migrate
Skill0 starsChanged 5 months agoMITView on GitHub
Use when manually triggering or re-triggering Local → Memex migration for the current Atelier project — bypasses the .ai/atelier.local-only opt-out marker and retries on prior failure.
63 other projects use a version of this.
Adopted by
Most recently taken up by
- tuist/agent-plugintheir own version, first seen Nov 8, 2026
- dsifry/metaswarmtheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 2026
- jwm-axoni/claude-workbenchtheir own version, first seen Nov 8, 2026
- AsiaOstrich/EngramGraphtheir own version, first seen Nov 8, 2026
- DawnEver/claude-code-configtheir own version, first seen Nov 6, 2026
Used with
Projects with it also use incident, sdd and 10 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.
JkudjoSkillincident
Production incident response — structured triage, hypothesis tree, safe remediation, incident record
Also in 4 projects that use this
liatrio-labsSkillsdd
Execute the Liatrio Spec-Driven Development (SDD) workflow when explicitly invoked by the user. NOTE: this skill is NOT intended to be dynamically loaded or automatically triggered; it should only ever be explicitly called by the user.
Also in 4 projects that use this
BerryKuipersSkillscaffold
Detect project stack, apply architecture patterns, wire quality gates, and scaffold features. Use when bootstrapping a project, adding a vertical slice, wiring CI/CD, adding Docker compose, or setting up quality gates.
Also in 4 projects that use this
MicrosoftSkillinit
Also in 8 projects that use this
agenticnotetakingSkillupgrade
Apply plugin knowledge base updates to an existing generated system. Consults the Ars Contexta research graph for methodology improvements, proposes skill upgrades with research justification. Never auto-implements. Triggers on "/upgrade", "upgrade skills", "check for improvements", "update methodology".
Also in 3 projects that use this
genomewalkerSkillcheckpoint
Save a checkpoint of task status, decisions, active files, and next steps
Also in 5 projects that use this
Other versions63 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 63
- garrytan/gbrain★ 32ksame name
- tuist/tuist★ 5.9ksame name
- parcadei/Continuous-Claude★ 3.9ksame name
- parcadei/Continuous-Claude-v2★ 3.9ksame name
- parcadei/Continuous-Claude-v3★ 3.9ksame name
- codewithmukesh/dotnet-claude-kit★ 808same name
- dsifry/metaswarm★ 426same name
- pipecat-ai/gradient-bang★ 420same name
- govctl-org/govctl★ 276same name
- AsiaOstrich/universal-dev-standards★ 84same name
53 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
7 rules. 0 are common, 0 are distinctive, and 7 are very specific to this project.
0
Common
Most of the 50 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
7
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 26
Verify mode: Run from scripts.mode_detector import detect_mode.
- Very specific: line 31
Clear opt-out marker if present: If .ai/atelier.local-only exists, delete it.
- Very specific: line 35
Verify there's something to migrate: If .ai/atelier.db doesn't exist, surface: "No local atelier database in this project.
- Very specific: line 39
Run the internal migration procedure: Read internal/migrate-local-to-memex/SKILL.md and follow it inline.
- Very specific: line 50
Settings recommendation (after pre-flight): If a startup_check() on this session returned a settings_rec_offer with eligible=True and …
- Very specific: line 68
Never proceed if detect_mode() != "memex".
- Very specific: line 70
Never skip the internal procedure — call into internal/migrate-local-to-memex/SKILL.md directly so all replay logic, source_ref checks, and …
“Common” is measured: kept by at least 6 in 10 of the 50 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
migrate
Manual trigger for the Local → Memex migration documented in spec §8 and
implemented in internal/migrate-local-to-memex/SKILL.md. The same
migration logic auto-prompts at the top of /atelier:{load,save,ingest,run}
when both a project-local .ai/atelier.db and Memex are present and no
marker has been written. This skill is the manual path for the
exception cases.
When to use
- You previously answered
nto the auto-prompt and now want to migrate. (Auto-prompt won't fire again because.ai/atelier.local-onlyis set.) - A prior migration failed partway through. You've resolved the cause (disk full, Memex bootstrap issue, etc.) and want to resume.
- You're scripting bulk migration across many projects: invoke
/atelier:migratefrom each project root rather than waiting for the auto-prompt at next session-open.
Procedure
- Verify mode. Run
from scripts.mode_detector import detect_mode; detect_mode(). If it returns"local", surface to user: "Memex is not installed (or not bootstrapped). Runmemex:runonce first, then re-invoke/atelier:migrate." Stop. - Clear opt-out marker if present. If
.ai/atelier.local-onlyexists, delete it. (Whether the user explicitly opt-out is no longer relevant — they're explicitly opting back in now.) - Verify there's something to migrate. If
.ai/atelier.dbdoesn't exist, surface: "No local atelier database in this project. Nothing to migrate." Stop. - Run the internal migration procedure. Read
internal/migrate-local-to-memex/SKILL.mdand follow it inline. The procedure is idempotent — rows already replayed (detected viasource_reflookup in memex's Index, per Plan 4 Task 1) are skipped and counted underalready_present. Surface the summary to the user. - On success, the procedure writes
.ai/atelier.migratedwith the timestamp + row counts. On failure, the local DB is untouched and no marker is written; the user can fix the underlying issue and re-run this skill. - Settings recommendation (after pre-flight). If a
startup_check()on this session returned asettings_rec_offerwitheligible=Trueand non-emptychanges, readinternal/settings-recommendation/SKILL.mdand follow its prompt protocol before returning control to the user. After the user's choice, continue. (Mode-agnostic; the procedure file is the single source of truth for the prompt text — do not inline it here.)
Differences from the auto-prompt path
| Aspect | Auto-prompt (Task 2) | /atelier:migrate (this skill) |
| When triggered | Top of any other skill, on first session-open after Memex appears | User-invoked explicitly |
Respects .ai/atelier.local-only | Yes — won't fire if marker present | No — clears the marker |
Respects .ai/atelier.migrated | Yes — won't fire if marker present | Same — but the internal procedure detects already-migrated rows via source_ref and counts them rather than re-writing |
| Required answer | y/N from user | None — invocation IS the consent |
Hard rules
- Never proceed if
detect_mode() != "memex". Atelier cannot migrate TO a target that doesn't exist. - Never skip the internal procedure — call into
internal/migrate-local-to-memex/SKILL.mddirectly so all replay logic, source_ref checks, and crash-safety guarantees are honored. - Surface the row-count summary to the user before stopping. Do not swallow the migration's output.
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.

