follow-through
Skill0 starsChanged 3 months agoMITView on GitHub
Ground personal advice in a private Markdown memory and maintain approved facts, preferences, people, life areas, work, decisions, plans, reviews, and outcomes. Use for personal decisions, life planning, relationship or preference context, follow-up reviews, unresolved personal work, or explicit bootstrap, decide, plan, and review requests.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- soilmass/motion-design-agenttheir own version, first seen Nov 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- soilmass/motion-design-agent★ 7same name
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
10 rules. About 0 are common, 8 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈8
Distinctive · estimate
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
- Distinctive: line 8
Use the configured private repository as durable personal context.
- Very specific: line 16
Read the repository's AGENTS.md, then INDEX.md.
- Distinctive: line 19
Search before reading broadly.
- Very specific: line 22
When creating or changing records, also read the repository's CONTEXT.md.
- Distinctive: line 28
Read references/workflows.md, then follow the matching workflow:
- Distinctive: line 42
Treat explicit current statements as stronger than stored context, but resolve material conflicts before relying on either.
- Distinctive: line 44
Never convert an inference into canonical knowledge without approval.
- Distinctive: line 47
Keep raw conversations, secrets, account numbers, identity documents, and raw medical or financial records out of the repository.
- Distinctive: line 49
Use synthetic examples only when demonstrating the public project.
- Distinctive: line 53
Run these from this skill directory:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Follow Through
Use the configured private repository as durable personal context. The repository owns its records and schema; this skill owns the workflow.
Start
- Resolve the repository by running
python3 scripts/follow_through.py wherefrom this skill directory. If setup is incomplete, follow the command's instruction and stop. - Read the repository's
AGENTS.md, thenINDEX.md. - On the first Follow Through request in a conversation, inspect due reviews
and relevant open work as directed by
AGENTS.md. - Search before reading broadly. Open only records useful to the request.
- Briefly state which stored context materially informed the answer.
When creating or changing records, also read the repository's CONTEXT.md. It
is the authority for record types, metadata, statuses, transitions, templates,
links, and supersession.
Route
Read references/workflows.md, then follow the matching workflow:
- ordinary advice or a personal question: retrieve
- explicit initial setup: bootstrap
- explicit choice-making: decide
- explicit personal planning: plan
- due, early, or deferred follow-up: review
- a request meeting
CONTEXT.md'sworkdefinition: work - an approved canonical update or requested commit: approve, write, validate, and commit
Preserve trust
- Treat explicit current statements as stronger than stored context, but resolve material conflicts before relying on either.
- Never convert an inference into canonical knowledge without approval.
- Propose the exact distilled change before writing. Approval applies only to that proposal.
- Keep raw conversations, secrets, account numbers, identity documents, and raw medical or financial records out of the repository.
- Use synthetic examples only when demonstrating the public project.
Repository commands
Run these from this skill directory:
python3 scripts/follow_through.py setup PATH
python3 scripts/follow_through.py connect PATH
python3 scripts/follow_through.py where
python3 scripts/follow_through.py validate [PATH]
python3 scripts/follow_through.py schema-diff [PATH]
python3 scripts/follow_through.py schema-update [PATH] --applysetup creates a new private repository from the bundled template. connect
registers an existing repository after validation. Schema updates print a diff
unless --apply is supplied; never apply one without explicit approval.
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.