context-save
Skill4 starsChanged 4 months agoMITView on GitHub
Checkpoint the live working context to runtime/checkpoints/<ts>.snapshot.md — open threads, decisions pending, what we just did and what's next — so a future cold session resumes without re-deriving it all. Working memory, not canon — durable facts get routed through /capture first, never frozen into a snapshot. Trigger on "save context", "checkpoint", or before clearing / ending a long session. Pairs with /context-restore.
23 other projects use a version of this.
Adopted by
Most recently taken up by
- onblueroses/stratatheir own version, first seen Nov 12, 2026
- timurgaleev/vibestacktheir own version, first seen Nov 8, 2026
- trungtm78/ClaudeSkillstheir own version, first seen Oct 25, 2026
- thedigitalorganizer/soloshiptheir own version, first seen Oct 15, 2026
- ignavm1/claude-skillstheir own version, first seen Oct 13, 2026
- manastalukdar/ai-devstudiotheir own version, first seen Oct 13, 2026
Used with
Projects with it also use ios-clean, ios-fix and 6 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.
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 5 projects that use this
Saqlain-811Skillios-fix
Autonomous iOS bug fixer. (gstack)
Also in 5 projects that use this
timurgaleevSkilldocument-generate
Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.
Also in 7 projects that use this
bastosSkillios-design-review
Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".
Also in 5 projects that use this
johnlindquistSkilldiagram
Maintain and synchronize Unified Impact Diagrams following Diagram Driven Development (DDD) methodology. Create, update, and manage diagrams that connect user value to technical implementation.
Also in 4 projects that use this
SentrySkillspec
Produce a verified spec — problem, desired outcome, and acceptance criteria — before building. Use when given a GitHub/Linear issue link, when starting from a fuzzy in-conversation idea, or asked to "figure out what to do" / "scope this" / "what should I build" — whenever the *what* isn't yet pinned down. Grills the ambiguities, checks the premise against the code, and produces acceptance criteria you sign off on — then hands to design-first.
Also in 8 projects that use this
- +2 more from Saqlain-811
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 23
- garrytan/gstack★ 142ksame name
- timurgaleev/vibestack★ 8same name
- onblueroses/strata★ 3same name
- GTMify/claude-skills-starter★ 2same name
- HanksChen0110/skills★ 2same name
- chloropine/cgstack★ 1same name
- IyedBecheikh/bstack★ 1same name
- jpoindexter/theft-kit★ 1same name
- leishifu666/skills★ 1same name
- mahiunfiltered/claude-code-skills★ 1same name
13 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 repository16 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- agents-syncSkill
- call-agentSkill
- captureSkill
- context-restoreSkill
- curatorSkill
- learnSkill
- onboardSkill
- recallSkill
- reviewSkill
- skillifySkill
- wiki-doctorSkill
- worklog-audioSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
2
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
- Very specific: line 25
Before snapshotting, scan the session for anything that is actually a fact or a decision (not just "where we are").
- Distinctive: line 63
No secrets / keys / PII in a snapshot (blocklist).
- Very specific: line 64
Don't overwrite prior snapshots — each save is a new timestamped file.
- Distinctive: line 66
Keep it short. It is a resume aid, not a transcript.
“Common” is measured: kept by at least 6 in 10 of the 17 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
Inherits references/kernel.md (the provenance contract). Reads references/wiki-spec.md for schema.
What this is
A checkpoint of working memory — the volatile state of an in-flight session — so the
next session can resume cold. It is deliberately NOT the brain: a snapshot is ephemeral scaffolding,
not a sourced note. Anything in it that is a durable fact must go through /capture (into wiki/ with
provenance) before or alongside the save — otherwise that fact dies with the snapshot.
What goes in a snapshot (and what doesn't)
- IN: open threads, the current goal, decisions pending your approval, the next concrete action,
file paths in flight, and a pointer to the current
context/state.md. - NOT IN: any claim that belongs in
wiki/(capture it instead), secrets / keys / PII (seereferences/blocklist.md), or raw transcript dumps.
Execution
1 — Sweep durable facts out first
Before snapshotting, scan the session for anything that is actually a fact or a decision (not just
"where we are"). Route those through /capture or /review so they land in wiki/ / decisions/log.md
with provenance. The snapshot is for the remainder — the volatile thread state.
2 — Write the snapshot
Timestamp ts=$(date +%Y-%m-%dT%H-%M-%S). Write runtime/checkpoints/<ts>.snapshot.md:
---
kind: checkpoint
created: <date-time>
state_ref: context/state.md @ <date> # what state.md said at save time
origin: agent-generated
---
# Where we are
<2–4 lines: the goal and how far we got>
# Open threads
- [ ] <thread> — <next action> — <files/paths>
# Decisions pending
- <decision awaiting your call> — <why it's blocked>
# Next action
<the single first thing to do on resume>
# Pointers
- state: context/state.md digests: digests/ index: INDEX.md
- related notes: [[id]], [[id]]3 — Confirm
Print the snapshot path and a one-line summary. Note that snapshots are local and ephemeral (gitignored): they are an aid to resume, not a record to cite.
Guardrails (hard)
- A snapshot is NOT a source. Never cite a snapshot in a
srcblock, and never let one substitute for capturing a fact intowiki/. - No secrets / keys / PII in a snapshot (blocklist).
- Don't overwrite prior snapshots — each save is a new timestamped file;
/context-restorepicks the latest by default. - Keep it short. It is a resume aid, not a transcript.
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.

