CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aws-well-architected

AWS Well-Architected integration. Manage data, records, and automate workflows. Use when the user wants to interact with AWS Well-Architected data.

Quality

64%

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 ./skills/aws-well-architected/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

61%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 content is a solid, command-driven integration guide with strong auth/connection state handling, but it is undermined by generic boilerplate (tautological heading, unexplained step numbering, an empty "Popular actions" section) and the absence of any concrete Well-Architected action example. Tightening structure and showing one real action invocation would move it from adequate to strong.

Suggestions

Fix the step numbering: label sections as explicit steps (1a/1b/2) so "skip to Step 2" resolves, and remove or populate the "## Popular actions" heading, which currently contains only a repeated discovery command.

Include one or two concrete Well-Architected action examples (e.g. a real `action list --intent "list workloads"` result and a sample `action run` invocation) instead of only QUERY placeholders.

Trim the introductory paragraph explaining what AWS Well-Architected is and its five pillars — Claude already knows this — and cut the filler line "Use action names and parameters as needed".

DimensionReasoningScore

Conciseness

Most of the body is efficient, concrete CLI guidance, but the opening paragraph explains what AWS Well-Architected is (five pillars, who uses it) — knowledge Claude already has — and lines like "Use action names and parameters as needed" are filler. This matches anchor 3 ("Mostly efficient but includes some unnecessary explanation or could be tightened"), not anchor 4, because the conceptual intro is a full paragraph of padding.

3 / 5

Actionability

The body provides mostly executable, copy-paste commands with clear placeholders (install, login with headless fallback, `connection ensure`, `action list --intent`, `action run --input`, and a proxy flag table). It stops short of anchor 5 because no real action is ever shown — only QUERY/actionId placeholders, with no concrete Well-Architected action example covering the common cases.

4 / 5

Workflow Clarity

A rough sequence exists (install → login → connection → discover → run) with a decent state-handling feedback loop (CLIENT_ACTION_REQUIRED → show uiUrl → re-poll), but "skip to **Step 2**" references a Step 2 that is never labeled, "#### 1b" has no corresponding 1a, and "## Popular actions" contains no actual actions. The dangling step references and missing checkpoints match anchor 3 ("Steps listed but validation gaps; sequence present but checkpoints missing or implicit") rather than anchor 4's clear, complete sequence.

3 / 5

Progressive Disclosure

As a single-file bundle (~140 lines) with no external references needed, the section organization is good: overview, install, auth, connecting, searching, running, proxy, best practices, with the proxy options appropriately kept to a compact table. It falls short of anchor 5 due to duplicated action-discovery guidance across "Searching for actions" and "Popular actions" and the misleading empty "Popular actions" heading.

4 / 5

Total

14

/

20

Passed

Description

52%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 names a distinct niche and includes an explicit 'Use when...' clause, but its capability statement is generic boilerplate and its trigger guidance is tautological. Rewriting it around concrete Well-Architected operations and real user phrases would lift it substantially.

Suggestions

Replace "Manage data, records, and automate workflows" with the concrete operations the skill supports, e.g. "List and review workloads, answer review questions, manage lenses and milestones, retrieve workload reports".

Expand the trigger clause with phrases users actually say: "Use when the user mentions well-architected reviews, workload reviews, lenses, milestones, or wants to evaluate an architecture against AWS best practices".

DimensionReasoningScore

Specificity

The domain is named ("AWS Well-Architected") but the actions are generic — "Manage data, records, and automate workflows" could apply to almost any integration and lists no concrete Well-Architected operations (review workloads, answer questions, lenses, milestones). This matches anchor 2 ("Names the domain but actions are minimal or generic"), and not anchor 3, which requires 1-2 genuinely concrete actions.

2 / 5

Completeness

Both a 'what' ("Manage data, records, and automate workflows") and an explicit 'when' ("Use when the user wants to interact with AWS Well-Architected data") are present, so it is not capped below 3; however the 'what' is generic and the 'when' is tautological, merely restating the domain rather than giving concrete trigger phrases. It sits between anchors 3 and 4 but is weaker than the anchor 4 example on both components.

3 / 5

Trigger Term Quality

"AWS Well-Architected" is the natural phrase a user would say and appears twice, but there are no variations or synonyms such as "well-architected review", "workload review", "architecture review", or "WAF" — fitting anchor 3 ("Some relevant keywords but missing common variations or synonyms"). It is not anchor 4 because keyword coverage is limited to the bare service name.

3 / 5

Distinctiveness Conflict Risk

"AWS Well-Architected" is a clear niche with a distinct, unambiguous trigger phrase ("interact with AWS Well-Architected data"), making it unlikely to fire for the wrong skill despite the generic "manage data, records" tail. This matches anchor 5 ("Clear niche with distinct triggers; minimal conflict risk").

5 / 5

Total

13

/

20

Passed

Validation

93%

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

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository

membranedev/application-skills

Path

skills/aws-well-architected/SKILL.md

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.