SKILLEMALL.ai
GitHub ↗ RU Sign in

BF prompt_design_tuning_best_practice

Collaboratively design, evaluate, iterate on, and recommend a final launch candidate for a target prompt under the principle of “human-gated, agent-executed” workflow.

ClawHub Agent Skills author: yuanjie v1.0.0 MIT-0 2 files body ≈ 3 171 tokens Open the sourceclawhub.ai↗ analyzed 5 d ago

As a process F 63/100 · Will not run — References files that are not bundled: scripts/run_generation.py, scripts/run_judge.py

AnalyzerAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw 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) Goose OpenCode
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
100
Quality 40%
73
Run on models
none yet
Process rating
F
63/100
Will not run
References files that are not bundled: scripts/run_generation.py, scripts/run_judge.py
Tools and files w 18
0
Inputs and preconditions w 11
0
Consistency w 8
40
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
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: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning name-format name should be kebab-case (lowercase letters, digits, hyphens)
  • warning missing-ref reference to a missing file: scripts/run_generation.py
  • warning missing-ref reference to a missing file: scripts/run_judge.py

Process rating: all ten parameters 63/100

Will not run. References files that are not bundled: scripts/run_generation.py, scripts/run_judge.py
  • 0Tools and files. 2 referenced file(s) missing: scripts/run_generation.py, scripts/run_judge.py
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 40Consistency. Frontmatter name (prompt_design_tuning_best_practice) differs from the folder (prompt-design-tuning)
  • 70When it triggers. States when to use, but not when not to
  • 100Steps. 232 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 6 branches, has a failure section
  • 100Execution cost. Instruction body is 3171 tokens
  • 100Running it twice. No mutating operations
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 22 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 167: enough signal without eating the budget
  • +4Structure: 37 headings
  • +3Step-by-step instructions: 232 items
  • +3Output format is stated explicitly
  • +4Has examples (0 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.

External checks

ClawHub: clean
This is an instruction-only prompt-tuning workflow skill with disclosed model-evaluation behavior and human approval gates, but users should control data sharing and spending before execution.
LLM: benign (high) · VirusTotal: · 29 May 2026