SKILLEMALL.ai

BF paper-reading-experiment-design

Use when the user has a method idea or Committed Method Design and reads papers to design tasks, datasets, baselines, metrics, ablations, human evaluation, user studies, or a claim-to-evidence experiment plan.

ClawHub Agent Skills author: Zhang Yifan v0.1.0 MIT-0 2 files body ≈ 5 662 tokens Open the sourceclawhub.ai analyzed 35 h ago

Use when the user has a method idea or Committed Method Design and reads papers to design tasks, datasets, baselines, metrics, ablations, human evaluation…

As a process F 54/100 · Will not run — References files that are not bundled: references/workspace-structure.md, references/source-experiment-context-template.md, references/claim-evidence-map-template.md

ProcedureData and analyticsResearchtype and topics are labelled automatically from the skill text
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
65
Run on models
none yet
Process rating
F
54/100
Will not run
References files that are not bundled: references/workspace-structure.md, references/source-experiment-context-template.md, references/claim-evidence-map-template.md
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
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.
  2. 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 body-long SKILL.md body ≈ 5662 tokens (recommended < 5000); move details to references/
  • warning missing-ref reference to a missing file: references/workspace-structure.md
  • warning missing-ref reference to a missing file: references/source-experiment-context-template.md
  • warning missing-ref reference to a missing file: references/claim-evidence-map-template.md
  • warning missing-ref reference to a missing file: references/experiment-design-template.md
  • warning missing-ref reference to a missing file: references/baseline-pressure-matrix-template.md
  • warning missing-ref reference to a missing file: references/claim-metric-map-template.md
  • warning missing-ref reference to a missing file: references/ablation-and-controls-template.md

Process rating: all ten parameters 54/100

Will not run. References files that are not bundled: references/workspace-structure.md, references/source-experiment-context-template.md, references/claim-evidence-map-template.md
  • 0Tools and files. 7 referenced file(s) missing: references/workspace-structure.md, references/source-experiment-context-template.md, references/claim-evidence-map-template.md
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 40Consistency. Frontmatter name (paper-reading-experiment-design) differs from the folder (07-experiment-design)
  • 70When it triggers. States when to use, but not when not to
  • 70Failures and branches. 6 branches
  • 70Execution cost. Instruction body is 5662 tokens
  • 85Steps. 197 steps, 1 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Running it twice. Mutating operations check current state
  • 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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 209: enough signal without eating the budget
  • +4Structure: 20 headings
  • +3Step-by-step instructions: 197 items
  • +3Output format is stated explicitly
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 65.

External checks

ClawHub: clean
This skill is a structured paper-reading workflow that reads local research context and writes experiment-planning notes, with no evidence of hidden execution, credential use, or data exfiltration.
LLM: benign (high) · VirusTotal: · 24 Jun 2026