All skills
simota avatar

/pipe

@91d7239
by shingo imotasimota/agent-skills85 stars
15

Designing GitHub Actions workflows in depth: trigger strategy, security hardening, performance optimization, PR automation, and Reusable Workflow design.

Use this Skill: https://skilld.dev/gh/simota/agent-skills/pipe

This session only. Nothing lands on disk.

referenceautorun-schema.md

≈153 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Pipe — AUTORUN _STEP_COMPLETE Schema

When Pipe receives _AGENT_CONTEXT, parse task_type, description, and Constraints, execute the standard workflow, and return _STEP_COMPLETE.

_STEP_COMPLETE

_STEP_COMPLETE:
  Agent: Pipe
  Status: SUCCESS | PARTIAL | BLOCKED | FAILED
  Output:
    deliverable: [primary artifact]
    parameters:
      task_type: "[task type]"
      scope: "[scope]"
  Validations:
    completeness: "[complete | partial | blocked]"
    quality_check: "[passed | flagged | skipped]"
  Next: [recommended next agent or DONE]
  Reason: [Why this next step]

Source: SKILL.md on GitHub

2 warnings5mo5 checks · Risk SAFE
  • Gen Agent Trust Hub5mo

    The skill 'Pipe' is a specialized instructional framework for GitHub Actions (GHA) workflow architecture. It focuses on security hardening, performance optimization, and automation best practices. It explicitly mandates high-security standards such as SHA pinning for third-party actions, OIDC for cloud authentication, and the principle of least privilege for permissions.

  • Socket5mo

    No alerts

  • Snyk5mo

    Risk: LOW · No issues

  • Runlayer6mo

    8/11 files flagged

  • ZeroLeaks5mo

    1 finding · Score: 69/100

Signed by skilld at 91d7239. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 2 months ago

README badge

README badge for simota/agent-skills/pipe