CtrlK
BlogDocsLog inGet started
Tessl Logo

bedrock-agentcore-policy

Amazon Bedrock AgentCore Policy for defining agent boundaries using natural language and Cedar. Deterministic policy enforcement at the Gateway level. Use when setting agent guardrails, access control, tool permissions, or compliance rules.

60

Quality

73%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/bedrock-agentcore-policy/SKILL.md

The canonical home for this skill is bedrock-agentcore-policy in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

63%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.

A thorough, code-rich skill with strong actionability and clear per-operation workflows, undermined by Cedar-pattern redundancy across sections and dangling references to bundle files that are not present.

Suggestions

Create the three referenced files (references/cedar-syntax.md, references/policy-patterns.md, references/troubleshooting.md) and move the inlined Cedar Quick Reference and Operation 3 patterns into them, leaving SKILL.md as an overview with one or two illustrative examples.

Consolidate the repeated permit/forbid Cedar demonstrations that currently appear in Operation 2, Operation 3, Quick Reference, and Best Practices into a single canonical set of examples to reduce redundancy.

Define or remove the simulate_policy() helper used in the Operation 5 test_scenarios so the test code is actually runnable end-to-end.

DimensionReasoningScore

Conciseness

The body is code-forward and mostly efficient, but Cedar permit/forbid patterns are demonstrated in four separate places (Operation 2, Operation 3's six patterns, Cedar Quick Reference, and Best Practices), creating notable redundancy that could be consolidated.

3 / 5

Actionability

Concrete, mostly executable boto3 and Cedar code runs throughout, with minor gaps such as the undefined simulate_policy() helper in the test scenarios and a partially sketched invoke_agent_runtime payload.

4 / 5

Workflow Clarity

Five operations are each sequenced with waiters for async completion (PolicyGenerationCompleted, PolicyEngineActive), and Operation 5 provides validation checks plus a debug feedback loop, though validation is split across operations rather than a single end-to-end pipeline.

4 / 5

Progressive Disclosure

A References section signals three files (cedar-syntax.md, policy-patterns.md, troubleshooting.md), but none of them exist on disk, and the Cedar syntax and pattern content that should live in those files is instead inlined in the body.

3 / 5

Total

14

/

20

Passed

Description

82%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, third-person description that crisply states both purpose and explicit 'Use when' triggers tied to a specific AWS product niche. Minor room to broaden capability specificity and add a few trigger synonyms.

DimensionReasoningScore

Specificity

Names the domain ('Amazon Bedrock AgentCore Policy', 'Cedar', 'Gateway') plus 1-2 concrete actions ('defining agent boundaries', 'policy enforcement') but does not enumerate a comprehensive set of capabilities, matching the 'names domain and 1-2 concrete actions' anchor.

3 / 5

Completeness

It explicitly answers both what it does ('defining agent boundaries using natural language and Cedar', 'Deterministic policy enforcement at the Gateway level') and when to use it ('Use when setting agent guardrails, access control, tool permissions, or compliance rules') with concrete trigger phrases.

5 / 5

Trigger Term Quality

'Use when setting agent guardrails, access control, tool permissions, or compliance rules' provides good natural keyword coverage users would actually say, though a few synonyms (e.g., RBAC, authorization) are absent.

4 / 5

Distinctiveness Conflict Risk

The Bedrock AgentCore / Cedar / Gateway framing carves a clear niche with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

17

/

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.

Validation13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (595 lines); consider splitting into references/ and linking

Warning

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

referenced_paths_exist

Referenced path issues: 3 missing

Warning

Total

13

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.