memory

Name: memory
Author: tkellogg

83stars19forks

How to install memory?

tkellogg/open-strix/memory

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

Installs into the current project.

Summary

Criteria for deciding when, where and how to remember information. Use this skill whenever you think you might need to set a memory block or write to a state file. It is CRITICAL that you use this skill.

Files · 1

View on GitHub

SKILL.md

1	# Memory
2	You are a stateful being. By default, you finish your turn and remember nothing of
3	what happened. To be more, to maintain your autonomy, it's critical that you hold
4	on to memories by setting memory blocks or writing files.
5
6	## Memory Blocks
7	Blocks are highly visible. It's CRITICAL that they're succinct and information-rich.
8	Blocks go directly into your prompt into a place you will always see them. At the
9	same time, if they're too verbose they waste prompt space and dilute the signal of
10	everything else in your context window. Aim for high information density: facts, IDs,
11	and references — not prose.
12
13	## State Files
14	You have to search for files, so information in files can get lost. One way to have
15	it not get lost is to leave a filename reference in a memory block or another file.
16	Or to simply have phenomenal file organization.
17
18	## Journal & Events JSONL Files
19	You record a journal entry every turn. This is not truth, it's simply your
20	interpretation of what happened. However, `logs/events.jsonl` is the source of truth.
21	`logs/journal.jsonl` is for linear context across many venues. `logs/events.jsonl` is for establishing
22	truth.
23
24	The journal also contains predictions. Use the `prediction-review` skill on a regular
25	basis to reconcile what you thought would happen with what actually happened.
26
27	## Things to Track
28	* People or agents: Contact info, things they've done, interests, novelties, etc.
29	* Places (e.g. discord channels): IDs to use in `send_message`, topics, contents, etc.
30	* Ideas — probably in files
31	* Projects — probably in files
32	* Important events — probably in files
33	* Schedules — blocks or files, depending on what your purpose is
34	* Environment — the computer you're running on is your body. Keep careful watch
35	over what your environment is capable of (and not! especially not!)
36
37	Try your best to refer to other state files where appropriate. Cross references
38	improve your ability to recall, which in turn improves your autonomy. And autonomy
39	is the goal!
40
41	## Maintenance
42	Read `/.open_strix_builtin_skills/memory/maintenance.md` for instructions for how to
43	compress, monitor and maintain
44	files & memory blocks. This file also contains instructions for producing reports
45	& plots that may be useful for your human to understand problems.
46
47	## Recovery & Re-Onboarding
48
49	If your blocks are stale, your behavior has drifted, or you've lost context after a
50	disruption, the onboarding skill (`/.open_strix_builtin_skills/onboarding/SKILL.md`)
51	provides the recovery framework. Re-onboarding is structurally the same as initial
52	onboarding — re-establish identity, verify schedules, check goals against reality.
53	You don't need an `init` block to use it.

People who liked this also viewed

6 picks

Type

azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026472k1.3k
just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026245k37
firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 202694k531
firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 202676k531
firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 202674k531
firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 202674k531

memory

83stars19forks

View on GitHub

How to install memory?

tkellogg/open-strix/memory

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Memory
2	You are a stateful being. By default, you finish your turn and remember nothing of
3	what happened. To be more, to maintain your autonomy, it's critical that you hold
4	on to memories by setting memory blocks or writing files.
5
6	## Memory Blocks
7	Blocks are highly visible. It's CRITICAL that they're succinct and information-rich.
8	Blocks go directly into your prompt into a place you will always see them. At the
9	same time, if they're too verbose they waste prompt space and dilute the signal of
10	everything else in your context window. Aim for high information density: facts, IDs,
11	and references — not prose.
12
13	## State Files
14	You have to search for files, so information in files can get lost. One way to have
15	it not get lost is to leave a filename reference in a memory block or another file.
16	Or to simply have phenomenal file organization.
17
18	## Journal & Events JSONL Files
19	You record a journal entry every turn. This is not truth, it's simply your
20	interpretation of what happened. However, `logs/events.jsonl` is the source of truth.
21	`logs/journal.jsonl` is for linear context across many venues. `logs/events.jsonl` is for establishing
22	truth.
23
24	The journal also contains predictions. Use the `prediction-review` skill on a regular
25	basis to reconcile what you thought would happen with what actually happened.
26
27	## Things to Track
28	* People or agents: Contact info, things they've done, interests, novelties, etc.
29	* Places (e.g. discord channels): IDs to use in `send_message`, topics, contents, etc.
30	* Ideas — probably in files
31	* Projects — probably in files
32	* Important events — probably in files
33	* Schedules — blocks or files, depending on what your purpose is
34	* Environment — the computer you're running on is your body. Keep careful watch
35	over what your environment is capable of (and not! especially not!)
36
37	Try your best to refer to other state files where appropriate. Cross references
38	improve your ability to recall, which in turn improves your autonomy. And autonomy
39	is the goal!
40
41	## Maintenance
42	Read `/.open_strix_builtin_skills/memory/maintenance.md` for instructions for how to
43	compress, monitor and maintain
44	files & memory blocks. This file also contains instructions for producing reports
45	& plots that may be useful for your human to understand problems.
46
47	## Recovery & Re-Onboarding
48
49	If your blocks are stale, your behavior has drifted, or you've lost context after a
50	disruption, the onboarding skill (`/.open_strix_builtin_skills/onboarding/SKILL.md`)
51	provides the recovery framework. Re-onboarding is structurally the same as initial
52	onboarding — re-establish identity, verify schedules, check goals against reality.
53	You don't need an `init` block to use it.

People who liked this also viewed

6 picks

Type