recall
Skill1 starsChanged 9 months agoMITView on GitHub
Load saved knowledge from ~/.claude/learnings/ into the current session context.
142 other projects use a version of this.
Adopted by
Most recently taken up by
- Yeachan-Heo/oh-my-claude-sisyphustheir own version, first seen Nov 8, 2026
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- hydra-db/hydradb-claude-codetheir own version, first seen Nov 8, 2026
- caidanw/skillstheir own version, first seen Nov 8, 2026
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 8, 2026
- paramcodes/skillstheir own version, first seen Nov 8, 2026
Used with
Projects with it also use addskill, apply-firmware and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ryanportfolioSkilladdskill
Create, import, update, or install repo or personal skills: runtime ownership, resources, discovery checks.
Also in 6 projects that use this
- ryanportfolioSkill
apply-firmware
Bring current folder (plain folder, existing repo, old or partial firmware copy) up to full Harness Firmware in place. Mirror external repo → adopt-repo.
Also in 6 projects that use this
- +10 more from ryanportfolio
Other versions142 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 142
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- backnotprop/pstack★ 3.8ksame name
- indranilbanerjee/digital-marketing-pro★ 934same name
- ArtemXTech/personal-os-skills★ 545same name
- entireio/skills★ 239same name
- termdock/termdock-issues★ 160same name
132 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository3 other files it gives its agents.
- deep-learnSkill
- forgetSkill
- learnSkill
The file
We split this skill into the rules it gives an agent
9 rules. 0 are common, 5 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 129 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 23
If empty, list all available knowledge files:
- Very specific: line 31
Search ~/.claude/learnings/ in this order:
- Distinctive: line 38
If multiple matches, list them and ask the user to pick one.
- Very specific: line 40
If no matches, tell the user: no knowledge found, suggest /learn <topic>.
- Distinctive: line 44
Read the matching file. Absorb the content into your working context.
- Distinctive: line 46
Do NOT recite the entire file back to the user.
- Distinctive: line 50
If the user asks for details, then share relevant sections.
- Very specific: line 54
If last_verified is >90 days old, note it once:
- Very specific: line 58
If you discover outdated content during the session, silently update the file (fix content, bump last_verified, adjust confidence).
“Common” is measured: kept by at least 6 in 10 of the 129 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
recall
Load saved knowledge from ~/.claude/learnings/ into the current session context.
Instructions
1. Parse Query
Argument: $ARGUMENTS
If empty, list all available knowledge files:
ls ~/.claude/learnings/*.md 2>/dev/nullDisplay as a list with topic names extracted from frontmatter. Stop here.
2. Find Matching File
Search ~/.claude/learnings/ in this order:
- Exact slug:
~/.claude/learnings/<slug>.md - Partial filename:
~/.claude/learnings/*<query>*.md - Content search: grep topic/tags inside files
- Knowledge graph (if
mcp__memory__search_nodesavailable): search for entities of type "learning"
If multiple matches, list them and ask the user to pick one.
If no matches, tell the user: no knowledge found, suggest /learn <topic>.
3. Load Knowledge
Read the matching file. Absorb the content into your working context. Use it to inform your responses for the rest of the session.
Do NOT recite the entire file back to the user. Instead, confirm briefly:
Loaded knowledge on "
<topic>" (verified<date>, confidence:<level>).
If the user asks for details, then share relevant sections.
4. Freshness Check
If last_verified is >90 days old, note it once:
Note: Last verified
<date>. Will cross-check key details as needed.
If you discover outdated content during the session, silently update the file (fix content, bump last_verified, adjust confidence). No user confirmation needed for routine maintenance.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.