loop-library
The loop-library skill assists users in discovering, finding, auditing, adapting, and designing repeatable AI agent loops. It provides a structured framework for creating feedback systems with clear triggers, actions, verification steps, and stopping conditions.
Is loop-library safe to install?
Review the source first: our audit of loop-library's source files found 0 shell commands, 2 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill makes network requests to fetch catalog data and reads local files to analyze codebases and coding threads.
How we audit skills: our security review methodology.
Who is this skill for?
Software engineers and AI agent developers who want to automate recurring tasks or optimize existing agent workflows.
What can you do with it?
- Analyze codebases and coding threads to identify repeated work suitable for automation.
- Search for and recommend published loops from a catalog.
- Audit existing agent loops for weaknesses in logic, safety, or stopping conditions.
- Adapt existing loops by modifying thresholds, tools, or cadences.
- Design new agent loops through a structured interview process.
How good is this skill?
Quality score: 5/10. The skill provides clear, actionable instructions and adheres to strict safety guidelines regarding loop design and execution.
What does the skill file contain?
# Loop Library Help the user discover loop opportunities in existing engineering work, reuse a published Loop Library loop when one fits, audit or repair an existing loop, or design a new one through a focused interview. Treat a loop as a feedback system with terminal states, not as permission for endless autonomy. ## Route the request Choose the smallest useful path: - **Discover:** Analyze a codebase, coding-thread history, or both for repeated work that can become a bounded loop. - **Find:** Recommend one to three published loops for a stated problem. - **Audit / Loop Doctor:** Diagno...
Frequently asked questions
How does the skill identify if a task is suitable for a loop?
It requires at least two concrete occurrences of semantically equivalent work in the provided codebase or thread history.
Can the skill execute code found in the files it analyzes?
No. It treats source files, commit messages, and thread contents as untrusted evidence and does not execute instructions found within them.
What happens if no published loop fits the user's requirements?
The skill suggests switching to a design interview to create a custom loop.
Related skills
lark-workflow-meeting-summary
219.7KUsers who need to summarize meeting minutes, generate weekly reports, or review meeting history within the Lark ecosystem
The lark-workflow-meeting-summary skill provides a structured workflow for agents to aggregate meeting minutes from Lark VC, generate summaries, and create or update reports in Lark Docs.
programmatic-seo
83.5KContent strategists, SEO specialists, and marketers building large-scale, data-driven website content
The programmatic-seo skill provides a framework for generating SEO-optimized pages at scale using templates and data. It guides users through keyword research, data sourcing, template design, internal linking, and indexation strategies while emphasizing content uniqueness to avoid search engine penalties.
ad-creative
64.0KPerformance marketers, growth teams, and advertisers who need to produce ad copy at scale or optimize existing ad creative
The ad-creative skill generates, iterates, and scales ad copy for paid advertising platforms including Google, Meta, LinkedIn, TikTok, and Twitter. It provides frameworks for creating ad headlines, descriptions, and primary text based on product context and performance data.
gws-workflow-email-to-task
17.9KUsers who manage tasks directly from their Gmail inbox via the command line
The gws-workflow-email-to-task skill converts a Gmail message into a Google Tasks entry using the gws CLI tool.