CB AgentEpstein
Harvest image datasets from art sites (Danbooru, yande.re, e621, Safebooru, Konachan, Gelbooru, X, Pixiv) into a folder a LoRA or fine-tune reads directly. Routes each source over plain HTTP or a real browser to get past bot walls, verifies X and Pixiv candidates by actually looking at them, and keeps artist/page/tag provenance on every row. Use for: building a dataset or reference set from a tag, ship, fandom or artist; collecting images for LoRA training; or scraping a site that 403s a normal client.
Harvest image datasets from art sites (Danbooru, yande.re, e621, Safebooru, Konachan, Gelbooru, X, Pixiv) into a folder a LoRA or fine-tune reads directly.…
As a process B 73/100 · Nearly there — weak spots: result and completion, consistency, execution cost
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-pipe-to-shell-known-hostscripts/bootstrap.py:163Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed; code comment)print(" # or install uv: curl -LsSf https://astral.sh/uv/install.sh | sh")code literalcomment
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 9161 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 479): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 73/100
- 40Result and completion. Does not say what the result is
- 40Consistency. Frontmatter name (AgentEpstein) differs from the folder (agent-epstein)
- 40Execution cost. Instruction body is 9161 tokens: crowds the task out of the window
- 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 76 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 18 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 tags): a typed call is more reliable
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
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- -32 of 13 scripts are never mentioned in SKILL.md
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 507: enough signal without eating the budget
- +4Structure: 29 headings
- +3Step-by-step instructions: 76 items
- +4Has examples (16 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.