single pull and not a research study. See processes/build-the-test-plan.md. Pick the…
  5. Run the approval gate. See processes/the-approval-gate.md. Brand-routed loops and novel high-stakes loops whose plan needs the user go to…
  6. Write the hypothesis document and route it. Use the output spec below. Route to hypotheses/awaiting-user/[YYYY-MM]/ when it needs the…

What it can do on your machine

Read from SKILL.md and the folder at commit 2a6f6c6. 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 (its code samples are markdown).

    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

Open Loops Advance loads about 2.1k tokens when it runs. Until then it costs about 116 tokens; SKILL.md has 1,128 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~116
When it runs · the whole SKILL.md, loaded when a task matches
~2.1k

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

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 1,128 words (~2,098 tokens).

“Take a loop the open-loops roll-up already promoted and turn it into a hypothesis: the loop's open question becomes a falsifiable prediction, and the test that would settle it — the few complementary pulls that each see a different angle…”

— opening of SKILL.md by real-simple-labs, Custom licence
name
open-loops-advance
triggers
advance the open loops, advance this loop, form a hypothesis, turn this loop into a hypothesis, plan how to test this loop, what's the hypothesis on this open…

Read the full SKILL.md on GitHub

Files

SKILL.md and 4 other files in .claude/skills/open-loops-advance of real-simple-labs/parker-brain.

  • SKILL.md
  • processes/INDEX.md
  • processes/build-the-test-plan.md
  • processes/the-approval-gate.md
  • strategy.md

Open the folder on GitHubat commit 2a6f6c6

Compare with similar skills

Open Loops Advance 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.

Open Loops Advance compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Open Loops Advance this skillreal-simple-labs/parker-brain102—~2.1kAutomated safety check: PassCustom licence
Loopalirezarezvani/claude-skills28k1 repos~1.1kAutomated safety check: PassMIT
Autonomous Loopsaffaan-m/ECC277k4 repos~5.8kAutomated safety check: PassMIT
Benchmark Optimization Loopaffaan-m/ECC277k1 repos~664Automated safety check: PassMIT
Loopasgeirtj/system_prompts_leaks69k—~2.2kAutomated safety check: WarnCC0-1.0
Continuous Agent Loopaffaan-m/ECC277k5 repos~298Automated safety check: PassMIT

Similar skills

  • Loop

    alirezarezvani/claude-skills

    Start an autonomous experiment loop with user-selected interval (10min, 1h, daily, weekly, monthly).

    28k GitHub starsUsed in 1 repo~1.1k tokens
    Agent WorkflowsAuto-check passed

  • Autonomous Loops

    affaan-m/ECC

    Patterns and architectures for autonomous Claude Code loops — from simple sequential pipelines to RFC-driven multi-agent DAG systems.

    277k GitHub starsUsed in 4 repos~5.8k tokens
    Agent WorkflowsAuto-check passed

  • Benchmark Optimization Loop

    affaan-m/ECC

    Convert 'make it faster' requests into a bounded measured optimization loop — baseline first, generate one-hypothesis variants, benchmark each against a correctness gate, and promote the fastest…

    277k GitHub starsUsed in 1 repo~664 tokens
    Auto-check passed

  • Loop

    asgeirtj/system_prompts_leaks

    Run a prompt or slash command on a recurring interval (e.g. An agent skill from asgeirtj/system_prompts_leaks.

    69k GitHub stars~2.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check: warnings

  • Continuous Agent Loop

    affaan-m/ECC

    Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls.

    277k GitHub starsUsed in 5 repos~298 tokens
    Agent WorkflowsAuto-check passed

  • Loop Design Check

    affaan-m/ECC

    Design a goal-oriented agent loop or review one for failure modes: spinning, Goodhart-gaming the verifier, or running a wrong answer to completion.

    277k GitHub starsUsed in 1 repo~2.9k tokens
    Agent WorkflowsAuto-check passed

More from real-simple-labs/parker-brain

All 22 skills in this repo

  • Open Loops Validate

    real-simple-labs/parker-brain

    Run a hypothesis's test plan, gather the evidence, and honestly resolve the loop into one of the four validation states — validated, invalidated, inconclusive, or insufficient evidence.

    102 GitHub stars~1.8k tokensUpdated yesterday
    Auto-check passed

  • Propagate Craft

    real-simple-labs/parker-brain

    Push-based re-ship of the factory methodology bundle into brand brains that carry the method as copied files — the legacy vendored-parker-system layout and decoupled brains that asked for a refresh.

    102 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

  • Weekly Creative Report

    real-simple-labs/parker-brain

    Build the brand's weekly creative report, a polished, shareable page an agency can send straight to the brand's CMO and team.

    102 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed

  • Update Parker Skill

    real-simple-labs/parker-brain

    Make a correct update to Parker's prompts, system docs, rubrics, knowledge docs, training corpus, or brand outputs — and propagate the change everywhere it needs to land.

    102 GitHub stars~4.6k tokensUpdated yesterday
    Auto-check passed

  • Ad Account Analysis

    real-simple-labs/parker-brain

    Analyze Meta ad account data — read what's spending, what's converting, what's fatiguing, and where the audience is being reached.

    102 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed

  • Dream

    real-simple-labs/parker-brain

    Run the dreaming system on demand for a brand and the person using it.

    102 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

Questions about Open Loops Advance

What does Open Loops Advance do?

Turn a promoted open loop into a hypothesis — a falsifiable prediction plus the few complementary pulls that together settle it, triangulated across the ad account, reviews, and competitors as the…. Open Loops Advance is an agent skill from real-simple-labs/parker-brain. Turn a promoted open loop into a hypothesis — a falsifiable prediction plus the few complementary pulls that together settle it, triangulated across the ad account, reviews, and competitors as the question needs and runnable with Parker's tools.

When should I use Open Loops Advance?

Open Loops Advance fits situations like: advancing a Tier-1 (or activated Tier-; loop from the open-loops roll-up into the testing queue; the user says advance the open loops; form a hypothesis.

How do I install Open Loops Advance in Claude Code?

Run `npx skills add real-simple-labs/parker-brain --skill open-loops-advance -a claude-code`. Or copy the skill folder (.claude/skills/open-loops-advance in real-simple-labs/parker-brain) into .claude/skills/open-loops-advance in your project. Claude Code loads it when a task matches its description.

How do I install Open Loops Advance in Codex?

Run `npx skills add real-simple-labs/parker-brain --skill open-loops-advance -a codex`. Or copy the skill folder (.claude/skills/open-loops-advance in real-simple-labs/parker-brain) into .agents/skills/open-loops-advance in your project. Codex loads it when a task matches its description.

Can I use Open Loops Advance 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 real-simple-labs/parker-brain --skill open-loops-advance -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/open-loops-advance, .gemini/skills/open-loops-advance, .github/skills/open-loops-advance and .opencode/skills/open-loops-advance in your project.

What does Open Loops Advance need to run?

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

Does Open Loops Advance 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 Open Loops Advance 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 Open Loops Advance use?

Open Loops Advance has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does Open Loops Advance use?

About 2.1k tokens (SKILL.md is roughly 8.4k 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 Open Loops Advance?

Skills that share tags, products or a category with Open Loops Advance: Loop (alirezarezvani/claude-skills, 28k stars), Autonomous Loops (affaan-m/ECC, 277k stars), Benchmark Optimization Loop (affaan-m/ECC, 277k stars) and Loop (asgeirtj/system_prompts_leaks, 69k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Open Loops Advance?

real-simple-labs (a GitHub organization) maintains it in real-simple-labs/parker-brain, which has 102 GitHub stars. The repository holds 22 skills in this directory. The repository was last updated on October 9, 2026.

Source: real-simple-labs/parker-brain on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.