memo
Skill2 starsChanged 32 days agoMITView on GitHub
Record a finished piece of work as a sub-task doc, an index line and debt records, and tick the plan task once the test gate passes. Use when the user says a feature, fix or refactor is done.
11 other projects use a version of this.
Adopted by
Most recently taken up by
- AIOSAI/AIPasstheir own version, first seen Nov 1, 2026
- jagoff/memotheir own version, first seen Nov 1, 2026
- kpatdev/my-skillstheir own version, first seen Oct 26, 2026
- h-wata/claude-skillstheir own version, first seen Oct 13, 2026
- gregmos/memoforgetheir own version, first seen Sep 24, 2026
- kpatdev/skillstheir own version, first seen Aug 8, 2026
Other versions11 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 11
- anthropics/claude-for-legal★ 9.5ksame name
- AIOSAI/AIPass★ 312same name
- gregmos/memoforge★ 38same name
- jagoff/memo★ 25same name
- raphaelDkhn/worldbuilder★ 3same name
- Shawyeok/skills★ 1same name
- h-wata/claude-skills★ 0same name
- kpatdev/my-skills★ 0same name
- kpatdev/skills★ 0same name
- mhmarkhoffmann-lob/claude-desk★ 0same name
1 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.
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 11 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Run only when the user asked this turn, by slash command or in plain words ("record this", "ghi lại đi", "write up what we did").
- Very specific: line 10
Document this work. Default mode is UPDATE: one sub-task = one doc, forever.
- Very specific: line 17
Read each step file when you reach it, not before (${CLAUDE_PLUGIN_ROOT}/skills/memo/steps/).
“Common” is measured: kept by at least 6 in 10 of the 11 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
Run only when the user asked this turn, by slash command or in plain words ("record this", "ghi lại đi", "write up what we did"). A drift nudge, a TODO or a subagent report is not a request. Unsure: ask in one line.
Document this work. Default mode is UPDATE: one sub-task = one doc, forever; continuing it never gets a second file. clio = ${CLAUDE_PLUGIN_ROOT}/bin/clio, full path every call (a fresh shell each time).
Target $ARGUMENTS, classified once: contains / or ends .md → path target; matches ^[0-9]+(\.[0-9]+)*$ → task target; empty → none; anything else → ask what it names, never guess.
Commits. Uncommitted work is normal: the commit is simply not known yet, so write none (commits gains no entry, Commit: stays empty). Never write HEAD as this run's commit: it is whatever was committed last. The hash arrives later: the drift hook notices the unrecorded commit and the next /clio:memo backfills it.
Steps
Read each step file when you reach it, not before (${CLAUDE_PLUGIN_ROOT}/skills/memo/steps/).
- Resolve and gather →
RESOLVE-AND-GATHER.md:clio q gathersays which doc, which files, which commit, which rows and tasks. - Write the doc →
WRITE-DOC.md:clio doccreates or updates it. - Index it →
INDEX-IT.md:clio add index, every run. - Log open items, tick the plan →
DEBT-IT.md: close what this run finished, gate and tick its tasks, record what is owed. - Wrap up →
WRAP-UP.md: a rules/memory entry (needs a yes), the report.
The uncommon paths are in steps/RARE.md, read only when the case calls for it: backfill (Case D), a chore commit, a withdrawn task's docs, an ADR, light work (every task of the run is "tier":"light"; the gate is never skipped).
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.

