AC hybrids3
Self-hosted lightweight object storage speaking three interfaces at once — the S3 API (boto3 / AWS-SDK compatible, AWS Sig V4), a plain HTTP API (curl-friendly, Bearer auth), and MCP (Streamable HTTP tools for agents). Buckets/objects with SQLite metadata and flat-file storage on disk; buckets are config-defined (no create/delete API), each with a public/private flag, a private key + public key pair, optional TTL expiry, and a max upload size. Auth is per-bucket keys plus a cross-bucket master key; presigned GET/PUT URLs for handing out single-object access. Use when the user wants to put/get/list/delete files in a self-hosted S3-compatible store, generate presigned upload/download links, drive their own boto3-compatible object storage, or connect an agent to object storage over MCP.
Self-hosted lightweight object storage speaking three interfaces at once — the S3 API (boto3 / AWS-SDK compatible, AWS Sig V4), a plain HTTP API…
As a process C 64/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5156 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 64/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70Execution cost. Instruction body is 5156 tokens
- 85Steps. 18 steps, 2 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (4 tags): a typed call is more reliable
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
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +3Description length 794: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 18 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.