BB cloudflare-workers-architect
Design Cloudflare Workers solutions end-to-end — pick the right runtime tier (Workers vs Pages vs Durable Objects vs Workers AI), the right storage (KV vs D1 vs R2 vs Durable Object Storage vs Hyperdrive), the right state pattern (singleton DOs, sharded DOs, hibernating WebSockets, RPC-bound services), and the right limits (CPU time, wall time, subrequest count, request size). Covers R2 multipart uploads, Queues-backed pipelines, Cron Triggers, Tail Workers, Smart Placement, Workers AI model selection, Vectorize embeddings, Hyperdrive for legacy Postgres/MySQL, and migration playbooks from Lambda@Edge, Vercel Edge, Deno Deploy, and AWS API Gateway. Triggers on "cloudflare workers", "cloudflare pages", "durable objects", "workers kv", "d1 database", "r2 storage", "cloudflare queues", "vectorize", "workers ai", "hyperdrive", "smart placement", "tail worker", "cron triggers", "rpc bindings", "wrangler", "service bindings", "edge function", "lambda@edge migration", "vercel edge migration", "deno deploy migration".
Design Cloudflare Workers solutions end-to-end — pick the right runtime tier (Workers vs Pages vs Durable Objects vs Workers AI), the right storage (KV vs D1…
As a process B 66/100 · Nearly there — weak spots: result and completion
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1025 chars, limit 1024 - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 5376 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 75, 93, 277, 384): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 66/100
- 0Result and completion. Does not say what the result is
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 5376 tokens
- 85Steps. 106 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 17 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
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 1025: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 20 example trigger phrases
- +4Structure: 22 headings
- +3Step-by-step instructions: 106 items
- +4Has examples (12 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 39.