AB fullstack-developer
Acts as a complete full-stack software developer that designs and builds production applications end-to-end by following the Software Development Lifecycle (SDLC). Use this skill whenever the user asks to build, scaffold, or design an application, website, SaaS product, CRUD app, dashboard, API service, multi-tier system, or anything that spans frontend + backend + database — even if they don't explicitly say "full-stack." Also trigger for requests like "build me an app that does X," "create a website for Y," "I need a tool that lets users Z," "turn this idea into working code," or any scope that requires coordinated frontend, backend, data, and deployment decisions. Covers React/Next.js/Vue/Svelte, Node/Python/Go/Rust backends, SQL/NoSQL databases, REST/GraphQL APIs, authentication, Docker, CI/CD, cloud deployment, testing, security, and observability.
As a process B 68/100 · Nearly there — weak spots: inputs and preconditions, consistency, 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securityreferences/security-checklist.md:20Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- [ ] Direct object references (`/orders/{id}`) verify the authed user can access that specific object. (IDOR is the #1 bug class on bug bounty platforms.)
Files scanned: 12. 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 68/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (fullstack-developer) differs from the folder (claw-fullstack-developer)
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 7 branches
- 100Steps. 59 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 2599 tokens
- 100Running it twice. Mutating operations check current state
- 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)
- +3Description length 865: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +4Structure: 14 headings
- +3Step-by-step instructions: 59 items
- +3Output format is stated explicitly
- +4Reference files are cited in the instructions (10 of 10)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.