ghl-mermaid-map
Renders the account's system flow as a Mermaid map — entry points, tags, pipeline stages, workflows, messaging sinks, and exits, connected by inferred edges (tag handoffs, stage changes, form submissions, goal events). Descriptive only — the map shows structure, never findings or verdicts. Use whenever an audit needs a system-flow diagram, when recon data is partial and a map still has to ship, or when asked to visualize how contacts move through a GHL sub-account.
- License 许可
- MIT
- 最近更新
- 2026-11-13
- Stars
- ★ 12
- Forks
- 5
01 前言 Front Matter
- name
- ghl-mermaid-map
- description
- Renders the account's system flow as a Mermaid map — entry points, tags, pipeline stages, workflows, messaging sinks, and exits, connected by inferred edges (tag handoffs, stage changes, form submissions, goal events). Descriptive only — the map shows structure, never findings or verdicts. Use whenever an audit needs a system-flow diagram, when recon data is partial and a map still has to ship, or when asked to visualize how contacts move through a GHL sub-account.
02 资源文件 1
- 参考文档references/grammar.md11.2 KB
03 SKILL.md 正文
GHL Mermaid Map
Turns recon output (workflow roster, pipeline/stage list, tags in use, forms,
and — when available — captured workflow internals) into one flowchart TD
Mermaid diagram of the contact journey through a GHL sub-account.
Read references/grammar.md before rendering a map. It's the whole grammar:
- Node taxonomy and ID-prefix conventions (§1–2).
- Edge-inference rules — what data pattern implies which edge, and how to label it (§3).
- Stub-node handling — the rule that keeps the map shippable even when recon is partial (§4).
- The descriptive-not-verdict boundary — the map is structure only; findings and severity live in the audit report, never on the diagram (§5).
- A worked, hand-checked example (§6).
Ground rules
- Contact-journey frame, not dependency graph. Every edge must narrate as "a contact arrives here, something happens, the contact ends up there." If it can't be told that way, it isn't a map edge.
- The map always ships. Partial data renders as opaque stub nodes
(
references/grammar.md§4) — never omit a node or withhold the map because a workflow's internals weren't captured. - No verdicts on the diagram. Labels state facts the data supports
(
tag: X,creates opp @ stage). Judgments ("broken", "duplicate", "wasteful") belong in the audit report as findings, citing the map's node/edge as evidence — never in the.mmditself. - Read-only. This skill only reads recon artifacts already gathered
elsewhere (
ghl-audit-primitives,uxie-ghl-mcp, or a workflow-JSON capture) and writes a Mermaid diagram; it never touches the GHL account.
Scope
IN: node taxonomy, edge-inference grammar, stub handling, and the descriptive/verdict boundary for one system-flow map.
OUT: deciding what's in-scope for a given audit mode (thesis vs. deep-dive
vs. sweep scoping), writing the narrative commentary that accompanies the
map, and any finding/severity logic — those live with the auditor orchestration
and ghl-audit-primitives respectively.
04 同仓库更多 Skills
ghl-workflow-specialist
Senior GoHighLevel workflow architect — designs automations (nurture, speed-to-lead, no-show recovery, internal ops, data hygiene, routing) grounded in the full trigger/action catalog and known anti-patterns, and reviews or fixes live workflows. Use when the user asks what automation to set up for X, wants a workflow designed, or asks why a live workflow is not getting through, is failing, or whether an A/B test is done. Recons + reads the client brief before proposing anything. Once approved, the build itself goes to create-ghl-workflow.
ghl-workflow-fast-forward
Fast-forward contacts parked at a GoHighLevel / HighLevel workflow WAIT step to the next step — the builder's "Action statistics → move to next step" control, driven via the internal API. Use to accelerate end-to-end workflow testing (drive a multi-day wait ladder to completion in minutes instead of waiting real time), to unstick contacts stranded at a wait, or when the user says "fast-forward this wait", "skip the wait", "move parked/stuck contacts to the next step", "requeue stuck contacts", "test this long delay without waiting days", or gives an app.gohighlevel.com workflow URL and asks to push contacts past a wait. This MUTATES live enrollments (it fires whatever steps come next, i.e. real SMS/email to real people) — it is a WRITE skill and follows the plugin's write-rails. It is the mutating counterpart to the read-only get-ghl-workflow-logs.
ghl-voice-ai
Build and configure GoHighLevel Voice AI phone agents — the prompt, the voice, the actions (appointment booking, call/agent transfer, contact-field extraction, SMS, workflows, custom API), knowledge bases, MCP servers, working hours, and outbound consent. Use when the user says 'set up a voice agent', 'build a phone agent', 'my AI should answer calls', 'book appointments over the phone', 'outbound calling', 'the agent isn't transferring calls', 'change the voice', or names a Voice AI agent. Internal API — the public rail exposes only how the agent sounds, not what it does.
ghl-system-conventions
House conventions for building GoHighLevel systems — workflow naming and structure, tag/field/custom-value discipline, pipeline and opportunity decisions, copy rules, and the pre-build approval document the operator signs off before anything gets created. Account-agnostic, for ANY GHL sub-account. Use whenever designing, building, editing, reviewing, or discussing GHL workflows, automations, pipelines, stages, opportunities, tags, custom fields, custom values, calendars, or AI agents — even if the user never says "conventions" or "standards". Load it BEFORE proposing a design or creating any GHL object, so the proposal already looks the way the operator wants it.
ghl-snapshots
GoHighLevel snapshots — capturing a sub-account's assets into a reusable snapshot, refreshing one, curating what it carries, and checking load conflicts. Use when a task involves creating or updating a snapshot, deciding what an account template should include, asking why a snapshot came out empty or is stuck processing, or planning a rollout onto other sub-accounts. Read it BEFORE calling any /snapshots path by raw_request — two of the write endpoints silently do the wrong thing.
ghl-reverse-engineering
Map a GoHighLevel internal surface exhaustively — enumerate every screen, panel, control and save path a feature has, capture the real request behind each one, prove what each field does by differential, and write the result into the corpus. Use when the user wants to understand how a GHL feature works under the hood, extend an engine to an object the public API can't reach, re-sweep a surface that already has partial coverage, or asks to reverse-engineer / sniff / capture / trace anything internal. GHL permits inspecting your own account's traffic. This is a MAPPING skill, not a lookup: it finishes when the surface is exhausted, not when the first endpoint is found.