gong

Gong API for searching calls, transcripts, and conversation intelligence. Use when working with Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics. Supports listing calls, fetching transcripts, user management, and activity stats.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

80%

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 concise and immediately actionable with complete, executable curl/jq snippets. It loses points on workflow clarity for lacking validation/feedback loops and on progressive disclosure for not signaling or linking the bundled gong.sh helper script.

Suggestions

Add a validation/feedback loop for batch fetches, e.g., loop pagination using the returned cursor until totalRecords is exhausted rather than relying on a single request.

Reference the bundled helper: add a short section such as '## Helper script' pointing to scripts/gong.sh for common operations, so the bundle is discoverable.

Include a verification step after transcript calls (e.g., check for an empty callTranscripts array and note transcripts may still be processing) to close the feedback loop.

Dimension	Reasoning	Score
Conciseness	The body is lean and command-focused: each section is a copy-paste curl/jq snippet with minimal prose, assuming Claude's competence and adding only Gong-specific details it would not already know.	3 / 3
Actionability	Every operation is a complete, executable bash snippet with real endpoints, headers, and jq transforms; the Endpoints Reference and Date Helpers make the guidance copy-paste ready.	3 / 3
Workflow Clarity	Operations are individually clear but there are no validation/verification checkpoints or feedback loops for batch or fetch operations (e.g., checking pagination cursor exhaustion, confirming a transcript has processed), capping workflow clarity per the rubric.	2 / 3
Progressive Disclosure	The body is well-organized into sections but is a monolithic SKILL.md with no reference to the bundled scripts/gong.sh helper; content that could be externalized is inline and the available bundle file is not signaled.	2 / 3
	Total	10 / 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.

The description is specific, trigger-rich, complete, and clearly scoped to Gong conversation intelligence. It hits all four anchor top-levels with concise, third-person phrasing and no fluff.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions including 'listing calls, fetching transcripts, user management, and activity stats' alongside the named domain of calls, transcripts, and conversation intelligence.	3 / 3
Completeness	Clearly answers what it does and includes an explicit 'Use when working with Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics' trigger clause.	3 / 3
Trigger Term Quality	Covers natural terms users would say ('call recordings', 'sales conversations', 'transcripts', 'meeting data', 'conversation analytics') plus the Gong brand, giving good keyword coverage.	3 / 3
Distinctiveness Conflict Risk	The Gong-specific domain and brand-named triggers carve a clear niche that is unlikely to conflict with other generic skills.	3 / 3
	Total	12 / 12 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
metadata_version	'metadata.version' is missing	Warning
metadata_field	'metadata' should map string keys to string values	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	13 / 16 Passed

Repository: jdrhyne/agent-skills
Commit: 292843f

Reviewed: about 18 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.