AF Skywork Document
Skywork Document (skywork) - Use for ANY task producing a document output. Generates professional documents in docx, pdf, markdown, and html. Capabilities: (1) Create new documents on any topic - reports, proposals, blogs, papers, fiction, memos, letters, contracts, plans, resumes, research summaries, study notes; (2) Base documents on user's uploaded files - rewrite resumes, summarize papers, expand outlines, translate; (3) Auto web search for up-to-date content. Trigger when users ask for a 'document'/'docx' OR when intent implies document output. If output is longer than a short answer and benefits from structure/formatting, default to this skill. Do NOT use for short plain-text answers, code files, small notes, ad-hoc Q&A, or casual chat. Trigger keywords include: 'write a report', 'draft a proposal', '写报告', '帮我写一篇', 'レポートを作って', '보고서 써줘', 'rédiger un document', 'redactar un informe', 'Bericht erstellen', 'написать документ', 'كتابة تقرير', 'scrivere un documento'.
As a process F 66/100 · Will not run — References files that are not bundled: url
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: 7. 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
missing-refreference to a missing file: url
Process rating: all ten parameters 66/100
- 0Tools and files. 1 referenced file(s) missing: url
- 30Running it twice. 9 mutating operations with no state check
- 40Consistency. Frontmatter name (Skywork Document) differs from the folder (skywork-document)
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 48 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 5 branches, has a failure section
- 100Execution cost. Instruction body is 2441 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Description length 982: 120–800 characters recommended
- -4Absolute local paths (C:\Users, /home/…): not portable
- -32 of 4 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 16 headings
- +3Step-by-step instructions: 48 items
- +3Output format is stated explicitly
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.