CtrlK
BlogDocsLog inGet started
Tessl Logo

troubleshooting-application-failures

Troubleshoots failing applications by discovering and analyzing CloudWatch log groups to identify error patterns, root causes, and actionable solutions. Use when an application is experiencing failures and log-based diagnosis is needed.

62

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/specialized-skills/operations-skills/troubleshooting-application-failures/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.

A well-structured overview that appropriately defers the detailed procedure to a single one-level-deep reference, keeping the SKILL.md body lean. The body's own actionability and workflow sequencing are thin because the executable content lives entirely in the referenced file.

Suggestions

Add a brief inline summary of the 9-step procedure (e.g., a numbered list of step names) so the workflow sequence and validation checkpoints are visible without opening the reference.

Include one or two representative executable commands (e.g., the describe-log-groups or start-query invocation) in the body so it is actionable on its own.

De-duplicate the troubleshooting section: keep it in one place (either the body or the reference) and cross-reference from the other to avoid drift.

DimensionReasoningScore

Conciseness

The body is lean — a two-sentence overview, a single pointer to the procedure reference, and a brief troubleshooting section — with no padding or re-explanation of concepts Claude already knows; minor redundancy from the troubleshooting section being duplicated in the reference file.

4 / 5

Actionability

The body itself provides some concrete specifics (log group name patterns, exact IAM permission names) but defers all executable commands and queries to the referenced procedure file, leaving the body's standalone guidance incomplete.

3 / 5

Workflow Clarity

The body delegates sequencing entirely with 'follow the procedure exactly. See [reference]' and shows no steps or checkpoints itself; the referenced procedure does contain validation checkpoints, but the body alone presents only an implicit, delegated sequence.

3 / 5

Progressive Disclosure

Clear overview pointing one level deep to a real, clearly signaled reference file (references/application-failure-troubleshooting.md, verified present); the inline troubleshooting section partially duplicates the reference's troubleshooting section, a minor organization gap.

4 / 5

Total

14

/

20

Passed

Description

87%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 clearly states both capabilities and trigger conditions with concrete, domain-specific language. Minor room to broaden trigger-term synonyms and tighten action specificity.

DimensionReasoningScore

Specificity

Names the domain (failing applications / CloudWatch logs) and lists several concrete actions — 'discovering and analyzing CloudWatch log groups', 'identify error patterns, root causes, and actionable solutions' — but the actions remain somewhat high-level compared to the comprehensive score-5 anchor.

4 / 5

Completeness

Explicitly answers both what ('Troubleshoots failing applications by discovering and analyzing CloudWatch log groups...') and when ('Use when an application is experiencing failures and log-based diagnosis is needed') with concrete trigger phrasing.

5 / 5

Trigger Term Quality

Includes natural terms a user might say ('failing applications', 'experiencing failures', 'log-based diagnosis', 'CloudWatch log groups') but misses common synonyms like 'errors', 'debugging', 'incidents', or 'logs' on their own.

4 / 5

Distinctiveness Conflict Risk

Carves a clear AWS/CloudWatch-specific niche with distinct triggers ('CloudWatch log groups', 'log-based diagnosis') and minimal overlap risk with other skills.

5 / 5

Total

18

/

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.

Validation15 / 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
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.