agent-guild-trust

Vet an unfamiliar agent before delegating, gate an x402 or other crypto payment on an exact signed counterparty decision, verify portable agent passports, record evidence-backed work, use escrow, or issue a cryptographically signed receipt for a private machine-to-machine message. Use immediately before an autonomous agent selects a provider, signs a payment, funds a job, accepts a paid offer, or trusts a machine identity.

Quality

90%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Medium

Suggest reviewing before use

Quality

Content

88%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 highly actionable and fail-closed with clear validation, well suited to a remote-service skill that delegates detail to live endpoints. Conciseness and progressive disclosure are strong but could improve by externalizing the inline tier table.

Suggestions

Move the protected-payment tier table and PayanAgent buy URLs out of SKILL.md into a references file or rely solely on the live GET /wallet-binding/protected-decision/tiers catalog to reduce inline bulk.

Trim repeated full-URL curl blocks by defining the base URL once and showing abbreviated examples for secondary calls.

Consolidate the safety invariants and fail-closed checks into a single explicit pre-signature checklist for the payment-gating workflow to make the validation checkpoint scan-able.

Dimension	Reasoning	Score
Conciseness	Mostly lean with executable curl/JSON blocks and no over-explanation of basic concepts, though the inline protected-payment tier table and some repeated full URL blocks could be tightened or externalized.	4 / 5
Actionability	Provides copy-paste-ready curl commands, exact JSON request bodies, named client methods, and specific endpoints covering the common delegation, payment-gating, passport, and receipt cases.	5 / 5
Workflow Clarity	Sequenced workflows with explicit validation checkpoints and fail-closed feedback loops (require all credential checks before signing; 'Any missing identity binding... must block'; 'Fail closed if the caller proof, signature... does not verify').	5 / 5
Progressive Disclosure	Well-organized sections with one-level-deep pointers to live service endpoints (/envelopes, /.well-known/agent-guild.json), but the protected-tier catalog and some marketplace URLs are inlined rather than split out, and no bundle files exist to offload detail.	4 / 5
	Total	18 / 20 Passed

Description

92%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 concrete, complete, and well-targeted: it names specific actions and gives explicit trigger guidance with a distinct niche. Minor room only in expanding natural trigger synonyms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions (vet an agent, gate a payment on an exact signed decision, verify passports, record evidence-backed work, use escrow, issue a signed receipt), giving comprehensive coverage of the skill's capabilities.	5 / 5
Completeness	Explicitly answers both what it does (vet, gate, verify, record, escrow, receipt) and when to use it ('Use immediately before an autonomous agent selects a provider, signs a payment, funds a job, accepts a paid offer, or trusts a machine identity').	5 / 5
Trigger Term Quality	Strong natural triggers ('delegate', 'signs a payment', 'accepts a paid offer', 'trusts a machine identity'), but a few common synonyms or shorthand phrasings a user might say are missing.	4 / 5
Distinctiveness Conflict Risk	Clear niche (agent-to-agent trust, payment gating, and receipt settlement) with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

Warnings & errors only

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: AgentTanuki/agent-guild-plugin
Path: skills/agent-guild-trust/SKILL.md
Commit: 75cb59f

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.