BF fullstack-dev
Full-stack backend architecture and frontend-backend integration guide. TRIGGER when: building a full-stack app, creating REST API with frontend, scaffolding backend service, building todo app, building CRUD app, building real-time app, building chat app, Express + React, Next.js API, Node.js backend, Python backend, Go backend, designing service layers, implementing error handling, managing config/auth, setting up API clients, implementing auth flows, handling file uploads, adding real-time features (SSE/WebSocket), hardening for production. DO NOT TRIGGER when: pure frontend UI work, pure CSS/styling, database schema only.
As a process F 49/100 · Will not run — References files that are not bundled: references/api-design.md, references/db-schema.md, references/auth-flow.md
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 8342 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: references/api-design.md - warning
missing-refreference to a missing file: references/db-schema.md - warning
missing-refreference to a missing file: references/auth-flow.md - warning
missing-refreference to a missing file: references/environment-management.md - warning
missing-refreference to a missing file: references/testing-strategy.md - warning
missing-refreference to a missing file: references/release-checklist.md - warning
missing-refreference to a missing file: references/technology-selection.md - warning
missing-refreference to a missing file: references/django-best-practices.md
Process rating: all ten parameters 49/100
- 0Tools and files. 8 referenced file(s) missing: references/api-design.md, references/db-schema.md, references/auth-flow.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (fullstack-dev) differs from the folder (minimax-fullstack-dev)
- 40Execution cost. Instruction body is 8342 tokens: crowds the task out of the window
- 100Steps. 45 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 7 branches, has a failure section
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 22 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)
- +3Output format is not stated: the model decides each time
- -5TODO / placeholder text left in the skill
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +3Description length 632: enough signal without eating the budget
- +4Structure: 74 headings
- +3Step-by-step instructions: 45 items
- +4Has examples (49 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.