CtrlK
BlogDocsLog inGet started
Tessl Logo

chainlink-ace-skill

Handle Chainlink ACE (Automated Compliance Engine) work using the public smartcontractkit/chainlink-ace repository and official docs.chain.link ACE Platform docs. Use for audited ACE core contracts, managed Platform/Beta scope, Coordinator API, Reporting API, Policy Management, PolicyEngine, PolicyProtected, policy chains, custom policies, extractors, mappers, Cross-Chain Identity (CCIDs), credential registries, KYC/AML credentials, sanctions screening, regulated tokens, ERC-20 and ERC-3643 compliance token examples, upgrade guidance, and BUSL licensing. Trigger on any mention of ACE, Automated Compliance Engine, chainlink-ace, Chainlink compliance, policy enforcement, ERC-3643, or onchain compliance rules, even if the user does not explicitly say 'ACE'.

89

1.16x
Quality

85%

Does it follow best practices?

Impact

98%

1.16x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

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 an exceptionally lean, well-structured overview that routes to a real, one-level-deep reference bundle and gates destructive writes behind explicit two-step validation. The main gaps are the absence of any worked example (a filled-in preflight or a concrete Coordinator API call) and process logic spread across sections instead of one coherent end-to-end sequence.

Suggestions

Add one worked example showing the preflight template filled in for a representative operation (e.g., attaching a SecureMintPolicy) so the answer contract is unambiguous in practice.

Consolidate the Policy Edit Answer Contract, rate-limit, and second-confirmation rules into one sequential write workflow (inspect -> table -> preflight -> confirm 1 -> confirm 2) so the steps read in execution order rather than across sections.

Move the two niche wallet-limit/VolumeRatePolicy paragraphs, which only apply to one request shape, into a reference file (e.g., policy-library.md) and keep a one-line pointer in the body.

DimensionReasoningScore

Conciseness

The body is ~95 lines of terse, telegraphic guidance with zero padding and no explanations of concepts Claude already knows (e.g., 'PolicyRejected reverts, Allowed skips remaining policies' assumes Solidity knowledge). Every token earns its place, matching the lean anchor 5 rather than anchor 4, which requires over-explanation to trim.

5 / 5

Actionability

Guidance is largely executable: exact selector-to-field mappings, a fully specified preflight template with named fields, a concrete fallback ladder ('WebFetch first; then curl -L <official-url>'), and a routing table whose nine reference paths all exist. As an instruction-only skill the absence of code is not penalized, but it falls short of anchor 5 because a few directives remain abstract ('Keep answers proportional', 'call out infinite staleness') and no worked example shows the preflight filled in.

4 / 5

Workflow Clarity

Write operations are clearly sequenced with validation checkpoints: inspect before recommending, preflight display, explicit approval, 'second explicit confirmation immediately before execution', fail-closed blockers when inspection is unavailable, and a numbered freshness sequence. Validation is present (so the destructive-operation cap at 3 does not apply), but the process is distributed across sections rather than a single ordered workflow with error-recovery loops, fitting anchor 4 rather than 5.

4 / 5

Progressive Disclosure

The body is an overview with a routing table mapping trigger asks to nine reference files, all of which exist in references/ and are linked one level deep (sibling references cross-link directly, no deeper nesting). Content is appropriately split and navigation is easy, matching anchor 5.

5 / 5

Total

18

/

20

Passed

Description

83%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.

A strong description: it states a concrete scope with an explicit, even aggressive, trigger clause covering synonyms and the unstated-'ACE' case. Its main weakness is that the capability list is largely topical nouns anchored by the generic verb 'Handle', and a couple of trigger phrases are broad enough to invite overlap with non-Chainlink compliance work.

DimensionReasoningScore

Specificity

The opening verb 'Handle ... work' is generic, but the description enumerates many specific capabilities (Coordinator/Reporting API, PolicyEngine, PolicyProtected, policy chains, extractors, mappers, CCIDs, KYC/AML credentials, ERC-3643 token examples, BUSL licensing). It lists several specific items with only minor coverage gaps, matching anchor 4 rather than 5 because the capabilities are named as topics rather than concrete actions.

4 / 5

Completeness

It clearly states what it does ('Handle Chainlink ACE (Automated Compliance Engine) work using the public smartcontractkit/chainlink-ace repository and official docs.chain.link ACE Platform docs') and explicitly when to trigger ('Trigger on any mention of ACE, ... even if the user does not explicitly say ACE') with concrete trigger phrases, exactly matching anchor 5.

5 / 5

Trigger Term Quality

'Trigger on any mention of ACE, Automated Compliance Engine, chainlink-ace, Chainlink compliance, policy enforcement, ERC-3643, or onchain compliance rules' gives good keyword coverage with synonyms and the repo name. A few natural user variations (e.g., 'ComplianceEngine', 'onchain KYC/AML', 'regulated token') appear only inside the what-clause rather than the trigger list, so it fits anchor 4 rather than the comprehensive anchor 5.

4 / 5

Distinctiveness Conflict Risk

The niche is clear and Chainlink-ACE-specific with distinct triggers, but broad trigger phrases like 'policy enforcement' and 'onchain compliance rules' create minor overlap risk with generic onchain-compliance or security-policy questions, fitting anchor 4 rather than the minimal-conflict anchor 5.

4 / 5

Total

17

/

20

Passed

Validation

100%

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
smartcontractkit/chainlink-agent-skills
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.