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

90%

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.

A tight, highly actionable API reference with strong conciseness and copy-paste examples, weakened only by missing validation/error-handling in the workflow and a helper script bundle that the body fails to surface.

Suggestions

Add explicit validation/error-handling to the call workflow — e.g. check curl's HTTP status code and surface non-200 responses before piping to jq, so failures are caught early.

Reference the existing scripts/gong.sh helper from the body (e.g. a '## CLI helper' section pointing to scripts/gong.sh) and prefer it for common operations, keeping the inline curls as the one-level-deep detail.

Add a brief feedback loop for transcript fetches, which 'may take time to process' — note how to detect an empty/pending transcript and retry rather than treating it as success.

Dimension	Reasoning	Score
Conciseness	Lean body of mostly executable curl/jq snippets with minimal prose; no padding explaining concepts Claude already knows, and practical 'Notes' earn their place.	3 / 3
Actionability	Every operation is given as complete, copy-paste-ready curl commands with jq parsing and concrete request bodies, not pseudocode.	3 / 3
Workflow Clarity	Setup → authentication → operations is sequenced, but there are no validation checkpoints or error-handling for the API calls (e.g. checking HTTP status, retrying on failure), capping clarity at 2.	2 / 3
Progressive Disclosure	The body is well-sectioned, but a scripts/gong.sh bundle exists that duplicates and extends the inline operations yet is never referenced from the body; content that could live in the helper is inline.	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.

A well-crafted description: third-person voice, concrete capability list, explicit 'Use when' trigger guidance, and a distinct Gong niche. It meets the top anchor on all four dimensions without verbosity.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'searching calls, transcripts', 'listing calls, fetching transcripts, user management, and activity stats' — rather than vague language.	3 / 3
Completeness	Explicitly answers both what it does and when to use it via the 'Use when working with...' clause, satisfying the explicit-trigger requirement.	3 / 3
Trigger Term Quality	Strong coverage of natural terms users would say: 'Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics'.	3 / 3
Distinctiveness Conflict Risk	A clear Gong-specific niche with distinct triggers (Gong, call recordings, conversation intelligence) makes conflict with other skills unlikely.	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: a4d31ad

Reviewed: 11 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.