SKILLEMALL.ai
GitHub ↗ RU Sign in

CC prpm-json-best-practices

Best practices for structuring prpm.json package manifests with required fields, tags, organization, multi-package management, enhanced file format, eager/lazy activation, and conversion hints

AgentWorkforce/relay Agent Skills author: AgentWorkforce 6 files body ≈ 8 751 tokens Open the sourcegithub.com↗ analyzed 8 h ago

Best practices for structuring prpm.json package manifests with required fields, tags, organization, multi-package management, enhanced file format…

As a process C 54/100 · Has gaps — weak spots: inputs and preconditions, consistency, execution cost

ProcedureSoftware developmentAI and agentstype 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
C
88/100
safety, quality, tests
Safety 60%
100
Quality 40%
71
Run on models
none yet
Process rating
C
54/100
Has gaps
Progress reporting w 2
0
Inputs and preconditions w 11
30
Consistency w 8
40
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 · 0

✓ No critical or high findings

Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 8751 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 54/100

  • 0Progress reporting. Says nothing while it works
  • 30Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (prpm-json-best-practices) differs from the folder (prpm-json-best-practices-skill)
  • 40Execution cost. Instruction body is 8751 tokens: crowds the task out of the window
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
  • 60Steps. 154 steps, 9 vague phrases
  • 60Result and completion. Output format stated, no completion criterion
  • 70Failures and branches. 4 branches
  • 100Running it twice. Mutating operations check current state
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 19 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)
  • -4Absolute local paths (C:\Users, /home/…): not portable
  • -216 emoji in the instructions: noise for the model
  • +1No license
  • +2Single-language instructions
  • +3Description length 192: enough signal without eating the budget
  • +4Structure: 81 headings
  • +3Step-by-step instructions: 154 items
  • +3Output format is stated explicitly
  • +4Has examples (50 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.