refresh
Skill4 starsChanged 18 days agoMITView on GitHub
Maintain the repo's knowledge. The index mode rebuilds the ticket catalog (INDEX.md) and the context mode rebuilds the domain knowledge pack (documentation/). Day to day, hooks keep both fresh automatically.
12 other projects use a version of this.
Adopted by
Most recently taken up by
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tooltheir own version, first seen Nov 8, 2026
- ansvisor/ansvisortheir own version, first seen Nov 1, 2026
- RightBlogger/bloggingskillstheir own version, first seen Nov 1, 2026
- zoo3323/usage-statuslinetheir own version, first seen Oct 15, 2026
- Tngc93/repo-onboardingtheir own version, first seen Oct 15, 2026
- prPMDev/my-portfolio-kittheir own version, first seen Oct 13, 2026
Other versions12 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 12
- ai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool★ 432same name
- ansvisor/ansvisor★ 233same name
- iliasedelkin/jobissimo★ 8same name
- fullymiddleaged/Clawness★ 5same name
- RightBlogger/bloggingskills★ 4same name
- prPMDev/my-portfolio-kit★ 2same name
- fabio-baumgartner/unternehmer-skills★ 1same name
- mkreindel/seo-toolkit-template★ 1same name
- NikolajSaudella/cue★ 1same name
- zoo3323/usage-statusline★ 1same name
2 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
2 rules. 0 are common, 0 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
0
Distinctive
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
- Very specific: line 31
Follow index.md: render deterministically (tools/build_ticket_index.py — stdlib, no model), enrich the un-enriched/stale set (the model …
- Very specific: line 38
Follow context-pack.md: verify each configured warehouse target, introspect via its adapter (inventory → DDL → dependencies → usage …
“Common” is measured: kept by at least 6 in 10 of the 10 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
/refresh
One maintenance skill for the two knowledge stores the other skills read:
/refresh index— the ticket catalog:tickets/INDEX.md(every ticket, status, one-line summary, tags, cross-refs) +tickets/OBJECTS.md(object → tickets reverse map). This is what/ticket's recall mines. Details: index.md./refresh context— the domain knowledge pack indocumentation/: data catalog, DDL, ERD, dependency graph, business glossary. This is what/ticket's domain + warehouse priming reads. With no warehouse seam, the pack is the glossary + domain notes built from tickets and repo docs (the introspection phases skip cleanly). Details: context-pack.md./refresh all— both.
You rarely need this
Day-to-day the index maintains itself: the PostToolUse hook re-renders INDEX.md on every ticket
folder change, the SessionStart hook surfaces the catalog, and /ship curates each ticket's
summary at close. Invoke /refresh to:
- bootstrap an existing backlog (
/refresh index --all— render every ticket, then enrich); - re-enrich a batch after bulk edits (
/refresh index ID1 ID2 …); - build or update the knowledge pack (
/refresh context, scoped to a schema if given;--refreshupdates in place — overwrite, don't sprawl).
Mode: index
Follow index.md: render deterministically (tools/build_ticket_index.py — stdlib, no
model), enrich the un-enriched/stale set (the model writes one curated record per ticket, ingested
via tools/ingest_index_records.py), re-render, then verify with --check and commit the whole index
together — INDEX.md, OBJECTS.md, index_data.json, and the graph layer (tickets/graph/ +
tickets/objects/) when project.graph_notes is on (the default).
Mode: context
Follow context-pack.md: verify each configured warehouse target, introspect via its adapter
(inventory → DDL → dependencies → usage ranking), generate data_catalog.md / erd.md /
glossary.md into documentation/ with freshness stamps, and update
documentation/AI_LAYER_INDEX.md. Don't invent business meaning — flag glossary gaps for a human
(reduce_assumptions).
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.