CtrlK
BlogDocsLog inGet started
Tessl Logo

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".

71

Quality

88%

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

77%Weight 40%Scale 1-3

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

The skill is highly actionable with a clear sequenced workflow and a pre-submit sensitive-data validation step, but it is monolithic — the executable script lives entirely inline in SKILL.md with no bundle files, and the bash is somewhat verbose due to fragmented repetitive echo blocks.

Suggestions

Move the bash script into a `scripts/clay-debug-bundle.sh` bundle file and have SKILL.md reference it, so the body becomes an overview with one-level-deep navigation (improves progressive_disclosure).

Consolidate the seven fragmented steps into a single cohesive script to remove repetitive `echo >> summary.txt` blocks and tighten token usage (improves conciseness).

Add a short re-verification loop after the sensitive-data review (e.g., 'if secrets found, re-redact and re-check before packaging') to turn the one-shot checkpoint into a true validate-fix-retry feedback loop.

DimensionReasoningScore

Conciseness

The body avoids explaining concepts Claude already knows, but the bash is fragmented across seven steps with repetitive `echo >> summary.txt` blocks that could be consolidated into a single leaner script, fitting 'mostly efficient but could be tightened'.

2 / 3

Actionability

Provides fully executable bash (`set -euo pipefail`, real `curl` webhook/API calls, `tar -czf` packaging, `sed` redaction, `grep` log search) plus a concrete fill-in markdown checklist — copy-paste ready with no pseudocode.

3 / 3

Workflow Clarity

A clearly numbered 7-step sequence with an explicit pre-submit validation checkpoint ('BEFORE SUBMITTING: Review for sensitive data!') and `set -euo pipefail` error handling; the operation is non-destructive diagnostics so the destructive/batch feedback-loop cap does not apply.

3 / 3

Progressive Disclosure

No bundle files exist and the entire ~185-line skill is monolithic — the full debug script is inline rather than split into a `scripts/clay-debug-bundle.sh` file, so content that should be separate stays inline despite well-organized sections.

2 / 3

Total

10

/

12

Passed

Description

100%Weight 40%Scale 1-3

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, third-person description that names concrete actions, supplies explicit 'Use when' triggers with multiple natural phrases, and occupies a clearly distinct niche. No first/second-person voice or vague fluff to penalize.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'Collect Clay debug evidence', 'preparing support tickets', 'collecting diagnostic information for Clay integration problems' — matching the anchor for several specific actions rather than a single domain mention.

3 / 3

Completeness

Explicitly answers what ('Collect Clay debug evidence for support tickets and troubleshooting') and when via an explicit 'Use when encountering persistent issues...' clause plus trigger phrases, satisfying both halves.

3 / 3

Trigger Term Quality

Provides five natural user phrases ('clay debug', 'clay support bundle', 'collect clay logs', 'clay diagnostic', 'clay support ticket') giving broad coverage of terms a user would plausibly say.

3 / 3

Distinctiveness Conflict Risk

The Clay-specific, product-prefixed triggers and narrow integration-debugging niche make it unlikely to fire for unrelated skills, matching the clear-niche anchor.

3 / 3

Total

12

/

12

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

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
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.