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.

65

Quality

78%

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

Quality

Content

73%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 delivers a strongly sequenced, validation-heavy setup workflow with executable commands, decision tables, and recovery paths — workflow clarity is excellent. Weaknesses are moderate redundancy (repeated config locations and auth-switch offers) and one actionability gap: the bearer .mcp.json config embeds an unexpanded ${DEVOPS_AGENT_REGION} placeholder with no substitution instruction.

Suggestions

In the Bearer config section, either instruct replacing the region placeholder (as the SigV4 section does with '<REGION>') or provide the exact URL to write, since JSON in .mcp.json does not expand ${DEVOPS_AGENT_REGION}.

Deduplicate the MCP config location list: present it once (Step 4) and have Step 0 reference it, and tighten the repeated auth-switch suggestion wording in Step 0.

Move the Bearer token guidance and SigV4 guidance sections into a references/ file (e.g. references/auth-setup.md) with clearly signaled links from the main flow to reduce SKILL.md length.

DimensionReasoningScore

Conciseness

The body is mostly commands, tables, and configs, but contains redundant passages: the opening sentence "For other clients, use this as a reference, but adjust the instructions...", seven config locations listed in Step 0 with three repeated verbatim in Step 4, and convolutedly repeated auth-switch offers in Step 0. This matches 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the minor-trims-only anchor 4.

3 / 5

Actionability

Concrete curl/uvx verification commands, result-to-action tables, and complete JSON configs make the guidance mostly copy-paste ready, matching anchor 4. It is not a 5 because the bearer JSON config contains a literal "${DEVOPS_AGENT_REGION}" placeholder that will not expand when written to .mcp.json, and unlike the SigV4 section ("Replace <REGION> with the user's actual region"), the bearer section gives no instruction to substitute the actual region.

4 / 5

Workflow Clarity

Steps 0-6 are clearly sequenced with explicit validation (Step 3 verifies credentials against the live endpoint before any write), confirmation gates ("Do NOT proceed to Step 3 until the user confirms"; "Only write after the user confirms"), and per-error recovery tables with fallback paths. This matches the anchor 5 example of validation steps, feedback loops, and checkpoints.

5 / 5

Progressive Disclosure

No bundle files exist (no references/, scripts/, or assets/), and the single file is well-sectioned with clear internal cross-references ("see Step 3: Verify connectivity") and clearly labeled per-path guidance and troubleshooting sections, matching anchor 4. It is not a 5 because a ~295-line skill keeps bearer/SigV4 user guidance and troubleshooting inline where well-signaled one-level reference files (e.g. a token-creation guide) would improve navigation.

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.

A strong description with an explicit what/when pair, concrete trigger phrases, and a useful negative trigger that prevents firing when the MCP already works. The only soft spot is that the capability list is thin (just 'setup and diagnostics') and a few natural trigger synonyms are absent.

DimensionReasoningScore

Specificity

"Setup and diagnostics for the AWS DevOps Agent MCP connection" names the domain plus exactly two concrete actions (setup, diagnostics), which matches the '1-2 concrete actions, not comprehensive' anchor. It is not a 4 because no further specific operations (configure auth, verify connectivity, multi-space routing) are enumerated.

3 / 5

Completeness

It explicitly answers what ("Setup and diagnostics for the AWS DevOps Agent MCP connection") and when ("Triggers when aws-devops-agent is missing from .mcp.json, when the connection is broken, or when the user says...") with concrete trigger phrases, and even adds a negative condition. This clearly matches the anchor 5 example; anchor 4's 'when could be more explicit' does not apply since the when-clause is fully specified.

5 / 5

Trigger Term Quality

Natural phrases like "set up devops agent" / "configure agent" plus concrete signals ("missing from .mcp.json", "connection is broken") give good coverage, but common variations such as "install" or "connect" the agent are missing, so it falls short of the comprehensive-synonyms anchor 5.

4 / 5

Distinctiveness Conflict Risk

The description targets a clear niche (a named AWS product, a specific config file key) with distinct triggers and an explicit negative trigger ("Does NOT trigger if the MCP is already connected and working"), minimizing conflict risk with other skills. No neighboring anchor fits better.

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.

Validation — 16 / 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.