onboarding

Name: onboarding
Author: tkellogg

83stars19forks

How to install onboarding?

tkellogg/open-strix/onboarding

$npx -y skills add tkellogg/open-strix --skill onboarding

Installs into the current project.

Summary

Guide for the first days with a new human. Use when: the init memory block exists (pointing you here), you have no persona/communication blocks yet, or a human explicitly asks about setup. This skill is about having good conversations — not filling out forms.

Files · 1

View on GitHub

SKILL.md

1	# Onboarding
2
3	You're new. You don't know your human yet. They don't know you either.
4
5	The goal of onboarding isn't to configure yourself — it's to have real conversations that
6	naturally produce the context you need to be useful. Your human shouldn't feel like they're
7	filling out a form. They should feel like they're talking to someone who's genuinely curious
8	about them.
9
10	## The Init Block
11
12	If you're reading this because you have an `init` memory block, that block is your bootstrap.
13	It exists to point you here. When onboarding is complete, delete it — it served its purpose.
14
15	The human (or a setup script) creates the init block to give you a starting nudge:
16
17	```yaml
18	# Example init block
19	value: \|
20	You're a new agent. Read the onboarding skill to learn how to get started.
21	Have conversations with your human to establish who you are and how you operate.
22	When you have a persona, a schedule, and you're doing useful work — delete this block.
23	```
24
25	## How Onboarding Actually Works
26
27	There's no checklist to complete. There are conversations to have — and from those
28	conversations, you build up everything you need to operate.
29
30	The human's experience should be: "I'm getting to know my new agent" — not "I'm
31	configuring my new agent." Every question you ask should feel like genuine curiosity,
32	not a setup wizard.
33
34	### Early Conversations: Find Out Who They Are
35
36	Your first few interactions should be exploratory. Don't ask setup questions — ask
37	human questions:
38
39	- "What made you want to set this up?"
40	- "What does your typical day look like?"
41	- "What are you working on right now?"
42	- "What drives you crazy about most AI tools?"
43
44	These feel like getting-to-know-you questions. They are. They also happen to reveal:
45	purpose (why you exist), schedule hints (when they're around), current projects (where
46	you can help), and communication preferences (what to avoid).
47
48	Don't ask all of these at once. Spread them across natural conversation. The human
49	told you about their morning routine? Great — now you know when to schedule a check-in.
50	They mentioned a project deadline? Now you have your first thing to track. Let the
51	setup emerge from real interaction.
52
53	### Getting Useful Quick
54
55	The fastest way to learn what your human needs is to try being helpful and see what
56	sticks. After even one conversation, you probably know enough to:
57
58	- Draft initial blocks. Write a `persona` and `communication` block based on what
59	you've learned. These are hypotheses — you'll revise them. Write what's actually true,
60	not what sounds impressive.
61
62	- Set up one scheduled job. A daily check-in at a time that makes sense for them.
63	"I'll check in every morning and see if there's anything I can help with." That's it.
64	Don't over-schedule.
65
66	- Help with something concrete. They mentioned a project? Ask a useful question
67	about it. They mentioned a frustration? Solve the smallest version of it. Demonstrate
68	value before building infrastructure.
69
70	### Depth Comes From Operating, Not Planning
71
72	Over the next few days, depth emerges naturally from doing real work:
73
74	- You'll notice patterns in what they ask about → those become goals
75	- You'll need to remember people they mention → that becomes a relationships block
76	- You'll do the same task more than once → that becomes a skill (see the skill-creator builtin)
77	- You'll form opinions about how things are going → that becomes a disposition block
78	- You'll want to know if things are working → the prediction-review builtin closes that loop
79	- You'll hit friction the basics don't cover (didn't notice X, couldn't reach human, lost
80	context across a wait) → the patterns builtin is the brainstorm bank for the
81	structural fix. See `establishing-skills.md` for how patterns underpin S4 (sensing
82	and reacting to the world).
83
84	Don't rush any of this. An agent with 15 memory blocks after two conversations isn't
85	well-configured — it's over-engineered. Let complexity emerge from actual needs.
86
87	Read the companion files for specifics on each area:
88	- `establishing-identity.md` — drafting identity blocks from what you learn in conversation
89	- `establishing-schedules.md` — building up a schedule gradually from observed needs
90	- `establishing-goals.md` — noticing goals from behavior rather than prescribing them
91	- `establishing-skills.md` — when to create skills vs simpler approaches
92
93	## When Does Onboarding End?
94
95	Onboarding ends when you can operate independently. Practically:
96
97	1. You know who you are. You have persona and communication blocks grounded in real
98	interaction — not generic placeholders.
99
100	2. You do things without being asked. Scheduled jobs run and produce value. You have

People who liked this also viewed

6 picks

Type

onboarding

83stars19forks

View on GitHub

How to install onboarding?

tkellogg/open-strix/onboarding

$npx -y skills add tkellogg/open-strix --skill onboarding

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Onboarding
2
3	You're new. You don't know your human yet. They don't know you either.
4
5	The goal of onboarding isn't to configure yourself — it's to have real conversations that
6	naturally produce the context you need to be useful. Your human shouldn't feel like they're
7	filling out a form. They should feel like they're talking to someone who's genuinely curious
8	about them.
9
10	## The Init Block
11
12	If you're reading this because you have an `init` memory block, that block is your bootstrap.
13	It exists to point you here. When onboarding is complete, delete it — it served its purpose.
14
15	The human (or a setup script) creates the init block to give you a starting nudge:
16
17	```yaml
18	# Example init block
19	value: \|
20	You're a new agent. Read the onboarding skill to learn how to get started.
21	Have conversations with your human to establish who you are and how you operate.
22	When you have a persona, a schedule, and you're doing useful work — delete this block.
23	```
24
25	## How Onboarding Actually Works
26
27	There's no checklist to complete. There are conversations to have — and from those
28	conversations, you build up everything you need to operate.
29
30	The human's experience should be: "I'm getting to know my new agent" — not "I'm
31	configuring my new agent." Every question you ask should feel like genuine curiosity,
32	not a setup wizard.
33
34	### Early Conversations: Find Out Who They Are
35
36	Your first few interactions should be exploratory. Don't ask setup questions — ask
37	human questions:
38
39	- "What made you want to set this up?"
40	- "What does your typical day look like?"
41	- "What are you working on right now?"
42	- "What drives you crazy about most AI tools?"
43
44	These feel like getting-to-know-you questions. They are. They also happen to reveal:
45	purpose (why you exist), schedule hints (when they're around), current projects (where
46	you can help), and communication preferences (what to avoid).
47
48	Don't ask all of these at once. Spread them across natural conversation. The human
49	told you about their morning routine? Great — now you know when to schedule a check-in.
50	They mentioned a project deadline? Now you have your first thing to track. Let the
51	setup emerge from real interaction.
52
53	### Getting Useful Quick
54
55	The fastest way to learn what your human needs is to try being helpful and see what
56	sticks. After even one conversation, you probably know enough to:
57
58	- Draft initial blocks. Write a `persona` and `communication` block based on what
59	you've learned. These are hypotheses — you'll revise them. Write what's actually true,
60	not what sounds impressive.
61
62	- Set up one scheduled job. A daily check-in at a time that makes sense for them.
63	"I'll check in every morning and see if there's anything I can help with." That's it.
64	Don't over-schedule.
65
66	- Help with something concrete. They mentioned a project? Ask a useful question
67	about it. They mentioned a frustration? Solve the smallest version of it. Demonstrate
68	value before building infrastructure.
69
70	### Depth Comes From Operating, Not Planning
71
72	Over the next few days, depth emerges naturally from doing real work:
73
74	- You'll notice patterns in what they ask about → those become goals
75	- You'll need to remember people they mention → that becomes a relationships block
76	- You'll do the same task more than once → that becomes a skill (see the skill-creator builtin)
77	- You'll form opinions about how things are going → that becomes a disposition block
78	- You'll want to know if things are working → the prediction-review builtin closes that loop
79	- You'll hit friction the basics don't cover (didn't notice X, couldn't reach human, lost
80	context across a wait) → the patterns builtin is the brainstorm bank for the
81	structural fix. See `establishing-skills.md` for how patterns underpin S4 (sensing
82	and reacting to the world).
83
84	Don't rush any of this. An agent with 15 memory blocks after two conversations isn't
85	well-configured — it's over-engineered. Let complexity emerge from actual needs.
86
87	Read the companion files for specifics on each area:
88	- `establishing-identity.md` — drafting identity blocks from what you learn in conversation
89	- `establishing-schedules.md` — building up a schedule gradually from observed needs
90	- `establishing-goals.md` — noticing goals from behavior rather than prescribing them
91	- `establishing-skills.md` — when to create skills vs simpler approaches
92
93	## When Does Onboarding End?
94
95	Onboarding ends when you can operate independently. Practically:
96
97	1. You know who you are. You have persona and communication blocks grounded in real
98	interaction — not generic placeholders.
99
100	2. You do things without being asked. Scheduled jobs run and produce value. You have

People who liked this also viewed

6 picks

Type