CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

72

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

The canonical home for this skill is gong in jdrhyne/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

90%Weight 40%Scale 1-5

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

A well-crafted reference-style body: lean, copy-paste-ready recipes with sensible gotcha notes and no padding. The main gaps are the absence of any error/validation guidance and the failure to surface the bundled scripts/gong.sh helper from the body.

Suggestions

Add a brief error-handling/validation note (e.g., check HTTP status or jq-empty results, retry on 429 given the ~3 req/s rate limit) so API failures are caught early.

Reference scripts/gong.sh from the body (e.g., a 'CLI Helper' section: 'For quick lookups, run scripts/gong.sh <command> — see gong.sh help'), since the bundle already provides a tested wrapper including a connection test.

Show one complete paginated follow-up request that combines the cursor with the date filter, since the current Pagination section only shows the cursor field in isolation.

DimensionReasoningScore

Conciseness

Lean and efficient throughout: no concept explanations, straight to credential setup, an auth snippet, and copy-paste recipes; the only near-redundancy is the one-line intro restating the description, which costs almost nothing. It assumes Claude's competence and every section earns its place.

5 / 5

Actionability

Fully executable copy-paste curl+jq commands for every operation, including auth header construction, jq result projection, and a portable date helper (BSD and GNU date variants). The pagination section shows the cursor field but not a complete follow-up request combining cursor with filter — a minor gap consistent with the top anchor's 'covers the common cases'.

5 / 5

Workflow Clarity

Setup → Authentication → Core Operations is a coherent, ordered sequence and the Notes section flags operational gotchas (transcript processing delay, rate limit, date format), but there is no response validation or error handling (e.g., checking for auth failures or empty results). It sits above 'checkpoints missing or implicit' (3) because the sequence and gotcha notes are clear, but below (5) which requires explicit validation steps and error-recovery feedback loops.

4 / 5

Progressive Disclosure

The body is well organized with clear sections (Setup, Authentication, Core Operations, Endpoints Reference, Pagination, Date Helpers, Notes) and no wall of text. However, the bundle's scripts/gong.sh — a ready-made CLI duplicating all body operations — is never referenced or linked from the body, so a one-level-deep resource goes unsignaled; that minor organization gap fits anchor 4 rather than 5.

4 / 5

Total

18

/

20

Passed

Description

87%Weight 40%Scale 1-5

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: third-person, concrete, with an explicit 'Use when...' clause covering multiple natural trigger contexts. Minor room to sharpen generic phrases like 'user management' and add a few more synonyms.

DimensionReasoningScore

Specificity

Lists several concrete actions ('listing calls, fetching transcripts, user management, and activity stats') alongside 'searching calls, transcripts', giving specific capability coverage; 'user management' and 'conversation intelligence' are slightly generic, keeping it below the comprehensive 5 anchor.

4 / 5

Completeness

Explicitly answers both what ('Gong API for searching calls, transcripts, and conversation intelligence... Supports listing calls, fetching transcripts, user management, and activity stats') and when ('Use when working with Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics') with concrete trigger contexts, matching the top anchor; the when-clause is explicit and specific, not merely serviceable.

5 / 5

Trigger Term Quality

Natural phrases users would say ('Gong call recordings, sales conversations, transcripts, meeting data, or conversation analytics') are present, but a few natural synonyms (e.g., 'call notes', 'deal reviews', 'revenue calls') are missing, so it fits the 'good coverage, a few natural terms missing' anchor rather than the comprehensive one.

4 / 5

Distinctiveness Conflict Risk

'Gong API' and 'Gong call recordings' establish a clear product-named niche with distinct triggers and minimal overlap risk with other skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
bap-jorkim/agent-skills-fork-feb-25
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.