canary-watch

Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions after deploys, merges, or dependency upgrades. Smoke / canary / post-deploy verification.

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/canary-watch/SKILL.md

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 clean, well-organized monitoring skill with concrete commands and thresholds, but it lacks executable implementation code or scripts and does not present its workflow as an explicit sequenced process with checkpoints.

Suggestions

Add a short numbered run sequence (run checks → compare to baseline → classify → notify → report) with explicit validation/stop conditions to lift workflow_clarity above 3.

Provide an executable script in a scripts/ bundle (or inline code) that performs the HTTP/SSE/asset/console checks, so the skill is copy-paste runnable rather than a behavior spec.

Move the full output markdown template and detailed alert thresholds into a references/ file, keeping SKILL.md as a lean overview, to push progressive_disclosure to 5.

Dimension	Reasoning	Score
Conciseness	Lean and efficient — no concept explanations Claude already knows, with well-structured lists and a compact thresholds block; the full output markdown template is slightly long but earns its place as a concrete format reference.	4 / 5
Actionability	Provides concrete slash-command invocations and specific YAML thresholds, but with no accompanying scripts or executable check code, Claude must implement the monitoring logic itself; guidance is concrete on what to check but incomplete on how.	3 / 5
Workflow Clarity	The implied flow (check → compare to baseline → classify critical/warning/info → notify → report) is discernible and thresholds are well-defined, but steps are not laid out as an explicit numbered sequence with validation checkpoints.	3 / 5
Progressive Disclosure	Well-organized into clearly signaled one-level sections (When to Use, How It Works, Watch Modes, Alert Thresholds, Output, Integration) with no nested references; slightly over 50 lines so not a perfect 5, but content is appropriately self-contained.	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, specific description that clearly states both capabilities and trigger contexts with good synonym coverage. Only minor deducts for the 'Use this skill to' voice and a couple of missing natural trigger phrases.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'checks HTTP endpoints, SSE streams, static assets, console errors, and performance regressions' — for comprehensive coverage; reduced from 5 by one per the second-person voice penalty for the imperative 'Use this skill to' phrasing.	4 / 5
Completeness	Explicitly answers both what ('monitor and verify a deployed URL', the enumerated checks) and when ('after releases', 'after deploys, merges, or dependency upgrades') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Good natural-term coverage with synonyms — 'releases', 'deploys', 'merges', 'dependency upgrades', 'Smoke / canary / post-deploy verification' — though a few common phrases like 'health check' or 'uptime' are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche — post-deploy URL canary/smoke verification — with distinct triggers and minimal overlap risk against other skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

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

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: affaan-m/ECC
Path: skills/canary-watch/SKILL.md
Commit: 06c5e11

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.