clay-debug-bundle

Collect Clay debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or collecting diagnostic information for Clay integration problems. Trigger with phrases like "clay debug", "clay support bundle", "collect clay logs", "clay diagnostic", "clay support ticket".

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

77%

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

A solid, highly actionable skill body: copy-paste-ready bash with a real review checkpoint for sensitive data. The weaker dimensions are conciseness (duplicated version probes and restated redaction) and progressive disclosure (the sizable script is inline rather than split into a scripts/ file).

Suggestions

Remove the duplicated node/python version probes — keep them only in Step 3's environment capture and drop the inline 'Current State' block, or have Step 3 source those values instead of re-running them.

Move the multi-step bash recipe into scripts/clay-debug-bundle.sh and reference it from the body, so SKILL.md stays an overview and the script is executable directly rather than reconstructed from code fences.

Trim the 'Sensitive Data Handling' section to a short pointer that reinforces the existing Step 7 review rather than restating redaction the script already performs.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean executable bash with no concept-explanation fluff, but it duplicates the node/python version probes (inline 'Current State' block and again in Step 3) and the sensitive-data section restates redaction the script already performs, so it could be tightened; not the 3-anchor because some tokens do not earn their place twice.	2 / 3
Actionability	Every step is fully executable bash with 'set -euo pipefail', real curl calls capturing HTTP codes, env-var guards, sed-based redaction, tar packaging, and a concrete fill-in checklist for the manual table diagnostics, matching the 3-anchor for copy-paste-ready guidance.	3 / 3
Workflow Clarity	A clear 7-step sequence includes an explicit validation checkpoint in Step 7 ('BEFORE SUBMITTING: Review for sensitive data!') with concrete secret/PII checks and a review-fix-submit feedback loop for a sensitive batch bundle, satisfying the 3-anchor despite this being a batch data-collection operation.	3 / 3
Progressive Disclosure	There are no bundle files (no references/scripts/assets directories), and the body is well-organized into clean sections with one clearly signaled one-level pointer ('clay-rate-limits'); however the full multi-step bash script lives inline when it could be split into a scripts/ file, so it is not the 3-anchor where content is appropriately split across files.	2 / 3
	Total	10 / 12 Passed

Description

90%

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 is niche-scoped, third-person, and answers both 'what' and 'when' with an explicit Use-when clause and natural trigger phrases. The only weakness is specificity, where it describes one broad collection action rather than enumerating several distinct concrete actions.

Dimension	Reasoning	Score
Specificity	It names the Clay domain and the concrete action 'Collect Clay debug evidence' and 'collecting diagnostic information', but it is essentially a single collection action rather than a list of multiple distinct concrete actions as in the 3-anchor; above the 2-anchor because the actions are concrete, below 3 because it is not comprehensive across multiple actions.	2 / 3
Completeness	It explicitly answers 'what' ('Collect Clay debug evidence for support tickets and troubleshooting') and 'when' with an explicit 'Use when...' clause plus 'Trigger with phrases like...', satisfying the 3-anchor; the missing-'Use when' cap does not apply because the clause is present.	3 / 3
Trigger Term Quality	It provides good coverage of natural phrases a user would actually say — 'clay debug', 'clay support bundle', 'collect clay logs', 'clay diagnostic', 'clay support ticket' — matching the 3-anchor for natural-term coverage.	3 / 3
Distinctiveness Conflict Risk	It is scoped to a clear niche (Clay integration) with distinct triggers unlikely to fire for unrelated skills, matching the 3-anchor; voice is third person/imperative ('Collect', 'Use when'), so no voice penalty applies.	3 / 3
	Total	11 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: jeremylongshore/claude-code-plugins-plus-skills
Commit: 02d6341

Reviewed: 4 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.