SKILLEMALL.ai
GitHub ↗ RU Sign in

AC pipe

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

simota/agent-skills Agent Skills author: simota 16 files body ≈ 6 038 tokens Open the sourcegithub.com↗ analyzed 2 h ago

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

As a process C 63/100 · Has gaps — weak spots: inputs and preconditions, running it twice

ProcedureGitHubAzureSoftware developmentInfrastructureData and analyticstype and topics are labelled automatically from the skill text
Runs in: Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) OpenClaw Goose OpenCode
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
96
Quality 40%
81
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Running it twice w 4
30
When it triggers w 12
50
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 4

✓ No critical or high findings

Medium and low: 4
  • low Risky intent intent-offensive-security reference/security-anti-patterns.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Purpose: Catch workflow-level security failures early: supply-chain compromise, privilege escalation, secret leakage, injection, and runner hardening gaps.
  • low Risky intent intent-offensive-security reference/security-hardening.md:3
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    Purpose: Secure GitHub Actions workflows against supply-chain compromise, privilege escalation, script injection, and secret exfiltration.
  • low Risky intent intent-offensive-security reference/security-hardening.md:23
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    | Privilege escalation | default or excessive workflow permissions | `permissions: {}` and job-level grants |
  • low Risky intent intent-offensive-security SKILL.md:95
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - Validate with `actionlint` before committing workflow changes. Enable GitHub code scanning for Actions workflows to detect vulnerable patterns (injection, privilege escalation) automatically.
    detector

Files scanned: 16. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6038 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 63/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 30Running it twice. 27 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 70Execution cost. Instruction body is 6038 tokens
  • 85Steps. 96 steps, 1 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +1No license
  • +2Single-language instructions
  • +3Description length 153: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 96 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (14 of 14)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.