Serena memory sync

Skill NDDev-it-com/rldyour-antigravity-cli/skills/serena-memory-sync

rldyour Antigravity CLI configuration: native extensions, GEMINI.md context, commands, skills, subagents, hooks, MCP, browser-provider routing, Serena memory, and runtime validation.

Install

npx -y skills add NDDev-it-com/rldyour-antigravity-cli --skill serena-memory-sync

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 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.

What its author says it does

Copied from the file, not written here

Синхронизируй fact-only Serena memories для Antigravity CLI adapter. EN: Serena memory sync.

SKILL.md

1.0 KB, as published. Nobody here has run it

Purpose

Keep .serena/memories synchronized with verified current facts.

Native Antigravity Boundary

Antigravity memories describe Antigravity CLI adapter files and runtime facts only.

When To Use

Use after adapter files, docs, validators, release metadata, or runtime baselines change.

Inputs

Changed files, current memories, and validation output.

Procedure

Update only durable facts.
Cite concrete file or upstream evidence.
Mark unverified facts NOT_PROVEN.
Run schema and semantic validators.

Evidence Required

Evidence bullet for every current fact claim.

Forbidden Actions

Do not store chat logs, speculation, secrets, tokens, or raw credentials.

Acceptance Checks

python3 scripts/validate_serena_memory_schema.py --strict and semantic validator.

Failure Reporting

List memory files needing more evidence or cleanup.

Gives 0 of the 12 instructions most memory context skills give

Counted across 674 of the 847 authors here whose files we hold, read 2026-08-06

inform the user when setup is completein 21 of 674, across 6 files
confirm the draft with the user before writingin 21 of 674, across 6 files
update the agent skills block in place if it existsin 21 of 674, across 6 files
present findings to the userin 20 of 674, across 5 files
write the three docs files from seed templatesin 20 of 674, across 5 files
ask the user about each decision one at a timein 19 of 674, across 4 files
edit CLAUDE.md if it existsin 18 of 674, across 3 files
explore current repo statein 18 of 674, across 3 files
do not overwrite user edits to surrounding sectionsin 18 of 674, across 3 files
back up the original file before overwritingin 16 of 674, across 8 files
keep the memory index under 200 linesin 15 of 674
Provide actionable steps and verificationin 13 of 674, across 2 files

Said here and by no other author read

cite concrete file or upstream evidence
run schema and semantic validators
include evidence for every fact claim
list memory files needing more evidence

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.