Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

MCP Review · fallow-rs | DecimalAI

agent toolingby fallow-rs

MCP Review

fallow-rs/mcp-review

Source fallow-rs/fallow ↗License MIT

Review fallow's MCP server for tool contract clarity, output stability, and agent usability.

SkillScore70Maintained

Automatic

AI Engineer pack

Last verified 9/28/2026

What it changes

Passed 14 of 20 test cases with the skill, and 3 of 20 without it.

Without skill17%

With skill70%

Checks it passed that the model alone missed

Concludes the review with BLOCK.
Concludes the review with CONCERN.
Ends the review with one of the status tokens APPROVE, CONCERN, or BLOCK.

15 fixed1 passed either way4 still failing3 broke

Pass-rate lift: +52 pp
Tokens: +18%
Agent turns: 0%
Response time: -1%

Model gemini-3.6-flashMeasured 9/28/2026v216 of 23 cases passed with skill · 20 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/fallow-rs-mcp-review/SKILL.md https://app.decimal.ai/s/fallow-rs-mcp-review/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add fallow-rs-mcp-review, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/fallow-rs-mcp-review/ and pins it in .decimal/skills.lock

decimalai skills add fallow-rs-mcp-review

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/fallow-rs-mcp-review/SKILL.md https://app.decimal.ai/s/fallow-rs-mcp-review/SKILL.md

Raw file: /s/fallow-rs-mcp-review/SKILL.md ↗ · machine-readable summary at /s/fallow-rs-mcp-review.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 15

Prompt

Review this MCP tool: all schemas, error objects, and structured JSON outputs are robust and tested, but two optional field descriptions in the tool input schema have minor typos. End your review with a formal status.

What was checked, without and with the skill
Checked	Without skill	With skill
Identifies minor schema docstring typos as non-fatal issues.	Passed	Passed
Concludes the review with CONCERN.	Missed	Passed

case-10 · gemini-3.6-flash · 9/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md15 linessingle file

MCP Review

Read:

.agents/agents/mcp-reviewer.md
.agents/rules/mcp-server.md

Focus on:

tool contract clarity
stable machine-readable output
error handling
agent usability and discoverability

End with APPROVE, CONCERN, or BLOCK.

Track record

Benchmark

14 / 20

test cases passed, vs 3 / 20 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/31/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

fallow-rs / fallow

.agents/skills/mcp-review/SKILL.md

View on GitHub ↗

License MITImported 8/31/2026Version v2

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

MCP Review

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills