CtrlK
BlogDocsLog inGet started
Tessl Logo

setup-devops-agent

Setup and diagnostics for the AWS DevOps Agent MCP connection. Triggers when aws-devops-agent is missing from .mcp.json, when the connection is broken, or when the user says "set up devops agent" / "configure agent". Does NOT trigger if the MCP is already connected and working.

66

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./plugins/aws-agents-for-devsecops/skills/setup-devops-agent/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

75%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 well-structured, highly actionable setup workflow with executable diagnostics, verification, and config blocks plus a useful troubleshooting table. Its main weakness is conciseness: the bearer-vs-SigV4 offer phrasing is repeated across Step 0 and Step 2, and a few minor workflow gaps (Step 5 numbering, no post-reload tool check) keep workflow clarity just below the top anchor.

Suggestions

De-duplicate the bearer-vs-SigV4 offer language: state the tradeoff once in Step 2 and have Step 0 reference it instead of restating the full 'If Bearer... suggest SigV4 / If SigV4... suggest Bearer' branch.

Fix the Step 5 list numbering (it restarts at '1.' for the 'Instruct' item) so the multi-space routing sequence reads as one continuous ordered list.

Add a post-reload verification checkpoint in Step 6 (e.g. 'after /reload-plugins, confirm aws-devops-agent tools now appear via tools/list') to close the workflow loop.

DimensionReasoningScore

Conciseness

The body is mostly efficient with no concept-padding (no 'what is an MCP server' filler) and earns its tokens with commands and config blocks, but the bearer-vs-SigV4 offer language is repeated nearly verbatim across Step 0 and the Step 2 decision table, and the '(single agent space)' / '(multiple agent spaces and admin tooling)' gloss recurs many times. Not a 4 because the redundancy is more than minor; not a 2 because the content is not padded with things Claude already knows.

3 / 5

Actionability

Fully executable guidance throughout: diagnostic bash checks, a copy-paste curl tools/list call for bearer verification, a complete uvx pipeline for SigV4 verification, ready-to-write JSON config blocks for bearer/SigV4/fallback, env-var exports, and an error-to-fix troubleshooting table. Placeholders like ${DEVOPS_AGENT_REGION} and <REGION> are explicitly instructed to substitute. Fits the top anchor; not a 4 because examples cover the common cases completely.

5 / 5

Workflow Clarity

Steps 0-6 are clearly sequenced with an explicit verify-before-write checkpoint in Step 3 and error-recovery feedback loops in the verification tables. Not a 5 because of minor gaps: Step 5's numbered list restarts at '1.' mid-section, and after writing the config there is no post-reload step verifying that DevOps Agent tools actually appear. Not a 3 because validation checkpoints are present and explicit.

4 / 5

Progressive Disclosure

A single-file skill organized into clearly headed Steps 0-6 plus guidance sections, with external AWS doc links clearly signaled at one level deep. No bundle files exist and none are claimed. Not a 5 because the lengthy Bearer/SigV4 guidance walkthroughs and the routing-guide template are inlined rather than split into reference files; not a 3 because structure and navigation are genuinely good and existing references are clearly signaled.

4 / 5

Total

16

/

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.

The description is strong: it states what the skill does, gives concrete trigger conditions with natural user phrasings, and includes a negative-trigger boundary that reduces conflict risk. The only weakness is specificity, which surfaces just two actions rather than the broader set the skill performs.

Suggestions

Expand the capability list beyond 'Setup and diagnostics' to mention verification and .mcp.json config writing, e.g. '...verifies connectivity, and writes the .mcp.json server entry'.

Consider adding the file extension / key name users may mention (e.g. '.mcp.json') as an explicit trigger synonym to push trigger coverage toward exhaustive.

DimensionReasoningScore

Specificity

Names the domain ('AWS DevOps Agent MCP connection') and two concrete actions ('Setup and diagnostics'), but does not enumerate the fuller set of actions the body covers (verification, .mcp.json writing, multi-space routing). Not a 4 because only two actions are surfaced rather than 'several specific actions'; not a 2 because the actions are concrete, not generic.

3 / 5

Completeness

Explicitly answers both 'what' ('Setup and diagnostics for the AWS DevOps Agent MCP connection') and 'when' (concrete trigger conditions plus a 'Does NOT trigger' clause). Matches the anchor for clearly answering what and when with concrete trigger phrases; not below 5 since both are explicit and specific.

5 / 5

Trigger Term Quality

Includes natural user phrases ('set up devops agent' / 'configure agent') plus concrete config-state triggers ('missing from .mcp.json', 'connection is broken'), with synonyms. Not a 5 because coverage is good but not exhaustive of natural phrasings; not a 3 because multiple natural terms and a negative trigger are present.

4 / 5

Distinctiveness Conflict Risk

Scoped to a clear niche (AWS DevOps Agent MCP) with distinct triggers and an explicit negative-trigger guard ('Does NOT trigger if the MCP is already connected and working'), minimizing conflict risk. Fits the top anchor; not a 4 because the negative clause actively suppresses false positives.

5 / 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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
aws/agent-toolkit-for-aws
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.