AB ai-workflow-os
Route complex AI-assisted work across project lifecycle guidance, formal project governance, coding execution, session memory, web-research intake, and cross-source synthesis without creating competing state. Use when a request spans two or more of these surfaces, the user is unsure which workflow skill applies, or a combined research-to-project-to-handoff flow needs clear authority and ordering. Typical triggers include 我这个需求该用哪个 skill, which skill should handle this, 研究和开发一起做, research then implement then hand off, 这个项目该怎么管, orchestrate this across skills, 从头到尾帮我跑一遍, and end-to-end AI workflow. Delegates to specialized skills when installed and uses bundled modules only as reduced-fidelity fallbacks. Applies a subtraction-first guard so a combined request does not silently become new scope.
Route complex AI-assisted work across project lifecycle guidance, formal project governance, coding execution, session memory, web-research intake, and…
As a process B 77/100 · Nearly there — weak spots: when it triggers, running it twice, progress reporting
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: 25. 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 77/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 1 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Tools and files. No external tools needed
- 100Steps. 66 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2327 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 13 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)
- +3Description length 803: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 66 items
- +3Output format is stated explicitly
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.