shopify-admin-agentic-policy-readability

Name: shopify-admin-agentic-policy-readability
Author: 40RTY-ai

168stars17forks

How to install shopify-admin-agentic-policy-readability?

40rty-ai/shopify-admin-skills/shopify-admin-agentic-policy-readability

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-agentic-policy-readability

Installs into the current project.

Summary

Ensure shipping, returns, refund, privacy, and terms policies exist as clean machine-readable text so AI agents can answer shopper questions and close the sale without escalating.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Before an AI agent completes a purchase for a shopper it checks the store's policies — "Do they ship to me? What's the return window?" If shipping/returns policies are missing, empty, or buried in an image/PDF, the agent can't answer, loses confidence, and abandons or sends the shopper elsewhere. This skill audits the store's policies and ensures the key ones exist as clean, plain-text/HTML content an agent can read and quote. Fixes `shipping-policy-readable` and `returns-policy-readable`.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session (`shopify auth login --store <domain>`)
6	- Required API scopes: `read_legal_policies` (or `read_online_store_pages`), `write_legal_policies`
7
8	## Parameters
9	All skills accept these universal parameters:
10
11	\| Parameter \| Type \| Required \| Default \| Description \|
12	\|-----------\|--------\|----------\|---------\|-------------\|
13	\| store \| string \| yes \| — \| Store domain (e.g., mystore.myshopify.com) \|
14	\| format \| string \| no \| human \| Output format: `human` (default) or `json` \|
15	\| dry_run \| bool \| no \| true \| Preview proposed policy bodies without writing (defaults ON — edits live store policies) \|
16
17	Skill-specific parameters:
18
19	\| Parameter \| Type \| Required \| Default \| Description \|
20	\|-----------\|------\|----------\|---------\|-------------\|
21	\| policies \| string \| no \| REFUND_POLICY,SHIPPING_POLICY \| Comma list of policy types to ensure: `REFUND_POLICY,SHIPPING_POLICY,PRIVACY_POLICY,TERMS_OF_SERVICE` \|
22	\| mode \| string \| no \| audit \| `audit` (report gaps only) or `apply` (write supplied/drafted bodies) \|
23	\| bodies_dir \| string \| no \| — \| Directory of `<POLICY_TYPE>.html` files to use as the source of truth when `mode: apply` \|
24
25	## Safety
26
27	> ⚠️ Step 2 (`shopPolicyUpdate`) replaces a LIVE legal policy's body — this is legally binding content. NEVER auto-generate legal text. In `mode: apply` the skill only writes bodies you supply via `bodies_dir`; it will not invent policy language. Default is `mode: audit` + `dry_run: true`. Have legal/ops review every body before `mode: apply`.
28
29	## Workflow Steps
30
31	1. OPERATION: `shop` — query
32	Inputs: none; read `shopPolicies { type body url }`
33	Expected output: Which target policies are present, empty, or image-only (heuristic: very short body or body that's just an `<img>`/link).
34
35	2. COMPUTE (no API): classify each policy as OK / missing / thin / image-only. In `audit` mode, stop here and report. In `apply` mode, load the matching `<TYPE>.html` from `bodies_dir` for each gap and emit a before/after preview.
36
37	3. OPERATION: `shopPolicyUpdate` — mutation (only in `mode: apply`, not `dry_run`)
38	Inputs: `shopPolicy: { id: <policy id>, body: <supplied HTML> }` per gap.
39	Expected output: Updated policy; collect `userErrors`.
40
41	## GraphQL Operations
42
43	```graphql
44	# shop:query — validated against api_version 2025-01
45	query PolicyAudit {
46	shop {
47	shopPolicies {
48	id
49	type
50	body
51	url
52	}
53	}
54	}
55	```
56
57	```graphql
58	# shopPolicyUpdate:mutation — validated against api_version 2025-01
59	mutation PolicyUpdate($shopPolicy: ShopPolicyInput!) {
60	shopPolicyUpdate(shopPolicy: $shopPolicy) {
61	shopPolicy { id type url }
62	userErrors { field message }
63	}
64	}
65	```
66
67	## Session Tracking
68
69	Claude MUST emit the following output at each stage. This is mandatory.
70
71	On start, emit:
72	```
73	╔══════════════════════════════════════════════╗
74	║ SKILL: <skill name> ║
75	║ Store: <store domain> ║
76	║ Started: <YYYY-MM-DD HH:MM UTC> ║
77	╚══════════════════════════════════════════════╝
78	```
79
80	After each step, emit:
81	```
82	[N/TOTAL] <QUERY\|MUTATION> <OperationName>
83	→ Params: <brief summary of key inputs>
84	→ Result: <count or outcome>
85	```
86
87	If `dry_run: true`, prefix every mutation step with `[DRY RUN]` and do not execute it.
88
89	On completion, emit:
90
91	For `format: human` (default):
92	```
93	══════════════════════════════════════════════
94	OUTCOME SUMMARY
95	<Metric label>: <value>
96	Errors: 0
97	Output: <filename or "none">
98	══════════════════════════════════════════════
99	```
100
101	For `format: json`, emit:
102	```json
103	{
104	"skill": "<skill-slug>",
105	"store": "<domain>",
106	"started_at": "<ISO8601>",
107	"completed_at": "<ISO8601>",
108	"dry_run": false,
109	"steps": [
110	{
111	"step": 1,
112	"operation": "<OperationName>",
113	"type": "query",
114	"params_summary": "<string>",
115	"re

People who liked this also viewed

6 picks

Type

shopify-admin-agentic-policy-readability

168stars17forks

View on GitHub

How to install shopify-admin-agentic-policy-readability?

40rty-ai/shopify-admin-skills/shopify-admin-agentic-policy-readability

$npx -y skills add 40RTY-ai/shopify-admin-skills --skill shopify-admin-agentic-policy-readability

Installs into the current project.

Summary

Ensure shipping, returns, refund, privacy, and terms policies exist as clean machine-readable text so AI agents can answer shopper questions and close the sale without escalating.

Files · 1

View on GitHub

SKILL.md

1	## Purpose
2	Before an AI agent completes a purchase for a shopper it checks the store's policies — "Do they ship to me? What's the return window?" If shipping/returns policies are missing, empty, or buried in an image/PDF, the agent can't answer, loses confidence, and abandons or sends the shopper elsewhere. This skill audits the store's policies and ensures the key ones exist as clean, plain-text/HTML content an agent can read and quote. Fixes `shipping-policy-readable` and `returns-policy-readable`.
3
4	## Prerequisites
5	- Authenticated Shopify CLI session (`shopify auth login --store <domain>`)
6	- Required API scopes: `read_legal_policies` (or `read_online_store_pages`), `write_legal_policies`
7
8	## Parameters
9	All skills accept these universal parameters:
10
11	\| Parameter \| Type \| Required \| Default \| Description \|
12	\|-----------\|--------\|----------\|---------\|-------------\|
13	\| store \| string \| yes \| — \| Store domain (e.g., mystore.myshopify.com) \|
14	\| format \| string \| no \| human \| Output format: `human` (default) or `json` \|
15	\| dry_run \| bool \| no \| true \| Preview proposed policy bodies without writing (defaults ON — edits live store policies) \|
16
17	Skill-specific parameters:
18
19	\| Parameter \| Type \| Required \| Default \| Description \|
20	\|-----------\|------\|----------\|---------\|-------------\|
21	\| policies \| string \| no \| REFUND_POLICY,SHIPPING_POLICY \| Comma list of policy types to ensure: `REFUND_POLICY,SHIPPING_POLICY,PRIVACY_POLICY,TERMS_OF_SERVICE` \|
22	\| mode \| string \| no \| audit \| `audit` (report gaps only) or `apply` (write supplied/drafted bodies) \|
23	\| bodies_dir \| string \| no \| — \| Directory of `<POLICY_TYPE>.html` files to use as the source of truth when `mode: apply` \|
24
25	## Safety
26
27	> ⚠️ Step 2 (`shopPolicyUpdate`) replaces a LIVE legal policy's body — this is legally binding content. NEVER auto-generate legal text. In `mode: apply` the skill only writes bodies you supply via `bodies_dir`; it will not invent policy language. Default is `mode: audit` + `dry_run: true`. Have legal/ops review every body before `mode: apply`.
28
29	## Workflow Steps
30
31	1. OPERATION: `shop` — query
32	Inputs: none; read `shopPolicies { type body url }`
33	Expected output: Which target policies are present, empty, or image-only (heuristic: very short body or body that's just an `<img>`/link).
34
35	2. COMPUTE (no API): classify each policy as OK / missing / thin / image-only. In `audit` mode, stop here and report. In `apply` mode, load the matching `<TYPE>.html` from `bodies_dir` for each gap and emit a before/after preview.
36
37	3. OPERATION: `shopPolicyUpdate` — mutation (only in `mode: apply`, not `dry_run`)
38	Inputs: `shopPolicy: { id: <policy id>, body: <supplied HTML> }` per gap.
39	Expected output: Updated policy; collect `userErrors`.
40
41	## GraphQL Operations
42
43	```graphql
44	# shop:query — validated against api_version 2025-01
45	query PolicyAudit {
46	shop {
47	shopPolicies {
48	id
49	type
50	body
51	url
52	}
53	}
54	}
55	```
56
57	```graphql
58	# shopPolicyUpdate:mutation — validated against api_version 2025-01
59	mutation PolicyUpdate($shopPolicy: ShopPolicyInput!) {
60	shopPolicyUpdate(shopPolicy: $shopPolicy) {
61	shopPolicy { id type url }
62	userErrors { field message }
63	}
64	}
65	```
66
67	## Session Tracking
68
69	Claude MUST emit the following output at each stage. This is mandatory.
70
71	On start, emit:
72	```
73	╔══════════════════════════════════════════════╗
74	║ SKILL: <skill name> ║
75	║ Store: <store domain> ║
76	║ Started: <YYYY-MM-DD HH:MM UTC> ║
77	╚══════════════════════════════════════════════╝
78	```
79
80	After each step, emit:
81	```
82	[N/TOTAL] <QUERY\|MUTATION> <OperationName>
83	→ Params: <brief summary of key inputs>
84	→ Result: <count or outcome>
85	```
86
87	If `dry_run: true`, prefix every mutation step with `[DRY RUN]` and do not execute it.
88
89	On completion, emit:
90
91	For `format: human` (default):
92	```
93	══════════════════════════════════════════════
94	OUTCOME SUMMARY
95	<Metric label>: <value>
96	Errors: 0
97	Output: <filename or "none">
98	══════════════════════════════════════════════
99	```
100
101	For `format: json`, emit:
102	```json
103	{
104	"skill": "<skill-slug>",
105	"store": "<domain>",
106	"started_at": "<ISO8601>",
107	"completed_at": "<ISO8601>",
108	"dry_run": false,
109	"steps": [
110	{
111	"step": 1,
112	"operation": "<OperationName>",
113	"type": "query",
114	"params_summary": "<string>",
115	"re

People who liked this also viewed

6 picks

Type