AC pinme-share
Upload any local file or directory to PinMe (pinme.eth.limo) and instantly get a short shareable URL (*.pinit.eth.limo). Supports all file types: HTML pages, PDFs, images, audio, video, documents, or entire directories. PinMe uses public IPFS — uploaded content is publicly accessible; do NOT upload internal / private / credential data. AppKey persists to ~/.local/share/pinme-share/appkey.json (XDG-compliant), overridable via PINME_APPKEY env or --set-appkey CLI. Use when the user says "upload this file", "share this HTML", "host this page", "give me a public link", "deploy to pinme", "upload to IPFS", "get a shareable link", "show my upload history", or hands over any file / directory and wants a URL to share.
Upload any local file or directory to PinMe (pinme.eth.limo) and instantly get a short shareable URL (.pinit.eth.limo). Supports all file types: HTML pages…
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
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
-
medium Concealment
en-hide-from-userscripts/upload_to_pinme.py:615Instruction to hide actions from the user (code comment)# Without this, `path` + `--list` (etc.) would silently run only the first
comment
Files scanned: 4. 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 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 9 mutating operations with no state check
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 25 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1797 tokens
- low 14 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
- -215 emoji in the instructions: noise for the model
- +1No license
- +2Single-language instructions
- +5Description quotes 8 example trigger phrases
- +3Description length 719: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 25 items
- +4Has examples (11 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 90.