BC paper2blog
Use when transforming an academic paper, arXiv/OpenReview PDF, conference paper, technical report, poster, slide deck, repository README, or related research materials into a bilingual editorial package for an editing team. Produces two articles by default — a Chinese WeChat public-account version (`blog_zh.docx`) and an English research-blog version (`blog_en.docx`). Use for drafting, revising, or packaging article copy, figure placement, captions, image prompts, and the final `.docx` deliverables.
Use when transforming an academic paper, arXiv/OpenReview PDF, conference paper, technical report, poster, slide deck, repository README, or related research…
As a process C 58/100 · Has gaps — References files that are not bundled: assets/figures/, assets/meta/reports/, assets/meta/sections.json
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/figures/ - warning
missing-refreference to a missing file: assets/meta/reports/ - warning
missing-refreference to a missing file: assets/meta/sections.json - warning
missing-refreference to a missing file: assets/meta/narration.json - warning
missing-refreference to a missing file: assets/meta/figures.json - warning
missing-refreference to a missing file: assets/meta/captions.json - warning
missing-refreference to a missing file: assets/meta/text.txt - warning
missing-refreference to a missing file: assets/meta/metadata.json - note
edit-residuethe text marks something as outdated (lines 62, 109): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 58/100
- 0Tools and files. 8 referenced file(s) missing: assets/figures/, assets/meta/reports/, assets/meta/sections.json
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 70Execution cost. Instruction body is 4795 tokens
- 100Steps. 81 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 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
- +4Description does not say when NOT to use the skill (false activations)
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 504: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 81 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.