alert-manager

Use when the user asks to "set up SEO alerts", "monitor rankings", "notify me when rankings drop", "traffic alerts", "watch competitor changes", "alert me if rankings drop", "notify me of traffic changes", or "watch my keywords for changes". Sets up and manages alerts for critical SEO and GEO metrics including ranking drops, traffic changes, technical issues, and competitor movements. Enables proactive monitoring and quick response to issues. For detailed rank analysis, see rank-tracker. For comprehensive reporting, see performance-reporter.

Quality

80%

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

Quality

Content

70%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 highly actionable and clearly sequenced with validation, but it suffers from significant verbosity: repetitive template tables and inline duplication of content that also lives in the reference file. Splitting the bulk of the alert-category templates and threshold tables into the existing reference would tighten SKILL.md and improve progressive disclosure.

Suggestions

Move the detailed per-category alert template tables (ranking, traffic, technical, backlink, competitor, GEO, brand) and the "Alert Threshold Recommendations" / "Alert Fatigue Prevention" tables into references/alert-threshold-guide.md, keeping only a concise overview and the response/delivery sections in SKILL.md.

Consolidate the duplicated threshold guidance — the "Recommended Alert Thresholds by Metric" table in SKILL.md overlaps the reference's baseline/threshold methodology; keep one authoritative source and cross-link it.

Trim placeholder-heavy tables (e.g., [keyword 1], [Competitor 1]) to one representative example per category plus a pointer to a fill-in template, reducing token cost without losing actionability.

Dimension	Reasoning	Score
Conciseness	The ~627-line body is padded with many near-duplicate placeholder alert tables (ranking, traffic, technical, backlink, competitor, GEO, brand) and duplicates material already in the reference file ("Alert Threshold Recommendations", "Alert Fatigue Prevention"), which is noticeably verbose rather than lean.	2 / 5
Actionability	It provides copy-paste-ready markdown templates with specific thresholds (e.g., "≥50% drop", "Drop ≥3"), priority icons, recipients, and concrete decision-table playbooks (Step \| Action \| If True \| If False) covering the common cases.	5 / 5
Workflow Clarity	The 11-step "When a user requests alert setup" sequence is clearly ordered, capped by an "Alert Summary", and reinforced with explicit Input/Output validation checkpoints and playbooks containing verify-then-close feedback loops.	5 / 5
Progressive Disclosure	There is one clearly signaled one-level reference ("Alert Threshold Guide" with a descriptive caption), but the threshold and fatigue-prevention content is duplicated inline in SKILL.md instead of being split out, and much of the repeated template content belongs in the reference file.	3 / 5
	Total	15 / 20 Passed

Description

91%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 is strong: it pairs an explicit trigger clause with a concrete capability statement and cross-skill boundary guidance. Trigger phrases are numerous and natural, and the what/when split is clearly answered.

Dimension	Reasoning	Score
Specificity	"Sets up and manages alerts for... ranking drops, traffic changes, technical issues, and competitor movements" lists several specific concrete actions with only minor coverage gaps, fitting between the comprehensive (5) and several-actions (4) anchors.	4 / 5
Completeness	It opens with an explicit "Use when the user asks to..." clause answering when, then states what ("Sets up and manages alerts for critical SEO and GEO metrics..."), concretely answering both what and when.	5 / 5
Trigger Term Quality	The description packs in many natural phrases users would actually say ("set up SEO alerts", "monitor rankings", "notify me when rankings drop", "alert me if rankings drop", "watch my keywords for changes") including synonym variations, matching the comprehensive-coverage anchor.	5 / 5
Distinctiveness Conflict Risk	It occupies a clear SEO/GEO alerting niche with explicit boundary pointers ("For detailed rank analysis, see rank-tracker; For comprehensive reporting, see performance-reporter"), but terms like "monitor rankings" and "watch my keywords" still risk minor overlap with rank-tracker.	4 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (658 lines); consider splitting into references/ and linking	Warning
metadata_field	'metadata' should map string keys to string values	Warning
relative_links	Relative link issues: 26 suspicious	Warning

	Total	13 / 16 Passed

Repository: teeclaw/phorm-nft
Path: .agents/skills/alert-manager/SKILL.md
Commit: 02adecb

Reviewed: ~8 hours 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.