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.
89
89%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
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.
This is a strong skill description that clearly identifies the tool (Gong API), lists specific capabilities, includes an explicit 'Use when' clause with natural trigger terms, and occupies a distinct niche. The description is concise yet comprehensive, covering both the what and when effectively. It uses proper third-person voice throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: searching calls, transcripts, conversation intelligence, listing calls, fetching transcripts, user management, and activity stats. | 3 / 3 |
Completeness | Clearly answers both what (Gong API for searching calls, transcripts, conversation intelligence; supports listing calls, fetching transcripts, user management, activity stats) and when (explicit 'Use when working with Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics'). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'Gong', 'call recordings', 'sales conversations', 'transcripts', 'meeting data', 'conversation analytics' — these are all terms a user would naturally use when needing this skill. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive due to the specific product name 'Gong' and the niche domain of sales conversation intelligence. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
79%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a strong, actionable API skill with excellent executable examples and good conciseness. Its main weakness is the lack of workflow sequencing for common multi-step patterns (e.g., searching then drilling into results) and missing error handling/validation guidance for API responses. The safety boundaries section is a notable strength.
Suggestions
Add a common workflow example showing a multi-step sequence like 'list recent calls → select call → fetch transcript' with validation of API responses between steps.
Include error handling guidance: what common error responses look like (401, 429 rate limit) and how to handle them.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It doesn't explain what Gong is, what APIs are, or how curl works. Every section delivers concrete, actionable content without padding. The Notes section is appropriately terse with only non-obvious details like rate limits and ID format quirks. | 3 / 3 |
Actionability | Every operation includes fully executable curl commands with jq processing pipelines that are copy-paste ready. The setup section provides exact file paths and JSON structure for credentials. Authentication shows the complete header construction pattern reused across all examples. | 3 / 3 |
Workflow Clarity | The skill presents individual operations clearly but lacks workflow sequencing for multi-step tasks (e.g., 'list calls → pick a call → get transcript'). Pagination is mentioned but there's no explicit loop/retry pattern. The safety boundaries are good but there are no validation checkpoints for verifying API responses or handling errors. | 2 / 3 |
Progressive Disclosure | The content is well-structured with clear headers and a useful endpoint reference table, but it's somewhat long for a single file. The endpoints reference table and date helpers could potentially be separated. However, there are no references to external files, which is acceptable given the content volume is borderline. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
72%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 8 / 11 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 | 8 / 11 Passed | |
- Repository
- jdrhyne/agent-skills
- Commit
6768672
- 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.