Memory
Record a decision, lesson, tool note, or any project knowledge mid-session.From its SKILL.md
npx -y skills add torarnv/claude-project-manager --skill memoryAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.8 KB, 425 tokens by cl100k_base, as published. Nobody here has run it
Memory Skill
Ad-hoc project memory management. Use to record something mid-session without
running a full /end.
Trigger phrases: "remember this", "note that", "record a decision", /cpr:memory.
Memory file semantics
| Content type | File |
|---|---|
| Architectural or design decision | decisions.md |
| Workflow friction or process lesson | lessons.md |
| CLI syntax, missing tool, flag trap, argument quirk | tools.md |
| Update to project goal or scope | spec.md |
| New phase, task, or open question | plan.md |
| Current state update | status.md |
Workflow
Step 1: Identify the target file
Determine where the content belongs using the table above. If ambiguous, ask the user which file is appropriate.
Step 2: Check workspace scope (workspace mode only)
If .memory/tasks/ exists, this is a workspace. Determine whether the content is:
- Cross-task — relevant to future tasks in general → write to root-level file
- Task-specific — relevant only to the current task → write to the task file or task directory
If unclear, ask the user.
Step 3: Write the content
Append to the appropriate file. If the file doesn't exist, create it with frontmatter:
---
name: {{Name}}
description: {{one-liner for MEMORY.md index}}
type: {{decisions|lessons|tools|spec|plan|status}}
---
For lessons.md, include this note at the top if creating for the first time:
_For tool-specific knowledge (CLI syntax, missing tools, flag traps), see [tools.md](tools.md)._
Step 4: Sync index
If a new file was created, add it to .memory/MEMORY.md with a one-line entry:
- [Title](file.md) — one-liner description
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most memory context skills give in 425 tokens
Counted across 754 of the 1,056 authors here whose files we hold, read 2026-09-06
- Preserve existing content structurein 15 of 754, across 9 files
- Front-load the leading wordin 14 of 754, across 10 files
- Update existing entries instead of duplicatingin 14 of 754, across 7 files
- Keep CLAUDE.md under one hundred linesin 14 of 754, across 12 files
- Read CLAUDE.md at the project rootin 14 of 754
- Keep each meaning in a single source of truthin 12 of 754, across 8 files
- Redact sensitive information before committingin 11 of 754, across 4 files
- Scan for all CLAUDE.md filesin 11 of 754, across 7 files
- Use frontmatter for metadata on filesin 10 of 754, across 3 files
- Repeat user interactions 10 timesin 10 of 754, across 4 files
- Write the CLAUDE.md file into the target folderin 10 of 754, across 8 files
- Use memlab to process snapshotsin 9 of 754, across 3 files
Said here and by no other author read
- Identify the target file using the table
- Ask the user if file choice is ambiguous
- Determine workspace scope if workspace exists
- Append content to the appropriate file
- Create file with frontmatter if missing
- Sync index if a new file was created
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.