CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

mpp-agent

Pay HTTP 402 APIs via Machine Payments Protocol (MPP).

60

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./optional-skills/payments/mpp-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a lean, highly actionable guide with a well-sequenced procedure, pre-payment probing, and verification steps, plus a genuinely useful Pitfalls section covering method mismatches and zero-amount challenges. Its only weaknesses are slight redundancy around the client-selection default rule and the absence of an explicit failure-recovery loop for payments.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (it never explains what HTTP 402 or MPP is) and uses a tight decision table, but the link-cli default is stated three times (When to Use, the table row, and the "Default:" paragraph), giving minor trim potential. This matches the 'efficient with minor instances that could be trimmed' anchor rather than the every-token-earns-its-place level.

4 / 5

Actionability

Commands are copy-paste ready throughout — `npm install -g mppx`, `mppx account create`, `curl -i <url>`, `mppx <url> --method POST --data '<json>'`, `tempo wallet pay <url>` — and common cases (GET and POST with body) plus verification (`mppx --version && mppx account list`, exit code 0) are covered. Placeholders like <url> are legitimate parameters, matching the fully-executable anchor.

5 / 5

Workflow Clarity

The mppx procedure is a clear numbered sequence (install → probe the 402 challenge → pay → verify the receipt) with a pre-payment validation checkpoint and terminal verification, and Pitfalls covers error modes. It falls short of 5 because there is no explicit recovery loop for a failed or underfunded payment attempt.

4 / 5

Progressive Disclosure

No bundle files exist, so structure is judged on the body itself: sections are well organized (When to Use, Choosing a client, Prerequisites, Procedures, Pitfalls, Verification), nothing bulk is inlined that belongs in a separate file, and detail for other clients is deferred one level deep via clearly signaled external references (e.g. the Tempo skill URL). This matches the clear-overview anchor.

5 / 5

Total

18

/

20

Passed

Description

57%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is crisp, niche, and written in proper imperative voice with a clear "what", but it completely lacks a "when" clause and natural trigger variations, leaving it reliant on users already knowing the MPP jargon. Adding a Use-when clause with user-side phrasing would lift the two capped dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when an API returns 402 Payment Required, the user mentions MPP / machine payments / per-request billing, or asks to set up an agent wallet for paid API calls."

Add natural synonyms users would say, such as "402 Payment Required", "pay-per-request", and "agent wallet", alongside the existing "HTTP 402" and "MPP" terms.

Optionally name one more concrete capability (e.g. inspecting/decoding the 402 challenge or verifying payment receipts) to broaden the specificity coverage beyond the single "Pay" action.

DimensionReasoningScore

Specificity

"Pay HTTP 402 APIs via Machine Payments Protocol (MPP)" names the domain precisely and gives one concrete action ("Pay"), matching the anchor for 1-2 concrete actions without comprehensive coverage. Not 4 because only a single action is listed.

3 / 5

Completeness

The "what" is clear (pay HTTP 402 APIs via MPP) but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines. Not 2 because the "what" is crisp, not vague.

3 / 5

Trigger Term Quality

Relevant keywords are present ("Pay", "HTTP 402", "APIs", "Machine Payments Protocol", "MPP") but common variations users would naturally say — "402 Payment Required", "per-request pricing", "agent wallet" — are missing, matching the 'some relevant keywords but missing variations' anchor.

3 / 5

Distinctiveness Conflict Risk

"HTTP 402" and "Machine Payments Protocol (MPP)" form a clear niche with distinct triggers; virtually no other skill would fire on these terms, matching the minimal-conflict-risk anchor.

5 / 5

Total

14

/

20

Passed

Validation

81%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/payments/mpp-agent/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.