wiki-update
Skill1 starsChanged 28 days agoMITView on GitHub
How to structure a docs/wiki/ page under the Obsidian LLM-wiki standard — placement and dedup before creating, page templates, facet vocabulary, link ontology, and whether a discovery is fixed inline or queued in wiki-todos.md.
10 other projects use a version of this.
Adopted by
Most recently taken up by
- Ar9av/obsidian-wikitheir own version, first seen Nov 8, 2026
- chobizzy/llm-wikitheir own version, first seen Nov 1, 2026
- boaz-hwang/boaz-wikitheir own version, first seen Oct 25, 2026
- rumi-chan/llm-wikitheir own version, first seen Oct 25, 2026
- 0xbadal/Skillstheir own version, first seen Oct 13, 2026
- kfchou/wiki-skillstheir own version, first seen Jul 3, 2026
Used with
Projects with it also use claude-history-ingest, graph-colorize 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.
Ivy-Chen1999Skillclaude-history-ingest
Ingest Claude Code conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Claude conversations for knowledge, import their ~/.claude folder, extract insights from previous coding sessions, or says things like "process my Claude history", "add my conversations to the wiki", "what have I discussed with Claude before". Also triggers when the user mentions their .claude folder, Claude projects, session data, past conversation logs, local-agent-mode sessions, or audit logs.
Also in 3 projects that use this
Ivy-Chen1999Skillgraph-colorize
Color-code the Obsidian graph view by rewriting `.obsidian/graph.json` colorGroups. Use this skill when the user says "color my graph", "color code obsidian", "colorize the graph", "color the graph by tag", "color by category", "highlight visibility in graph", "make the graph colorful", "distinguish tags in graph", or wants nodes in Obsidian's graph view tinted by tag, folder, or visibility. Generates a `colorGroups` array from the vault's actual tags/categories and merges it into the existing graph.json without clobbering other graph settings. Always backs up first.
Also in 3 projects that use this
nexuschainsSkillcross-linker
Scans the wiki vault and adds missing [[wikilinks]] between pages that are related but not yet connected. Use this skill when the operator says "link my pages", "find missing links", "cross-reference the wiki", "connect my wiki", "add wikilinks", or after any large ingest to weave new pages into the existing knowledge graph. Also trigger when orphaned pages need connecting or when wiki-lint reports fragmented tag clusters. This is a write-heavy skill — it modifies page files to insert links, unlike wiki-lint which only reports.
Also in 3 projects that use this
nexuschainsSkilltag-taxonomy
Enforces and normalizes tags across the wiki against the controlled vocabulary in wiki/schema/tag-taxonomy.md. Use this skill when the operator says "fix my tags", "normalize tags", "tag audit", "clean up tags", "tag taxonomy", or "my tags are a mess". Also use when creating or updating wiki pages and the right tags are unclear. Operates in three modes: Audit (report current state), Normalize (apply fixes), and Classify (tag a single new page). Always reads the taxonomy file before assigning any tags.
Also in 3 projects that use this
jehrhardtSkillwiki-capture
Quickly capture raw thoughts, links, images, or notes to today's Obsidian daily note from anywhere in Pi. Use when the user wants to jot something down for later wiki processing.
Also in 3 projects that use this
- +6 more from Ivy-Chen1999
- +1 more from nexuschains
Other versions10 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 10
- Ar9av/obsidian-wiki★ 3.7ksame name
- kfchou/wiki-skills★ 189same name
- bozhouDev/bozhou-skills★ 78same name
- Ivy-Chen1999/llm-wiki-kit★ 21same name
- CodePhobiia/claude-roblox-game-studio★ 9same name
- crabin/llm-wiki★ 8same name
- chobizzy/llm-wiki★ 3same name
- 0xbadal/Skills★ 1same name
- rumi-chan/llm-wiki★ 1same name
- boaz-hwang/boaz-wiki★ 0same 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.
In this repository20 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adversarial-reviewSkill
- clean-architectureSkill
- decision-recordingSkill
- design-system-checkSkill
- dispatch-handoffSkill
- feature-branchingSkill
- finding-dispositionSkill
- git-recoverySkill
- gotcha-recordingSkill
- human-checkpointSkill
- plan-reviewSkill
- plan-writingSkill
- pr-createSkill
- simplicity-ladderSkill
- spec-writingSkill
- subagent-contractSkill
- subagent-dispatchSkill
- tdd-loopSkill
- update-toolkitSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 9 edited versions we read keep these.
1
Distinctive
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
- Distinctive: line 13
Write the concept's essence (1–2 standalone sentences).
- Very specific: line 14
Check for existing pages under another name: walk docs/wiki/ and grep -r "aliases:" -A3 docs/wiki/.
“Common” is measured: kept by at least 6 in 10 of the 9 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
Wiki Update — standard, templates, routing
Single source of truth for the wiki schema (rule 18). Ticking an entity's Behavior cases needs nothing from here.
Placement — before creating any page
- Write the concept's essence (1–2 standalone sentences).
- Check for existing pages under another name: walk
docs/wiki/andgrep -r "aliases:" -A3 docs/wiki/. - Exists → merge into that page, add the new name to
aliases, extendsources, bumpupdated. - Does not exist → create from a template below. Filename = canonical name without
* " \ / < > : | ? # ^ [ ](put symbol-bearing variants inaliases). - Target of a new link does not exist → create a
status: stubpage in the same change (or if outside your write scope, omit the link and queue awiki-todos.mditem). - Merge duplicate pages into the more canonical filename (keeping union of links/provenance and old name in
aliases; ask the human if ambiguous). Split multi-concept pages and rewire links.
Canonical page template
---
aliases: [Agentic loop, Sense-Plan-Act]
type: concept # concept | procedure | reference | tutorial | entity | decision | summary
abstraction: pattern # principle | pattern | technique | instance
domains: [agents, software]
status: developing # stub | developing | stable
sources:
- docs/raw/anthropic-agents.md
implements:
- "[[feedback-principle]]"
specializes: []
contrasts_with:
- "[[linear-pipeline]]"
alternative_to: []
depends_on:
- "[[world-model]]"
contradicts: []
open_questions:
- How does this relate to hierarchical planning?
created: 2026-07-21
updated: 2026-07-21
---
# Agentic loop (Sense–Plan–Act)
> [!abstract] Essence
> One or two sentences that capture the concept, understandable out of context —
> read first, and the fingerprint used for dedup.
## Model
What it is, why it matters, when it applies.
## Detail
How it works: examples, variants, parameters.
## Boundaries
Edge cases, where it does NOT apply, open tensions and contradictions, *unverified* claims.
## Provenance
- Claim ← source; every non-trivial claim traces to a `docs/raw/` file.type: concept pages use the Essence → Model → Detail → Boundaries → Provenance spine and the abstraction facet (entity pages use abstraction: instance and the Entity spine below; decision, summary, and reference pages omit abstraction and use their own templates). Frontmatter wikilinks are quoted strings (one per list item); body wikilinks are unquoted.
[infra] concept pages also carry a ## Behavior section of verifiable operational assertions ([ ]/[~]/[x]); lint must not flag it.
Entity page template (docs/wiki/entities/<slug>.md)
---
aliases: []
type: entity
abstraction: instance
domains: [<domain>]
status: developing # stub | developing | stable
sources: []
depends_on:
- "[[other-entity]]"
contradicts: []
open_questions: []
created: YYYY-MM-DD
updated: YYYY-MM-DD
---
# <Entity Name>
> [!abstract] Essence
> What this entity exists to do, in user-facing terms.
## Behavior
- [ ] B1: <observable behavior, no implementation detail>
(States: `[ ]` not started · `[~]` test written and confirmed failing · `[x]` passing.)
## Implementation
- Files: [src/foo.py](../../../src/foo.py)
- Key functions: `do_thing()`
- Used by: [[consumer-entity]]
## Tests
- Files: [tests/test_foo.py](../../../tests/test_foo.py)
- Mapping: B1 → `test_does_thing`
## Boundaries
- Edge cases, known limitations, open tensions, unverified claims.
## Provenance
- Requirement ← `docs/raw/...`, a decision page, or a requirements section.Other templates
Supporting files beside this skill (open only when creating or restructuring that page):
summary-template.md—docs/wiki/summaries/<slug>.mdfor an ingested source.design-system-template.md—docs/wiki/design-system.md, only for projects with a UI surface.
Facet vocabulary (closed)
| Property | Allowed values | Use |
type | concept, procedure, reference, tutorial, entity, decision, summary | Reader need. |
abstraction | principle, pattern, technique, instance | Generality rung (required on concept and entity). |
domains | controlled list (agents, software, design, …) | Application domains. |
status | stub, developing, stable — decisions: proposed, accepted, superseded, deprecated | Maturity (stub = known gap). |
Ledgers (log.md, todos.md, wiki-todos.md, gotchas.md, commands.md), root spec pages (requirements.md, architecture.md, git-conventions.md, design-system.md), and folder README.md guides are type: reference navigational pages and are exempt from the orphan rule. Only content pages (entity, concept, decision, summary) can be orphans.
Link ontology — and the gap each relation makes computable
| Relation | Direction | Gap rule |
implements | technique/pattern → principle | A technique implements ≥1 principle. |
specializes | instance/pattern → more general concept | Required on instance except type: entity and type: summary. |
contrasts_with | ↔ comparable alternatives | Symmetric. |
alternative_to | ↔ same function, different approach | Symmetric. |
depends_on | concept → prerequisite | Target must exist (at least as stub). |
contradicts | ↔ explicit conflict | Unresolved conflicts escalate to the human. |
supersedes / superseded_by | decision ↔ decision | Superseded ADR has status: superseded + superseded_by. |
Fill schema gaps with status: stub and open_questions, never invented prose.
Inline or queued
- Inline (in the same change, by write roles): one ADR, one gotcha, the active entity page, a single broken link, or a stub for a new link target.
- Queued in
docs/wiki/wiki-todos.md(directly or viaFollow-ups:): cross-section orphans, contradictions between pages (setcontradictson both; don't resolve), patterns recurring 3+ times (promote toconcepts/), ambiguous merges/splits, or edits requiring 5+ pages read. - Routing: pitfall →
gotchas.md; design fork → ADR; repeated pattern →wiki-todos.md.wiki-maintaineris manual only (/project:wiki).
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.

