human-cognition-cache SKILL.md skillA
human-cognition-cache from pengqianhan/ai-human-research-os is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pengqianhan/ai-human-research-os/human-cognition-cache@git:20260723.0222ad0Pins git:20260723.0222ad0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pengqianhan/ai-human-research-os
- Path
research-skills-hub/open-paper-skills/human-cognition-cache/SKILL.md- Versions recorded
- 2
- Latest version
- git:20260723.0222ad0, committed Jul 23, 2026
- First version recorded
- Jul 15, 2026
- Size
- 10,679 bytes
- Repository stars
- 3
- License
- MIT
Scaffold human cognition with a project-local, git-trackable four-quadrant cache. Use when (1) initializing, reading, updating, or migrating the cache; (2) completing a task beyond the human's confirmed understanding, where cognition should guide agent autonomy and decision escalation; (3) explaining a verified artifact at the human's level and recording evidence-backed cognitive growth; or (4) finishing any substantive task, where the conversation revealed durable cognition that should be…
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Human Cognition Cache Use the human's current cognition as a **scaffold**, not a ceiling. Help the human complete tasks beyond their present knowledge, preserve human authority over goals and consequential choices, and turn verified delivery into durable understanding when the task calls for it. ## Contract Scope: - Model the human's cognition in this project: what they can state, know they do not know, reveal through judgment, or may not yet realize. - Use that model to choose when to act, ask, explain, or teach. - Keep project facts and agent knowledge in their own project artifacts. Inputs: - The current request, conversation, and verified task artifacts. - The relevant entries in the project-local cognition cache. - Human corrections to entries the agent recorded on its own. Outputs: - A maintained Markdown cognition cache with indexed, evidence-labelled entries. - For cognition-aware tasks, an explicit allocation of agent-owned work and human-owned decisions. - When understanding matters, an artifact-grounded cognitive handoff and any evidence-backed cognition transitions. Limitations: - The cache is an open-world, fallible model. Missing entries mean …
Read the whole file at its exact version.
How to install
mdr add pengqianhan/ai-human-research-os/human-cognition-cache@sha256:3c3dfd06e71a8aafThe line at the top of this page pins the label git:20260723.0222ad0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_acgd2bnchxjpmwf3)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 2 versions of this file, between Jul 15, 2026 and Jul 23, 2026, about one every 9 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260723.0222ad0 latest | 2026-07-23 | 0222ad0 | 10,679 B | A | view · diff |
| git:20260715.38d79be | 2026-07-15 | 38d79be | 7,309 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (10679 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
pengqianhan/ai-human-research-os · 3 stars · license MIT · pushed 2026-10-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_acgd2bnchxjpmwf3 GET https://markdownregistry.com/api/v1/resolve?ref=pengqianhan/ai-human-research-os/human-cognition-cache GET https://markdownregistry.com/api/v1/blob/3c3dfd06e71a8aaf6bcc4fff2b175caa7d37ad391730ebb4b507ebc43ae4ecab
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.