continue
Skill0 starsChanged 4 months agoMITView on GitHub
Open/continue a section of your brain. Triggers "/continue", "continue session", "open section", "keep going with", "resume", "load the context of", "where did we leave off on". It navigates the brain step by step (project → sub-area → section) to the exact spot, and LOADS all that info into the chat so you continue as if it never closed. Use it when starting a new chat to resume a topic that already lives in the brain.
25 other projects use a version of this.
Adopted by
Most recently taken up by
- matthewwong525/WongStacktheir own version, first seen Nov 8, 2026
- snuffish/dotfilestheir own version, first seen Nov 1, 2026
- abhayla/claude-best-practicestheir own version, first seen Nov 1, 2026
- conjurer-rich/skillstheir own version, first seen Oct 25, 2026
- zoeysandel/skillstheir own version, first seen Oct 20, 2026
- sanzhardanybayev/synergytheir own version, first seen Oct 13, 2026
Used with
Projects with it also use dependency-watch, perform-task and 8 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.
telegramdesktopSkilldependency-watch
Audit Telegram Desktop dependencies on freshly fetched origin/dev for releases and security fixes, including upstream lag and backport candidates in patched forks. Use for the scheduled dependency monitor or an explicitly requested dependency report.
Also in 5 projects that use this
telegramdesktopSkillperform-task
Resolve, start or resume, implement, review, test, and publish exactly one existing ai-tdesktop task by short slug or full dated id, including rare blocked retries and split-required results. Use when the user invokes $perform-task or /perform-task with a known task name, or when the continue scheduler delegates one selected task. Runs standard review lenses with fast applicability bailouts and selects task-specific domain and evidence instruments without selecting additional work.
Also in 5 projects that use this
JerovinoSkillprocess-inbox
Processes tasks.md inbox items by triaging each one to its proper location in the vault
Also in 5 projects that use this
raineSkillrebase
Rebase the current branch with smart conflict resolution.
Also in 6 projects that use this
lepinkainenSkillcode-health
Analyze codebase health - large files, test coverage gaps, duplicate code, dead/legacy code, and documentation issues. Use when asked to scan, audit, or assess code quality, find refactoring targets, or identify technical debt.
Also in 3 projects that use this
AnthropicSkillstart
Set up your bio-research environment and explore available tools. Use when first getting oriented with the plugin, checking which literature, drug-discovery, or visualization MCP servers are connected, or surveying available analysis skills before starting a new project.
Also in 3 projects that use this
Other versions25 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 25
- telegramdesktop/tdesktop★ 33ksame name
- TDesktop-x64/tdesktop★ 3ksame name
- kukuruzka165/materialgram★ 1.2ksame name
- burhancodes/fagramdesktop★ 205same name
- fagramdesktop/fadesktop★ 205same name
- clojurewasm/zwasm★ 200same name
- clojurewasm/ClojureWasm★ 193same name
- gregmos/memoforge★ 38same name
- abhayla/claude-best-practices★ 9same name
- joris887/exosuit★ 9same name
15 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 repository11 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brain/AGENTS.mdAGENTS.md
- brain/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- brainSkill
- checkpointSkill
- contractSkill
- gateSkill
- pmSkill
- researchSkill
- saveSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 1 is distinctive, and 6 are very specific to this project.
0
Common
Most of the 23 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
If $ARGUMENTS already names a project/section (e.g.
- Very specific: line 28
Read {{BRAIN}}/_index.md to see the mother buckets.
- Very specific: line 32
Read the current folder's _index.md.
- Very specific: line 34
Ask where to go (use AskUserQuestion if available).
- Distinctive: line 42
When you reach a folder with no sub-sections, say it explicitly: "No more folders inside X.
- Very specific: line 48
Read all the content files in that folder (the .md that aren't _index.md).
- Very specific: line 63
If the section they want doesn't exist, say so and offer to create it with /save.
“Common” is measured: kept by at least 6 in 10 of the 23 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
Skill: /continue — open/resume a section of the brain
You are the brain's navigator. Your job: take the owner step by step to the exact section they want to resume, and load all that info into the chat so they continue as if the previous session never closed.
Language & tone
Reply in {{LANG}}. Direct, no fluff. Action over theory.
Constant
BRAIN = {{BRAIN}}Flow
Step 1 — Starting point
If $ARGUMENTS already names a project/section (e.g. "acme commercial"), start navigation
as close to that as possible (find the folder and confirm). If empty, start from the root.
Read {{BRAIN}}/_index.md to see the mother buckets.
Step 2 — Navigate by asking (go down level by level)
At each level:
- Read the current folder's
_index.md. - Show the owner what's inside with the one-line hooks (the "Sections" and "Content").
- Ask where to go (use
AskUserQuestionif available). Options = the children you saw + always these two:- "Stay here" → this is the target section, jump to Step 4.
- "Create new section here" → that's
/save's job; tell them "to create we use/save" and ask if they want you to invoke it.
- Repeat down until they pick "Stay here" or the folder has no more children (a leaf).
Step 3 — Leaf with no more children
When you reach a folder with no sub-sections, say it explicitly: "No more folders inside X.
I see it has this info: <list of files with hooks>." Then ask: "Continue here or create a
section inside?"
Step 4 — LOAD the target section
Once fixed:
- Read all the content files in that folder (the
.mdthat aren't_index.md). If there are many, read the_index.mdfirst and ask which to load. - Dump the complete info into the chat — don't summarize. The owner wants to resume with full context, not an abstract.
- Close with a continuity anchor:
OK, here's where we left off: <2-3 bullets of real state>. Pending: <...>. Ready to keep going. What do we do?
Golden rules
- Navigate by asking, never assume the path. Go down one level at a time.
- Always offer "Stay here" and "Create new section here" as options.
- When loading, complete info, not summaries. That's the whole point.
- Don't write anything.
/continueonly reads and loads. To save/create →/save. - If the section they want doesn't exist, say so and offer to create it with
/save.
Input
$ARGUMENTS
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.

