blog-decay

Detect content decay from Google Search Console exports by comparing current and previous page performance, flagging quarter-over-quarter traffic drops, dropped pages, and refresh, consolidate, prune, or query-shift actions. Use when the user says "/blog decay", "content decay", "traffic drop", "QoQ decline", "GSC decay", or "refresh declining posts".

Quality

100%

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

100%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is tight and actionable: concrete commands, input-format specs, severity and action decision tables, and validation guidance, all well-structured with one-level cross-references. Its only real weakness is packaging — the core referenced scripts are not shipped in this skill package.

Suggestions

Ship the referenced scripts/ directory: the body's primary command ('python3 scripts/content_decay.py ...') points to scripts/content_decay.py, but no scripts/ bundle directory exists in this skill package, so the command is not executable as shipped.

Verify the cross-skill path 'skills/blog-google/scripts/run.py' resolves in the deployment context, or document that blog-google must be installed separately, so the Optional Live GSC Export workflow is runnable.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes competence — it never explains what GSC, redirects, or QoQ mean, and every section (severity table, action table, input format) earns its tokens rather than padding concepts Claude already knows.	3 / 3
Actionability	Gives fully concrete, copy-paste-ready commands with options ('python3 scripts/content_decay.py current.json previous.json --threshold 0.30'), specifies the accepted input shapes, and supplies decision tables — matching the executable level-3 anchor.	3 / 3
Workflow Clarity	Two sequenced workflows (offline, live) with explicit validation checkpoints ('confirming identical filters, sufficient row limits, matching dimensions, and URL inspection'; 'only after checking indexation, canonical status, query loss...') provide clear sequence and checklists; the task is analytical rather than destructive, so no feedback-loop cap applies.	3 / 3
Progressive Disclosure	A single well-organized SKILL.md with clearly labeled sections and one-level-deep cross-references (Cross-references → blog-google, blog-rewrite) and no nested reference chains, matching the clear-overview level-3 anchor.	3 / 3
	Total	12 / 12 Passed

Description

100%

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: it names concrete capabilities, supplies an explicit 'Use when' trigger clause with natural phrasing, and carves out a distinct niche. No vague fluff or over-claims, and it stays in third person throughout.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'flagging quarter-over-quarter traffic drops, dropped pages, and refresh, consolidate, prune, or query-shift actions' — matching the anchor for comprehensive specific actions rather than the partial level-2 example.	3 / 3
Completeness	Explicitly answers both what (detect decay by comparing current vs previous GSC exports and flagging drops/actions) and when via an explicit 'Use when the user says...' clause, satisfying the level-3 anchor.	3 / 3
Trigger Term Quality	Provides natural trigger phrases a user would say — "/blog decay", "content decay", "traffic drop", "refresh declining posts" — giving good coverage rather than just a few relevant keywords.	3 / 3
Distinctiveness Conflict Risk	Clear niche (blog content decay from Search Console exports) with distinct triggers unlikely to collide with other skills; uses correct third-person voice so no specificity penalty.	3 / 3
	Total	12 / 12 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	14 / 16 Passed

Repository: AgriciDaniel/claude-blog
Path: brain/.raw/sources/claude-blog-skill/skills/blog-decay/SKILL.md
Commit: aec971a

Reviewed: about 14 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.