AF skill-creator-max
Build a NEW agent skill from scratch, end-to-end — a thin conductor dispatches fresh subagents through five gated roles (compose spec -> design structure -> red-green build -> compress -> independent attack). EXPENSIVE (large token cost): trigger ONLY on an explicit user request to author/build/create an agent skill — "build me a skill", "create a new skill", "package this repeated workflow so it triggers automatically", "$skill-creator-max". Do-NOT fire for: summarizing or writing daily/session memory or journaling (incl. Chinese "总结/记录今天的记忆"), or any generic "create/make/summarize X" that is not authoring an agent skill.
Build a NEW agent skill from scratch, end-to-end — a thin conductor dispatches fresh subagents through five gated roles (compose spec -> design structure ->…
As a process F 58/100 · Will not run — References files that are not bundled: scripts/validate_spec, scripts/validate_structure, scripts/validate_report
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: 23. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/validate_spec - warning
missing-refreference to a missing file: scripts/validate_structure - warning
missing-refreference to a missing file: scripts/validate_report - warning
missing-refreference to a missing file: scripts/validate_compression - warning
missing-refreference to a missing file: scripts/validate_decision
Process rating: all ten parameters 58/100
- 0Tools and files. 5 referenced file(s) missing: scripts/validate_spec, scripts/validate_structure, scripts/validate_report
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 4 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70When it triggers. States when to use, but not when not to
- 100Steps. 6 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2319 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +3Description length 630: enough signal without eating the budget
- +4Structure: 10 headings
- +3Step-by-step instructions: 6 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (1 of 1)
- +3All 7 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.