new-claude-github-actions-flow

new-claude-github-actions-flow is a Multi-stage workflow orchestration skill for AI agents, published by Fiestaboard in the FiestaBoard repository on GitHub. Skillspace rates new-claude-github-actions-flow F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.

Scaffold or tune a Claude-powered GitHub Actions feedback loop — the docs-audit pattern (scheduled cron → audit → file issues → open PRs → auto-review → capture rejections to learn from). Use this skill whenever the user wants to create a new automated Claude workflow for a domain (tests, perf, i18n, plugins, security, infra, accessibility, schema migrations, etc.), mirror the docs-audit pattern, set up a recurring audit-and-fix loop, add a scheduled Claude job to GitHub Actions, build a "Claude workflow" or "Claude feedback loop", or tune knobs on an existing claude-*.yml workflow (cron schedule, model tier, batch size, queue thresholds, file globs, draft caps, allowed-tools allowlists, time-window gates). Trigger eagerly on phrases like "set up an automation", "Claude cron", "recurring Claude job", "audit loop", "feedback loop", "scan repeatedly for X", "automate fixing X", "fan out Claude on X", "add a workflow that runs every day", or any request to tune cron / effort / model on an…

Grade
F
Quality
45 / 100
Safety
Risky
GitHub stars
31

Unproven: rated by static analysis only, not yet compared head-to-head.

Our two independent classifiers differ on this skill's category, so treat the placement as provisional.

This rating describes the version of the repository we crawled; it may have changed since.

View source on GitHubFiestaboard/FiestaBoard

Our review

Architecture
95 / 100
Maturity
Structured: ships references or scripts
Security scan
High-risk patterns
License
MIT
Adoption
Adopted by 0 other repositories, in 0 collections

What the scanner flagged

  • references sensitive credential env
  • mentions secrets in text

Not checked yet

  • Not judged on the rubric yet (not a contender in its category)
  • No blind task eval yet
  • Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
  • Sibling files (scripts, references) not fetched; security scan covers SKILL.md only

Better-rated skills in Multi-stage workflow orchestration

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.