highlevel
Connect your AI assistant to GoHighLevel CRM via the official API v2. Manage contacts, conversations, calendars, pipelines, invoices, payments, workflows, and 30+ endpoint groups through natural language. Includes interactive setup wizard and 100+ pre-built, safe API commands. Python 3.6+ stdlib only — zero external dependencies.
72
58%
Does it follow best practices?
Impact
100%
1.40xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/10xcoldleads/highlevel/SKILL.mdQuality
Discovery
82%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 description with excellent specificity and distinctiveness, clearly naming the GoHighLevel CRM platform and listing numerous concrete capabilities. The main weakness is the absence of an explicit 'Use when...' clause, which would help Claude know exactly when to select this skill. The trigger terms are naturally aligned with what users would say when working with GoHighLevel.
Suggestions
Add an explicit 'Use when...' clause, e.g., 'Use when the user mentions GoHighLevel, GHL, CRM contacts, pipelines, or wants to interact with the GoHighLevel API.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: manage contacts, conversations, calendars, pipelines, invoices, payments, workflows, and references 30+ endpoint groups and 100+ pre-built API commands. Also mentions interactive setup wizard and technical requirements. | 3 / 3 |
Completeness | The 'what' is well-covered (connect to GoHighLevel CRM, manage various entities, setup wizard, pre-built commands). However, there is no explicit 'Use when...' clause or equivalent trigger guidance, which per the rubric caps completeness at 2. | 2 / 3 |
Trigger Term Quality | Includes strong natural keywords users would say: 'GoHighLevel', 'CRM', 'API', 'contacts', 'conversations', 'calendars', 'pipelines', 'invoices', 'payments', 'workflows'. These are terms a user working with GoHighLevel would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Very clearly scoped to GoHighLevel CRM specifically via its official API v2. The mention of 'GoHighLevel' as a named product creates a distinct niche that is unlikely to conflict with other CRM or API skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill covers an impressive breadth of GoHighLevel API functionality with a clear setup wizard and helper script, but it is far too verbose for a SKILL.md — the 39-endpoint reference table, detailed scope matrices, and promotional content should be moved to reference files. The actionability is moderate with concrete commands listed but lacking input/output examples, and the workflow lacks validation checkpoints for destructive operations like sending messages or voiding invoices.
Suggestions
Move the 39-endpoint group table, scope recommendation tables, and Agency vs Sub-Account comparison to reference files (e.g., references/endpoints.md, references/scopes.md) and replace with brief summaries linking to them.
Add concrete input/output examples for the most common commands (e.g., show exact JSON input for create_contact and expected response format).
Add explicit validation/confirmation steps for destructive operations — e.g., 'Before sending a message, confirm the contactId exists by running get_contact first' or 'Before voiding an invoice, verify the invoice status.'
Remove all promotional/affiliate content (5-Day Challenge links, 'Built by' section, social media links) which waste tokens and are not actionable skill content.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose — the massive 39-row endpoint table, detailed Agency vs Sub-Account comparison, scope tables, webhook event lists, SDK references, and promotional/marketing content (affiliate links, social media links, 'Built by' section) consume enormous token budget. Much of this is reference material that belongs in separate files, and Claude doesn't need explanations of what Private Integrations are or how OAuth works. | 1 / 3 |
Actionability | The setup steps and helper script command table provide concrete guidance, and the `python3 scripts/ghl-api.py` commands are specific and executable. However, there are no actual code examples showing API call construction, no example input/output pairs for the commands, and the 39-endpoint coverage table describes capabilities rather than providing executable instructions. | 2 / 3 |
Workflow Clarity | The setup workflow has clear numbered steps (create integration → get location ID → set env vars → test connection), but there are no validation checkpoints or error recovery steps for API operations. For a skill involving destructive operations (create/update/delete contacts, send messages, void invoices), there are no confirmation or verification steps mentioned. | 2 / 3 |
Progressive Disclosure | The references directory structure is well-organized with clear one-level-deep links to 10 reference files. However, the SKILL.md itself is a monolithic wall of text with the full 39-endpoint table, detailed scope tables, and extensive notes that should be in reference files rather than inline in the main skill file. | 2 / 3 |
Total | 7 / 12 Passed |
Validation
81%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 9 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
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 | 9 / 11 Passed | |
- Repository
- openclaw/skills
- Commit
06ad5e3
- 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.