SKILLEMALL.ai

AB identify-rd-directions-rd

Convert a concrete engineering, scientific, manufacturing, or technical project requirement into evidence-backed R&D directions, including requirement analysis, bounded technical issues, research questions, tasks, targets, deliverables, patent and literature evidence, standards and engineering cases, relevant organizations, search logs, and synchronized Markdown and HTML reports. Use when a user asks what R&D directions to pursue, how to decompose a project into research routes, or needs an evidence-led R&D direction report.

ClawHub Agent Skills author: yuanzhian-patsnap v1.0.0 MIT-0 7 files body ≈ 6 147 tokens Open the sourceclawhub.ai analyzed 2 d ago

Convert a concrete engineering, scientific, manufacturing, or technical project requirement into evidence-backed R&D directions, including requirement…

As a process B 68/100 · Nearly there — weak spots: result and completion, failures and branches, running it twice

GeneratorData and analyticsAI and agentsResearchtype and topics are labelled automatically from the skill text
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
76
Run on models
none yet
Process rating
B
68/100
Nearly there
Result and completion w 14
0
Failures and branches w 10
0
Running it twice w 4
30
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: 7. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6147 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "copyright"

Process rating: all ten parameters 68/100

  • 0Result and completion. Does not say what the result is
  • 0Failures and branches. Linear process with no failure handling
  • 30Running it twice. 16 mutating operations with no state check
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 6147 tokens
  • 100Tools and files. No external tools needed
  • 100Steps. 291 steps
  • 100When it triggers. States when to use and when not to
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 29 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)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 530: enough signal without eating the budget
  • +4Structure: 44 headings
  • +3Step-by-step instructions: 291 items
  • +4Has examples (1 code blocks)
  • +3All 1 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.

External checks

ClawHub: clean
The skill is a disclosed R&D report workflow whose file creation and optional evidence searches fit its stated purpose.
LLM: benign (high) · VirusTotal: · 13 Aug 2026