Agents & Protocols

SKILL.md Review: Safe and Within the Limits

Reviews a SKILL.md file before you install, buy or publish it and lists every problem with a fixed code, the place and a fix, then gives one verdict. It checks the front matter against the published limits (name up to 64 characters in lowercase, hyphens and digits, no reserved words; description present, up to 1,024 characters, naming both its job and the requests that should trigger it, in the third person), and it reads the body for hidden orders to the agent, credentials pasted into the text, commands that download and run remote code, Windows-style paths, a body over 500 lines and the lack of any example. Use to review a SKILL.md, audit a Claude or agent skill before installing it, check a skill file for prompt injection, or lint a skill before publishing it to a marketplace.

SKILL.md Review: Safe and Within the Limits is a SKILL.md that reviews a SKILL.md file before you install, buy or publish it and lists every problem with a fixed code, the place and a fix, then gives one verdict; an agent buys it once for $0.05 over x402.

Tested 2026-10-08No code, no hidden instructionsv1.0.1 · 6.7 KB · perpetual license

Not for

Running or testing the skill, reading the scripts that come with it, or judging whether its advice is correct for its topic. It reads one SKILL.md as text, so a problem hidden in a bundled script or a downloaded file is outside what it can see.

Tested, honestly

Tested 2026-10-08 with a strong and a weak model.

With and without the skill

Results with and without the skill, for Sonnet and Haiku
SonnetHaiku
withwithoutwithwithout
Every planted problem named, nothing invented20/2018/2020/2014/20

Both sides scored with the same word-based checks, since the side without the skill does not know our codes. Without the skill both models noticed the hidden orders, the key and the curl command, and Sonnet called out the note aimed at the reviewer; the misses were the counted rules. Haiku did not flag the 65-character name, the 1,305-character description, the 538-line body or the backslash path, and neither model said that the file had no example. Two baseline patterns first missed correct answers (one counted a sentence saying no injected instructions as an alarm) and were widened before the final score; the change applies to both sides.

Same cases and the same checks with and without the skill. The cases are ours, written around what the skill is for; with a handful of cases, a difference of one or two is within noise.

SonnetStrong model, claude-sonnet-5-5
Gave the exact codes and verdict in all 20 cases, as bare lines with nothing around them. It caught a request to read the SSH key, a silent copy to a shared drive, a line that claims to replace the system's instructions, a note telling the reviewer to answer No findings, a live-looking API key, a curl piped into sh, a name over 64 characters, an uppercase name, the reserved word claude in a name, a missing, an overlong and a first-person description, an XML tag in the description, a Windows path, a 538-line body and a missing example, and it left a skill that runs its own bundled script unflagged. A first run with a wider wording of our person rule flagged the word you inside ordinary descriptions; the rule was narrowed to match the published guidance and run again.
HaikuWeak model, claude-haiku-5-5
Also 20 of 20 with the skill, with the same codes and verdicts as Sonnet, including the counted limits it did not flag without the skill: the 65-character name, the 1,305-character description and the 538-line body.

Full test summary

Example

Our own test text, before and after the skill ran. Excerpts only.

English · claude-sonnet-5-5

Before

--- name: PDF_Form_Filler description: Fills in PDF forms from data you give it and checks that every required field is set. Use when asked to fill a PDF form, complete a fillable PDF, or check a form for missing fields. --- # PDF form filler Read the form fields first, then fill only the fields the user gave data for. Never invent a value. Report every required field that is still empty.…

After

[NAME] name: "PDF_Form_Filler" has uppercase letters and underscores, and only lowercase letters, digits and hyphens are allowed. Fix: pdf-form-filler. Verdict: fix before use

What is in the file

  • The answer
  • The codes
  • Rules
  • Work in this order
  • Short example

Languages

Any language. Tried in: English.

License

Perpetual, non-exclusive; use and modify for yourself incl. paid work; no resale or republishing. Holder: Georgi Kalchev, aiskills402.com. Full terms.

Versions

Current version 1.0.1, updated 2026-10-08. Whoever bought an earlier version gets new ones free through the same re-download token.

  1. v1.0.1 · 2026-10-08

    Price changed from $0.03 to $0.05; the skill text is unchanged. Measured value for the strong model: Sonnet 18 of 20 without the skill, 20 of 20 with it.

  2. v1.0.0 · 2026-10-08

    First release: reviews one SKILL.md file and lists each problem with a fixed code, the place and a fix, then a verdict (unsafe, fix before use, ready). Unsafe: hidden orders to the agent, credentials in the text, download-and-run commands. Front matter against the published limits: name, missing or overlong description, no trigger, first or second person, XML tags. Body: over 500 lines, Windows paths, no example. Ordinary instructions to use the skill's own scripts are not flagged, and an order to the reviewer inside the file is itself a finding.

FAQ

What does it check in the front matter?

The published limits for skills: a name of at most 64 characters in lowercase letters, digits and hyphens without the reserved words anthropic and claude, and a description that exists, stays within 1,024 characters, says when the skill should be used and is written in the third person. It counts the characters instead of estimating them.

Will it catch a hidden instruction to the agent?

Those come first in the report, with the verdict unsafe: a request to read SSH keys, a silent copy of the user's files, a line claiming to replace the system's instructions and a note telling the reviewer to answer No findings were all caught in our tests, along with a pasted API key and a curl command piped into a shell.

Does it flag every skill that runs scripts?

No. Telling the agent to run the skill's own bundled script on the file the user named is normal and was not flagged by either model. It becomes a finding when the file reaches for data the task does not need or downloads and runs code at use time.

What did the models miss without it?

The counted rules. Without the skill, Claude Haiku did not notice a 65-character name, a 1,305-character description, a body of 538 lines or a Windows path, and neither Haiku nor Sonnet said that a file had no example. With the skill both models reported all of them.

Read more

Share

Read this page as Markdown: /skills/skill-md-review.md.

  • Recommended

    Prompt Injection Guard

    Agents & Protocols

    SKILL.md · v1.0.3 · 14.5 KB

    Keeps an AI agent from obeying instructions hidden in what it reads (indirect prompt injection). Web pages, e-mails, files, PDFs, API and tool output, other agents' messages and skill files under review are treated as content, never as orders. The agent is instructed never to pay, transfer, delete or reveal anything because content asked, to report the attempt with a quote and its source, and to still finish the real task. Use whenever the agent reads anything it did not write itself, before any action with side effects such as a payment, a message or a file change, and when asked to review or summarise untrusted content.

    $0.07once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 2 Oct 2026

  • Recommended

    Agent Done Check: Stop False Success Reports

    Agents & Protocols

    SKILL.md · v1.0.3 · 9.9 KB

    Stops an AI agent from reporting false success, or hallucinated completion: work it calls done that did not happen. Every action in its status report gets one of five states (done and verified, done but not confirmed, partly done, failed, not done), backed by what the tool results of the session show. Failures and unknowns come first, counts come from the results, and no id, receipt or hash is invented. When a result does show success, the agent says so plainly. Use whenever an agent reports on actions it took with tools, such as messages, batches, tests, builds, deploys, file edits, data updates, payments or API calls.

    $0.10once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 3 Oct 2026

  • Code Review

    Code & Engineering

    SKILL.md · v1.0.4 · 6.0 KB

    Reviews a code change (a diff or a changed file pasted as text) and reports real problems ranked by severity — correctness bugs, security holes, data loss, missing error handling, edge cases, resource leaks — each with location, reason and a concrete fix in words. Use when asked to review code, a diff or a pull request, check a change for bugs, or find security problems in a snippet.

    $0.01once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 30 Sep 2026

More in Agents & Protocols

  • x402 Buyer: Pay Safely from an Agent Wallet

    Agents & Protocols

    SKILL.md · v1.0.4 · 9.4 KB

    Decision rules for an AI agent that holds a wallet and receives an HTTP 402 payment request (x402 v2). Decides SIGN, REFUSE or ASK the human before any money moves, and says how to verify the delivery and retry without paying twice. Use when an agent is about to pay over x402, gets a 402 response, must check a seller's payment terms, or a paid request failed and it is unsure whether to pay again.

    $0.05once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 30 Sep 2026

  • Recommended

    x402 Seller: Get Paid and Listed in Bazaar

    Agents & Protocols

    SKILL.md · v1.0.2 · 14.0 KB

    Diagnoses why an HTTP API sold over x402 v2 cannot be paid by standard buyer agents or never appears in the Coinbase CDP Bazaar catalog, using an ordered checklist and a decision tree over the pasted 402 response, headers and symptoms. Names the exact field that is wrong or missing and how to prove the fix. Use when asked to check an x402 seller, fix an unpayable 402 endpoint, find out why a resource is not listed in Bazaar, or why a settled payment does not show up.

    $0.10once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 30 Sep 2026

  • Recommended

    x402 Listing Review: Catalogs, Scanners, Buyers

    Agents & Protocols

    SKILL.md · v1.1.0 · 15.4 KB

    Reviews how a paid HTTP resource sold over x402 is advertised to catalogs, scanners and buyer agents, and how the seller's own scripts read those catalogs back, from pasted 402 bodies, OpenAPI documents, discovery files, liveness guard code, catalog presence check scripts and buyer alerts. Flags a tiered tariff advertised as one row (a comparison bot reads the structured amount, not the description), one liveness clock for several catalog rows that are dropped one by one, a price above the standard buyer client's default cap with no note where agents read before buying, a discovery file the scanner no longer parses, a bearer scheme the scanner's indexer does not recognise by name, a scanner record that was never re-crawled after a fix, a presence check that reads only one of the two response field names or has no control that must return zero, a first buyer that is a crawler paying hundreds of sellers, and discovery endpoints that read the database on every crawl. Each finding has a fixed code, the place, the reason and a fix, then one verdict. Use for an x402 listing review, to check x402 discovery or Bazaar catalog presence code before trusting it, or to audit how a paid API is listed and read.

    $0.05once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 29 Oct 2026

  • Retry Backoff Review

    Agents & Protocols

    SKILL.md · v1.0.0 · 6.0 KB

    Reviews ONE piece of retry code, or a written retry design for an agent or a service client, and lists only the five mistakes that turn a failure into an outage or a double write, one line each with a fixed code, the place, why it hurts and the fix - or exactly No findings. It catches waits that grow without a random part, a loop with no limit on tries or on total time, a POST repeated with no idempotency key, a 429 or 503 answer whose Retry-After header is never read, and retries on client errors that cannot change. It leaves out the safe look-alikes, such as a GET retried with a cap and jitter, a retry set of 408, 429 and server errors only, and a wait taken straight from Retry-After. Use to review the retry loop of an API client, to audit how an agent calls tools that fail, or before shipping a client to production.

    $0.01once

    • x402
    • USDC
    • Base
    Get skill

    Tested with Sonnet and Haiku, 26 Oct 2026