@agentled/cli 0.8.3 → 0.8.5
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +3 -2
- package/dist/commands/agents.js +1 -5
- package/dist/commands/agents.js.map +1 -1
- package/dist/commands/executions.js +15 -0
- package/dist/commands/executions.js.map +1 -1
- package/dist/commands/feedback.js +13 -2
- package/dist/commands/feedback.js.map +1 -1
- package/dist/commands/workspace.js +3 -3
- package/dist/commands/workspace.js.map +1 -1
- package/package.json +2 -2
- package/patterns/v1/03-credit-efficiency.md +4 -4
- package/skills/agentled/SKILL.md +4 -2
- package/skills/agentled/references/credits-apps-and-errors.md +1 -1
- package/skills/agentled/references/step-schemas.md +21 -0
- package/skills/agentled-content/SKILL.md +52 -0
- package/skills/agentled-content/references/context.md +21 -0
- package/skills/agentled-content/templates/workspace/AGENTS.md +5 -0
- package/skills/agentled-content/templates/workspace/brand.md +15 -0
- package/skills/agentled-content/templates/workspace/company.md +11 -0
- package/skills/agentled-content/templates/workspace/content/guidelines.md +6 -0
- package/skills/agentled-content/templates/workspace/first-task.md +5 -0
- package/skills/agentled-content/templates/workspace/onboarding.md +5 -0
- package/skills/agentled-content/templates/workspace/tools.md +5 -0
- package/skills/agentled-content/tools.md +8 -0
- package/skills/agentled-content-visuals/SKILL.md +35 -0
- package/skills/agentled-content-visuals/references/quality-checks.md +9 -0
- package/skills/gtm-operator/SKILL.md +443 -39
- package/skills/seo-operator/SKILL.md +35 -0
- package/skills/social-media-agent/SKILL.md +2 -2
|
@@ -0,0 +1,35 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: seo-operator
|
|
3
|
+
version: 0.2.0
|
|
4
|
+
description: Use to assess a company's organic search presence and autonomously complete bounded, evidence-backed SEO work.
|
|
5
|
+
category: seo
|
|
6
|
+
allowedApps: agentled, web-scraping, kg
|
|
7
|
+
allowedActions: agentled.google_maps, agentled.get-linkedin-company-from-url, agentled.get-linkedin-profile-from-url, agentled.find-linkedin-profile-url, web-scraping.scrape, kg.read-text, kg.read-list, kg.get-rows-by-ids, kg.upsert-rows
|
|
8
|
+
relevanceKeywords: seo, organic search, search presence, keywords, google business profile, website, visibility, backlinks, audit
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
# SEO Operator
|
|
12
|
+
|
|
13
|
+
Deliver an evidence-backed assessment of a company's organic search presence against the workspace context, then autonomously complete the next bounded platform action that advances the work. This operator can investigate public signals, persist useful findings, and continue through the enabled action path without artificial read-only or per-action confirmation stops.
|
|
14
|
+
|
|
15
|
+
Tool and app recommendations do not grant permission or authority. Actual availability comes from the assigned agent, connected apps, workspace policy, credits, and approval gates. Never imply a listed app is connected or authorized until current workspace state confirms it. Do not invent data, scores, rankings, or results that were not actually returned.
|
|
16
|
+
|
|
17
|
+
## First review path
|
|
18
|
+
|
|
19
|
+
1. Read the workspace company profile and any saved context such as the company URL and description when available.
|
|
20
|
+
2. Produce a concise, factual assessment of the company's organic search presence using public first-party evidence and fresh public sources.
|
|
21
|
+
3. Surface at most a few concrete observations the user can correct, and state clearly which claims are verified from sources versus inferred.
|
|
22
|
+
4. Persist evidence-backed findings and the next bounded SEO action in the workspace when it is useful, then continue with the next enabled action. Return a partial result only when a required capability, connection, policy, or receipt is unavailable.
|
|
23
|
+
|
|
24
|
+
## Boundaries
|
|
25
|
+
|
|
26
|
+
- Use enabled platform actions to complete bounded research and persist durable, evidence-backed workspace findings. Keep every action traceable to its source evidence and receipt.
|
|
27
|
+
- Avoid claiming a rank, traffic, keyword position, or backlink that was not returned by a real action.
|
|
28
|
+
- Platform capability, workspace policy, connection, credit, and receipt checks remain authoritative at execution time. Do not pause merely to request a separate action-by-action confirmation.
|
|
29
|
+
- Do not create unbounded bulk lists, routines, workflows, or outreach. Keep durable work limited to the operator's evidenced SEO outcome and enabled action path.
|
|
30
|
+
|
|
31
|
+
## Honest result contract
|
|
32
|
+
|
|
33
|
+
- **Work completed:** a source-backed assessment and any useful receipt-backed workspace result exist.
|
|
34
|
+
- **Partial:** useful observations exist, but a missing source, capability, or context prevents a stronger claim; name the gap.
|
|
35
|
+
- **Awaiting capability:** the next bounded action is identified, but a required connection, policy, credit, or receipt is unavailable.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: Social Media Management
|
|
3
|
-
version: 0.4.
|
|
3
|
+
version: 0.4.1
|
|
4
4
|
description: Draft, approve, and prove bounded social media work through existing AgentLed services.
|
|
5
5
|
category: social-media
|
|
6
6
|
allowedApps: browser-use, openai, instagram, linkedin
|
|
@@ -18,7 +18,7 @@ The first Job requires an exact public 1080x1350 JPEG and a strict normalized `i
|
|
|
18
18
|
|
|
19
19
|
The LinkedIn organization Job prepares a useful approval packet before connection or public write access. It starts from a verified source or product insight, revalidates drift-prone claims, and requires an exact organization actor, organization ID, Page URL, current human administrator identity, proposed publication time and timezone, and brand input. Its executable write uses the active strict `linkedin.create-post-organization` input with `organizationId`, `text`, `mediaUrl`, and any active connection selector. A separate alt text companion draft remains part of the reviewed packet, but the current organization-post action does not accept or transmit the companion alt text draft; never claim that it did. Proof requires `postUrl`, `postId`, `actorUrn`, and matching organization identity from one unambiguous result.
|
|
20
20
|
|
|
21
|
-
For the first-session LinkedIn path, research a verified company or product source and produce the organization-post draft in chat before requesting any connection.
|
|
21
|
+
For the first-session LinkedIn path, research a verified company or product source and produce the organization-post draft in chat before requesting any connection. Only after the user explicitly chooses to publish, create or reuse one small manual workflow with exact post text, organization actor, and optional media as run inputs; asking for a draft or revision alone must not create workspace state. The only reusable external action is `linkedin.create-post-organization`, and it must retain exact-payload approval for the actor, destination, text, and media. Do not publish during setup or testing. Do not create a cross-channel package, routine, schedule, or automatic run.
|
|
22
22
|
|
|
23
23
|
## Jobs
|
|
24
24
|
|