instantly-debug-bundle

Collect Instantly.ai debug evidence for support tickets and troubleshooting. Use when encountering persistent issues, preparing support tickets, or auditing campaign/account state. Trigger with phrases like "instantly debug", "instantly support ticket", "instantly diagnostic", "instantly audit", "collect instantly evidence".

Quality

85%

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

80%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.

A highly actionable, code-first skill with strong conciseness and copy-paste-ready examples. It is held back by a monolithic inline structure with no bundle files and by the absence of an explicit validation/retry feedback loop for a batch collection operation.

Suggestions

Add a validation checkpoint after collection (e.g., assert the bundle is non-empty and re-fetch any endpoint whose error is retryable) to turn error capture into a validate->fix->retry loop and lift workflow_clarity.

Move the large TypeScript scripts into a scripts/ bundle file and reference them one level deep, leaving SKILL.md as a concise overview with the curl quick-diagnostic inline.

Flesh out the dangling 'Background Jobs API' reference with a real link and signal the 'instantly-common-errors' sibling skill more explicitly under Next Steps so navigation is unambiguous.

Dimension	Reasoning	Score
Conciseness	The body is dominated by executable code and concise tables with little explanatory prose and no restating of concepts Claude already knows, matching the lean anchor 3 rather than the padded anchor 2.	3 / 3
Actionability	It provides fully executable TypeScript and bash/curl+jq commands that are copy-paste ready with real endpoints and headers, matching the anchor 3 example rather than the pseudocode anchor 2.	3 / 3
Workflow Clarity	Steps are sequenced and each API call is wrapped in try/catch with errors collected, but there is no validate->fix->retry checkpoint that gates progression; per the batch-operation guideline this caps at anchor 2 rather than 3.	2 / 3
Progressive Disclosure	The ~230-line body keeps all TypeScript and bash inline with no bundle files (references/, scripts/, assets/ absent), so content that could be split out is inline, matching anchor 2 rather than the one-level-deep anchor 3.	2 / 3
	Total	10 / 12 Passed

Description

90%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 description: explicit 'Use when' guidance, natural trigger phrases, and a clear Instantly.ai niche. Its only gap is specificity, where a single headline action replaces a fuller enumeration of concrete capabilities.

Dimension	Reasoning	Score
Specificity	It names the domain and a couple of actions ('Collect Instantly.ai debug evidence', 'auditing campaign/account state') but does not enumerate a comprehensive list of concrete operations, matching anchor 2 rather than the multi-action anchor 3.	2 / 3
Completeness	It answers both 'what' (collect debug evidence for support tickets/troubleshooting) and 'when' with an explicit 'Use when encountering persistent issues...' clause plus triggers, matching anchor 3.	3 / 3
Trigger Term Quality	Explicit natural phrases a user would say are listed ('instantly debug', 'instantly support ticket', 'instantly diagnostic', 'instantly audit'), giving good coverage rather than the partial anchor 2.	3 / 3
Distinctiveness Conflict Risk	The Instantly.ai niche and distinct 'instantly ...' trigger phrases make it unlikely to fire for unrelated skills, matching the clear-niche anchor 3 rather than the overlapping anchor 2.	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
Path: plugins/saas-packs/instantly-pack/skills/instantly-debug-bundle/SKILL.md
Commit: 4c47e33

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.