AF crucible
Use when the user wants a full product delivery pipeline (PM→UX→Dev→Test), or when building something from scratch with quality gates, or when requesting "团队化开发", "全流程", "带审查的开发", "自审开发", "迭代交付", "crucible". Supports configurable stages with built-in implement→review→fix self-review loops.
Use when the user wants a full product delivery pipeline (PM→UX→Dev→Test), or when building something from scratch with quality gates, or when requesting…
As a process F 44/100 · Will not run — References files that are not bundled: references/methodology.md, references/verification.md, references/security-checklist.md
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
missing-refreference to a missing file: references/methodology.md - warning
missing-refreference to a missing file: references/verification.md - warning
missing-refreference to a missing file: references/security-checklist.md - warning
missing-refreference to a missing file: references/tooling.md - warning
missing-refreference to a missing file: companion/pm-disciplines.md - warning
missing-refreference to a missing file: companion/dev-disciplines.md - warning
missing-refreference to a missing file: companion/test-disciplines.md - warning
missing-refreference to a missing file: companion/gate-disciplines.md - warning
missing-refreference to a missing file: roles.md - warning
missing-refreference to a missing file: gates.md - warning
missing-refreference to a missing file: references/lessons.md
Process rating: all ten parameters 44/100
- 0Tools and files. 11 referenced file(s) missing: references/methodology.md, references/verification.md, references/security-checklist.md
- 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
- 30Running it twice. 2 mutating operations with no state check
- 40Result and completion. Does not say what the result is
- 70When it triggers. States when to use, but not when not to
- 100Steps. 52 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3628 tokens
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 2 example trigger phrases
- +3Description length 290: enough signal without eating the budget
- +4Structure: 56 headings
- +3Step-by-step instructions: 52 items
- +4Has examples (21 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 78.