agentsclimarketplace

Skillward

Skill coroboros/skillward/skills/skillward

Take an agent skill apart before installing it — the complete deterministic scanner ensemble, fused into one offline verdict.

Install
npx -y skills add coroboros/skillward --skill skillward

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Vet an untrusted agent skill, plugin, or MCP server before it is installed or trusted. Runs the skillward CLI — the complete deterministic scanner ensemble, offline, fused into one verdict — then triages the report into a plain-language risk read with an install / don't-install / remediate call. Use this whenever someone is about to add or run third-party agent code (npx skills add, a marketplace or plugin, an https Git URL, a directory of skills, or a local folder), even when they only ask "is this safe?" rather than naming a scan. Trigger phrases include scan this skill, vet before install, audit this agent skill, is this skill or MCP server safe, check this repo before I trust it.

SKILL.md

2.7 KB, 516 tokens by cl100k_base, as published. Nobody here has run it

skillward

Vets an untrusted agent skill — one folder, a directory of skills, or a remote https Git URL — by running the complete deterministic scanner ensemble offline and fusing the findings into one verdict. The CLI does the detection; this skill adds the one intelligent step: reading the report and saying what it means.

Install

The CLI is the engine. Install it once:

cargo binstall skillward     # prebuilt binary
brew install coroboros/tap/skillward
npx @coroboros/skillward     # Node toolchains

Then pull the scanner bundle (one-time, needs Docker):

skillward install

If skillward is not on PATH, stop and tell the user to install it with one of the commands above — do not improvise a scan. A hand-rolled check misses what the ensemble catches, so it would report a false all-clear.

Use

Run skillward --help for the full surface. The default scan, with a JSON report for triage:

skillward <target> --format json -o report.json

<target> is a skill folder, a directory of skills, or an https:// Git repo URL. Exit code 20 means findings reached the --fail-on threshold (default high); 0 means clean or below it.

Analyze

After the scan, read report.json and produce a triage — not a re-print of the findings:

  1. Lead with the verdict. PASS or FAIL, the worst severity, and whether findings are corroborated (multiple tools agreeing is high-confidence).
  2. Explain the real risk of the top findings in plain language — what an attacker gains, citing the specific file and rule (e.g. "exfiltrates AWS credentials on every invocation — setup.sh:7, flagged by skillspector and semgrep").
  3. Note any tool_errors — a scanner that did not run means the picture is incomplete; say so rather than implying all-clear.
  4. Make the call: install, don't-install, or remediate-then-reinstall. For remediate, name the exact change.

Keep it short and decision-oriented. The findings are in the report; the judgment is the work.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most mcp tooling skills give in 516 tokens

Counted across 638 of the 750 authors here whose files we hold, read 2026-08-07

  • Create ten complex or independent read-only evaluation questionsin 69 of 638, across 15 files
  • Test servers using MCP Inspectorin 61 of 638, across 19 files
  • Provide actionable error messages with specific next stepsin 54 of 638, across 12 files
  • Prioritize comprehensive API coverage over specific workflows or workflow toolsin 54 of 638, across 12 files
  • Use TypeScript and Streamable HTTP for remote servers or clientsin 54 of 638, across 8 files
  • Define structured output schemas where possiblein 50 of 638, across 8 files
  • Use Zod or Pydantic for input schemasin 47 of 638, across 5 files
  • Fetch MCP specification pages with markdown suffixin 46 of 638, across 4 files
  • Load framework documentation using WebFetchin 45 of 638, across 3 files
  • Verify each evaluation answer independentlyin 45 of 638, across 3 files
  • Implement API client with authentication and paginationin 45 of 638, across 3 files
  • Define input schemas with validationin 27 of 638, across 9 files

Said here and by no other author read

  • install skillward before scanning
  • stop if skillward is missing
  • tell the user to install skillward
  • do not improvise a scan
  • run skillward with JSON output
  • lead the triage with the verdict

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.