AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Skill Loop

skill-takumiyoshikawa-skill-loop-skill-loop · by takumiyoshikawa

Use when bootstrapping skill-loop in a repository, creating a GitHub issue loop starter, or writing and updating skill-loop.yml and starter skills.

No reviews yet
0 installs
23 views
0.0% view→install

Install

$ agentstack add skill-takumiyoshikawa-skill-loop-skill-loop

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-takumiyoshikawa-skill-loop-skill-loop)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Skill Loop? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

skill-loop

Use this skill for two cases:

  • bootstrap skill-loop into a repository with a GitHub issue workflow
  • write, simplify, or migrate skill-loop.yml

Modes

  • GitHub bootstrap: read references/github-init.md
  • YAML authoring or migration: read references/yaml-authoring.md, then follow the selected pattern reference only

Working style

  • Keep the generated setup minimal.
  • Prefer tracker.repo plus a small skills: graph.
  • Prefer an issue-check entrypoint that uses gh to choose the next ready issue and complete the minimum setup before planning.
  • Treat YAML authoring as pattern selection first, then concrete authoring.
  • Reuse templates from assets/ instead of writing large starter files from scratch.
  • Default to .claude/skills/ for generated starter skills unless the repository already uses another skill directory.

Expected outputs

  • create or update skill-loop.yml
  • select the right workflow pattern before drafting YAML
  • create starter skills only when the selected pattern actually needs them
  • explain the execution flow in terms of the chosen pattern

Validate

  • YAML: validate one or more skill-loop YAML files against schema.json
  • schema:https://raw.githubusercontent.com/takumiyoshikawa/skill-loop/refs/heads/main/schema.json

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.