meta-synthesize-locals
Skill0 starsChanged 47 days agoMITView on GitHub
Synthesizes verbose SKILL.local.md files after migration from the old single-file pattern. For each skill that has a SKILL.local.md that looks like a full copy of SKILL.md, reads both files and rewrites SKILL.local.md to contain only the user's actual customizations (rules, overrides, additions). Triggered by: "synthesize skills", "sync local overrides", "clean up local files", "/synthesize-skills".
In this repository96 other files it gives its agents.
- AGENTS.mdAGENTS.md
- team_context/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- fin-company-cfoSkill
- fin-invoice-reconciliationSkill
- fin-month-end-reportingSkill
- fin-personal-cfoSkill
- meta-find-skillsSkill
- meta-memory-recallSkill
- meta-memory-writeSkill
- meta-skill-creatorSkill
- meta-skillifySkill
- meta-toolifySkill
- meta-wrap-upSkill
- mkt-ab-testingSkill
- mkt-ad-creativeSkill
- mkt-adsSkill
- mkt-asoSkill
- mkt-brand-voiceSkill
- mkt-churn-preventionSkill
- mkt-cold-emailSkill
- mkt-co-marketingSkill
- mkt-community-marketingSkill
- mkt-content-repurposingSkill
- mkt-copy-editingSkill
- mkt-copywritingSkill
- mkt-croSkill
- mkt-directory-submissionsSkill
- mkt-emailsSkill
- mkt-eventsSkill
- mkt-free-toolsSkill
- mkt-icpSkill
- mkt-influencer-marketingSkill
- mkt-jab-hookSkill
- mkt-launchSkill
- mkt-lead-magnetsSkill
- mkt-marketing-loopsSkill
- mkt-offersSkill
- mkt-onboardingSkill
- mkt-paywallsSkill
- mkt-popupsSkill
- mkt-positioningSkill
- mkt-programmatic-seoSkill
- mkt-prospectingSkill
- mkt-public-relationsSkill
- mkt-referralsSkill
- mkt-sales-enablementSkill
- mkt-schemaSkill
- mkt-signupSkill
- mkt-smsSkill
- mkt-socialSkill
- mkt-ugc-scriptsSkill
- mkt-visual-identitySkill
- ops-analyticsSkill
- ops-attributionSkill
- ops-cronSkill
- ops-ingestSkill
- ops-loopifySkill
- ops-project-managementSkill
- ops-revopsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 27
Keep: dated ## Rules entries, modified sections, added content
- Distinctive: line 34
Keep it minimal — only what differs from the base:
- Distinctive: line 46
If the user made no customizations at all, write a minimal stub:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Synthesize Local Skill Overrides
Cleans up SKILL.local.md files created during migration. Keeps only what
the user actually customized — removes content identical to the base.
Steps
- Scan
.claude/skills/for allSKILL.local.mdfiles - For each one, read the base
SKILL.mdalongside it - Determine if the local file is a verbose migration artifact:
- Has YAML frontmatter → full copy, needs synthesis
- Has section headings that are identical to the base → full copy
- Already lean (only
## Rulesor small additions) → skip, already clean
- For verbose files: synthesize
- Extract what is unique to the local file vs the base
- Keep: dated
## Rulesentries, modified sections, added content - Discard: content identical to the base
- Rewrite
SKILL.local.mdwith only the delta
- Report what was synthesized and what was skipped
Output format for SKILL.local.md
Keep it minimal — only what differs from the base:
## Rules
- YYYY-MM-DD: user rule here
## Section Name (only if user modified it)
User's version of the section.If the user made no customizations at all, write a minimal stub:
## Rules
<!-- No local rules yet. Add dated entries here. -->Rules
Updated when users flag issues with the synthesis process.
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.

