park
Skill13 starsChanged 11 days agoMITView on GitHub
Park an idea, task or question for later — set it aside with its context, don't lose the thought.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- jskswamy/skillstheir own version, first seen Nov 8, 2026
- anotherben/claude-harnesstheir own version, first seen Nov 8, 2026
- Fanar-labs/just-continuetheir own version, first seen Nov 1, 2026
- robritacca-dotcom/rift-dstheir own version, first seen Nov 1, 2026
- robritacca-dotcom/design-systemtheir own version, first seen Oct 28, 2026
- House945/skillstheir own version, first seen Oct 15, 2026
Used with
Projects with it also use checkpoint.
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.
genomewalkerSkillcheckpoint
Save a checkpoint of task status, decisions, active files, and next steps
Also in 3 projects that use this
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- redis/docs★ 86same name
- robritacca-dotcom/rift-ds★ 9same name
- anotherben/claude-harness★ 7same name
- jskswamy/skills★ 3same name
- stonegiantstudio/skills★ 3same name
- mattpollak/relay★ 2same name
- corygabrielsen/skills★ 1same name
- House945/skills★ 1same name
- robritacca-dotcom/design-system★ 1same name
- braincandy-parallel/tamarindos-workflow-kit★ 0same name
2 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 repository9 other files it gives its agents.
- docs-reflectSkill
- memory-setupSkill
- memorySkill
- reflectSkill
- session-continueSkill
- session-endSkill
- session-insightsSkill
- session-restoreSkill
- session-startSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
4
Distinctive
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 25
If unclear — ask the user briefly.
- Distinctive: line 93
Do not close the session — the user continues working
- Distinctive: line 94
Do not duplicate — if it is already in the backlog or memory, point out where
- Distinctive: line 97
If the user did not provide an argument — suggest the last discussed topic
“Common” is measured: kept by at least 6 in 10 of the 12 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
/park — Set something aside
Parked is a state, not a kind of content: an idea, a task, a question put aside with its context to come back to. Does not close the session — only captures the thought. Unlike an ideas catalog, a parked item has to end: picked up, moved on, or dropped (see Step 5).
Step 1: Determine what to park
From the argument or from the context of recent messages, determine:
- What — the essence (1-2 sentences)
- Kind — idea, task or question
- Why — what problem it solves or why it matters
- Workstream — which workstream it belongs to (from
workstreams.json), or none - Context — key details from the current conversation that would be lost without recording
- Next step — what to do when coming back
If unclear — ask the user briefly.
Step 2: Choose the form
- Item (default) — one file per item, so Claude Code's recall can bring it back by its description when the topic returns. Save the draft to /tmp/park.md:
---
name: {short title}
description: {one line — what it is and when it matters}
type: project
---
## What
{essence}
## Why
{problem it solves}
## Context
{key details from the conversation}
## Next step
{what to do when you come back to this}- Quick line — when the thought is raw and stopping to structure it costs more than it's worth:
node "${CLAUDE_PLUGIN_ROOT}/scripts/memory.js" note "PARKED: {essence}"Step 3: Propose & confirm
MUST show the user what will be saved and where BEFORE writing anything:
Park this?
What: {essence}
Kind: {idea | task | question}
Workstream: {name, or none}
Save? (yes/skip)Wait for explicit confirmation. Do NOT write until the user confirms.
Step 4: Write
node "${CLAUDE_PLUGIN_ROOT}/scripts/memory.js" park --title="{short title}" --kind={kind} --workstream={name} --content=/tmp/park.mdOmit --workstream when the item belongs to none: it goes to parked/. Within a workstream it goes to workstreams/{name}/. The command stamps category: parked and the date and never overwrites. Show its output as the receipt.
Step 5: The exit
A parked item is done when it was picked up, moved to the backlog, a decision or an ideas catalog, or dropped. Then remove it and record where it went:
node "${CLAUDE_PLUGIN_ROOT}/scripts/memory.js" parked [<workstream>] # what is parked, oldest flagged
node "${CLAUDE_PLUGIN_ROOT}/scripts/memory.js" unpark <file> --to={picked-up|backlog|decision|ideas|drop}Move the content first if it goes somewhere; unpark only removes the item and notes the exit.
Rules
- Do not close the session — the user continues working
- Do not duplicate — if it is already in the backlog or memory, point out where
- Context from the conversation matters more than wording — better to record it raw than to lose it
- One park = one item. If there are several — offer to park them one by one
- If the user did not provide an argument — suggest the last discussed topic
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.

