CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

aws-cloudwatch-url-builder

Construct deep-link URLs for the AWS CloudWatch console — Logs Insights queries, Alarm detail pages, Metrics graphs. Use when encoding log groups, time ranges, query strings, metric dimensions, or opening CloudWatch views in a Playwright browser session. Keywords: CloudWatch deep-link Logs-Insights alarm metrics fragment-encoding *XX-encoding epoch timestamp hash-routing url-construction SPA alarm-detail metric-graph log-group query-string cloudwatch-console.

71

Quality

89%

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

SKILL.md
Quality
Evals
Security

Quality

Content

92%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-crafted, highly actionable skill body: it teaches only CloudWatch's unusual fragment-encoding language, gives complete templates and an executable encoder, sequences the work with an explicit verification step, and backs it with concrete BAD/GOOD anti-patterns. The only real weakness is verbatim duplication of the templates and encoding tables between the body and the reference file.

Suggestions

Keep only abbreviated inline versions of the three URL templates (or just the fragment portion) in SKILL.md and leave the full templates plus the complete encoding tables in references/encoding-reference.md, which already contains them.

Drop or shorten the 'Expected result:' lines under each template; they state what the template obviously does.

DimensionReasoningScore

Conciseness

The body is dense with non-obvious CloudWatch-specific knowledge (the '*XX' fragment encoding, '$3F'/'$D'/'$26' segment encoding, ISO timestamps with '*3a' colons) and never explains basics Claude already knows. It misses a 5 because the full URL templates and the encoding table are duplicated verbatim between the SKILL.md body and references/encoding-reference.md, and the 'Expected result' lines under each template are filler that could be trimmed.

4 / 5

Actionability

Fully executable guidance throughout: complete copy-paste URL templates for all three page types (Logs Insights, alarm detail, metrics graph), an encoding quick-reference table, a runnable python3 shell one-liner with its exact expected output ('*2faws*2flambda*2fmy-service-prod-Handler'), and a concrete ISO timestamp example. These cover the common cases end to end.

5 / 5

Workflow Clarity

The 'Build Order' section gives a clear 5-step numbered sequence ending in an explicit 'Verify' step (timestamps ISO 8601 UTC with '*3a' colons, region in both subdomain and query string), plus the alarm 'rule of thumb' and nine anti-patterns each paired with BAD/GOOD examples that serve as failure-mode checkpoints. This matches the anchor-5 example's validate-before-proceed structure; no error-recovery loop is needed for read-only URL construction.

5 / 5

Progressive Disclosure

A single reference file (references/encoding-reference.md, verified to exist) held one level deep, clearly signaled both in Build Order step 4 and in a References table with a 'When to Use' column. The body keeps an operational quick reference inline while the full parameter tables and encoded-query examples live in the reference — matching the anchor-5 structure.

5 / 5

Total

19

/

20

Passed

Description

83%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 in third-person voice with a concrete 'what' and an explicit 'Use when' trigger clause covering the skill's three URL types. Trigger keywords are good but mix natural user phrasing with internal jargon, and the Playwright clause creates minor overlap with the companion navigation skill.

Suggestions

Add one or two natural user phrasings to the keywords (e.g. 'CloudWatch console link', 'open Logs Insights query') and trim internal jargon like 'SPA', 'hash-routing' and '*XX-encoding' that no user would naturally say.

Narrow the 'opening CloudWatch views in a Playwright browser session' trigger toward URL construction specifically, to reduce overlap with the companion aws-console-navigator skill.

DimensionReasoningScore

Specificity

'Construct deep-link URLs for the AWS CloudWatch console — Logs Insights queries, Alarm detail pages, Metrics graphs' names the domain and three concrete targets, matching the anchor-4 'several specific actions; minor gaps' level. It stays below 5 because the capability is a single verb (construct URLs) instantiated over three objects, unlike the anchor-5 example's multiple distinct actions (extract, fill, merge, convert).

4 / 5

Completeness

It clearly answers both questions: the 'what' is 'Construct deep-link URLs for the AWS CloudWatch console — Logs Insights queries, Alarm detail pages, Metrics graphs' and the 'when' is the explicit clause 'Use when encoding log groups, time ranges, query strings, metric dimensions, or opening CloudWatch views in a Playwright browser session'. This mirrors the anchor-5 example's 'actions + Use when...' shape with concrete trigger phrases.

5 / 5

Trigger Term Quality

The keyword list includes genuinely natural terms users would say — 'CloudWatch deep-link Logs-Insights alarm metrics log-group query-string cloudwatch-console' — giving good coverage, but a few natural phrases are missing (e.g. 'console link', 'open Logs Insights query', 'CloudWatch alarm page') and several keywords are internal jargon a user would not naturally say ('SPA', 'hash-routing', '*XX-encoding', 'epoch timestamp'). This sits between the anchor-4 'good coverage; a few natural terms missing' and anchor-5 comprehensive-synonym level, noticeably above the midpoint but not clearly matching 5.

4 / 5

Distinctiveness Conflict Risk

The niche is clear (building CloudWatch console deep-links with fragment encoding), so it would rarely trigger for unrelated skills, but the 'opening CloudWatch views in a Playwright browser session' clause overlaps the companion aws-console-navigator skill's territory (SSO auth, region switching, Playwright navigation) mentioned in the body. That is exactly the anchor-4 case: mostly distinct with minor overlap risk against a closely related skill.

4 / 5

Total

17

/

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

pantheon-org/tekhne

Path

skills/infrastructure/aws-investigation-toolkit/skills/aws-cloudwatch-url-builder/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.