AC skill-compiler
Use when you need to compile any prompt OR multi-source content (PDF/video/URL/image/doc) into a production-grade, reusable AI Skill. Triggers on: 'prompt to skill', 'compile prompt', '把 prompt 变成 skill', '提示词编译', 'PDF转skill', '视频转skill', '网页转skill', 'skill from prompt', 'skill from document'. Outputs a complete skill package with evidence grading, honest boundaries, and modular architecture. Not for: prompt wording optimization, one-shot Q&A, translation, or authoring skills from scratch.
Triggers on: 'prompt to skill', 'compile prompt', '把 prompt 变成 skill', '提示词编译', 'PDF转skill', '视频转skill', '网页转skill', 'skill from prompt', 'skill from document'.
As a process C 51/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
How to improve
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (skill-compiler) differs from the folder (skillcompiler)
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 100Steps. 45 steps
- 100When it triggers. States when to use and when not to
- 100Execution cost. Instruction body is 2156 tokens
- 100Running it twice. No mutating operations
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
- -224 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 494: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (13 of 14)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.