/cortex-wiki-author
Author first-class wiki pages (ADRs, specs, file docs, notes) that live alongside Cortex memory. Use when the user says 'this is an ADR', 'document this decision', 'write an ADR', 'add a spec', 'spec this out', 'document this file', 'add a note about', 'link these pages',
$ npx -y skills add cdeust/Cortex --skill cortex-wiki-author --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/cortex-wiki-author
Context preview
The summary Claude sees to decide when to auto-load this skill.
Author first-class wiki pages (ADRs, specs, file docs, notes) that live alongside Cortex memory. Use when the user says 'this is an ADR', 'document this decision', 'write an ADR', 'add a spec', 'spec this out', 'document this file', 'add a note about', 'link these pages',
SKILL.md
cortex-wiki-author.SKILL.mdname: cortex-wiki-author
description: "Author first-class wiki pages (ADRs, specs, file docs, notes) that live alongside Cortex memory. Use when the user says 'this is an ADR', 'document this decision', 'write an ADR', 'add a spec', 'spec this out', 'document this file', 'add a note about', 'link these pages', 'bookmark this as a spec', or when finalizing a design decision that should persist as a human-readable document."
Wiki Author — Long-form Documentation Layer
Keywords
adr, spec, decision, design doc, rfc, file doc, notes, wiki, documentation, link pages, bidirectional link, supersedes, implements, depends on
Overview
Cortex's wiki is a Markdown authoring surface for the long-form artifacts that don't fit the thermodynamic memory model: architecture decision records, specs, per-file documentation, and free-form notes. Pages live under `~/.claude/methodology/wiki/` and are **never pruned** — they are first-class authored content, not derived views. Every write also registers a protected pointer memory in PostgreSQL so `recall` surfaces wiki pages alongside regular memories.
**Use this skill when:** the user is making a decision that should persist, finalizing a spec, documenting a file's purpose, or asking for two wiki pages to be linked.
**Do NOT use for:** ephemeral facts (use `remember`), domain profiles (use `query_methodology`), or regenerating documentation from memory (the wiki is authored, not projected).
Workflow
Record an architecture decision
cortex:wiki_adr({
"title": "Use pgvector for retrieval",
"context": "We need a searchable memory store with hybrid ranking.",
"decision": "Adopt PostgreSQL + pgvector + pg_trgm as the single backend.",
"consequences": "No SQLite fallback. Operator must provision Postgres 15+.",
"status": "accepted",
"tags": ["storage", "retrieval"]
})Returns `{ path, number, title, status, ... }`. ADR numbers auto-increment.
Write a spec
cortex:wiki_write({
"path": "specs/wiki-authoring.md",
"content": "# Wiki authoring\n\n## Summary\n\nClaude authors ADRs and specs during sessions..."
})Pass the final markdown you want to land. Use `"mode": "append"` to add to an existing page, `"replace"` to overwrite.
Document a file
cortex:wiki_write({
"path": "files/mcp_server-handlers-wiki_write.md",
"content": "# `mcp_server/handlers/wiki_write.py`\n\n## Purpose\n\nComposition root for the wiki authoring tool..."
})Link two pages bidirectionally
cortex:wiki_link({
"from_path": "adr/0001-use-pgvector-for-retrieval.md",
"to_path": "specs/retrieval-pipeline.md",
"relation": "implements"
})Adds the forward relation to `from_path` and the inverse (`implemented_by`) to `to_path`. Idempotent. Known relations: `supersedes`/`superseded_by`, `implements`/`implemented_by`, `depends_on`/`depended_on_by`, `derived_from`/`derives`, `see_also`.
Read a page (to update it)
cortex:wiki_read({ "path": "adr/0001-use-pgvector-for-retrieval.md" })List pages
cortex:wiki_list({}) // all kinds
cortex:wiki_list({ "kind": "adr" }) // just ADRsRegenerate the table of contents
cortex:wiki_reindex({})Writes `.generated/INDEX.md`. This is the only file ever auto-regenerated — authored pages are untouched.
Layout
~/.claude/methodology/wiki/
adr/NNNN-<slug>.md # numbered decision records
specs/<slug>.md # feature specs, PRDs, design docs
files/<slug>.md # per-source-file documentation
notes/<slug>.md # free-form notes and investigations
.generated/INDEX.md # auto-generated table of contents
Tips
- **No prune, ever.** Authored pages survive across sessions, version bumps, and machine moves (as long as the wiki root is preserved).
- **ADR numbers are monotonic.** Don't reuse them — supersede instead via `wiki_link(new, old, "supersedes")`.
- **Links live in the page.** The `## Related` section is the source of truth for wiki-internal links — not a sidecar index.
- **Wiki pages are recallable.** After `wiki_write`, the page content (first 500 chars) is indexed in PostgreSQL as a protected memory tagged `wiki`, so `recall` returns it alongside regular memories.
- **Back-links are authoritative.** `wiki_link` always updates both pages. If you move or rename a file, re-run `wiki_link` so the related sections stay consistent.
Read more
name: cortex-wiki-author description: "Author first-class wiki pages (ADRs, specs, file docs, notes) that live alongside Cortex memory. Use when the user says 'this is an ADR', 'document this decision', 'write an ADR', 'add a spec', 'spec this out', 'document this file', 'add a note about', 'link these pages', 'bookmark this as a spec', or when finalizing a design decision that should persist as a human-readable document."
Wiki Author — Long-form Documentation Layer
Keywords
adr, spec, decision, design doc, rfc, file doc, notes, wiki, documentation, link pages, bidirectional link, supersedes, implements, depends on
Overview
Cortex's wiki is a Markdown authoring surface for the long-form artifacts that don't fit the thermodynamic memory model: architecture decision records, specs, per-file documentation, and free-form notes. Pages live under `~/.claude/methodology/wiki/` and are **never pruned** — they are first-class authored content, not derived views. Every write also registers a protected pointer memory in PostgreSQL so `recall` surfaces wiki pages alongside regular memories.
**Use this skill when:** the user is making a decision that should persist, finalizing a spec, documenting a file's purpose, or asking for two wiki pages to be linked.
**Do NOT use for:** ephemeral facts (use `remember`), domain profiles (use `query_methodology`), or regenerating documentation from memory (the wiki is authored, not projected).
Workflow
Record an architecture decision
cortex:wiki_adr({
"title": "Use pgvector for retrieval",
"context": "We need a searchable memory store with hybrid ranking.",
"decision": "Adopt PostgreSQL + pgvector + pg_trgm as the single backend.",
"consequences": "No SQLite fallback. Operator must provision Postgres 15+.",
"status": "accepted",
"tags": ["storage", "retrieval"]
})Returns `{ path, number, title, status, ... }`. ADR numbers auto-increment.
Write a spec
cortex:wiki_write({
"path": "specs/wiki-authoring.md",
"content": "# Wiki authoring\n\n## Summary\n\nClaude authors ADRs and specs during sessions..."
})Pass the final markdown you want to land. Use `"mode": "append"` to add to an existing page, `"replace"` to overwrite.
Document a file
cortex:wiki_write({
"path": "files/mcp_server-handlers-wiki_write.md",
"content": "# `mcp_server/handlers/wiki_write.py`\n\n## Purpose\n\nComposition root for the wiki authoring tool..."
})Link two pages bidirectionally
cortex:wiki_link({
"from_path": "adr/0001-use-pgvector-for-retrieval.md",
"to_path": "specs/retrieval-pipeline.md",
"relation": "implements"
})Adds the forward relation to `from_path` and the inverse (`implemented_by`) to `to_path`. Idempotent. Known relations: `supersedes`/`superseded_by`, `implements`/`implemented_by`, `depends_on`/`depended_on_by`, `derived_from`/`derives`, `see_also`.
Read a page (to update it)
cortex:wiki_read({ "path": "adr/0001-use-pgvector-for-retrieval.md" })List pages
cortex:wiki_list({}) // all kinds
cortex:wiki_list({ "kind": "adr" }) // just ADRsRegenerate the table of contents
cortex:wiki_reindex({})Writes `.generated/INDEX.md`. This is the only file ever auto-regenerated — authored pages are untouched.
Layout
~/.claude/methodology/wiki/ adr/NNNN-<slug>.md # numbered decision records specs/<slug>.md # feature specs, PRDs, design docs files/<slug>.md # per-source-file documentation notes/<slug>.md # free-form notes and investigations .generated/INDEX.md # auto-generated table of contents
Tips
- **No prune, ever.** Authored pages survive across sessions, version bumps, and machine moves (as long as the wiki root is preserved).
- **ADR numbers are monotonic.** Don't reuse them — supersede instead via `wiki_link(new, old, "supersedes")`.
- **Links live in the page.** The `## Related` section is the source of truth for wiki-internal links — not a sidecar index.
- **Wiki pages are recallable.** After `wiki_write`, the page content (first 500 chars) is indexed in PostgreSQL as a protected memory tagged `wiki`, so `recall` returns it alongside regular memories.
- **Back-links are authoritative.** `wiki_link` always updates both pages. If you move or rename a file, re-run `wiki_link` so the related sections stay consistent.
Cross-platform persistent memory MCP for Codex, Gemini CLI, Claude Code, and other local MCP hosts. 36 cited neuroscience mechanisms, local-first SQLite/PostgreSQL, hybrid retrieval, decay-based consolidation, and reproducible benchmarks. Claude adds optional automatic lifecycle hooks.
Repo: cdeust/Cortex
Other skills on hypermnesia-mcp.
- /cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this
Open skill - /cortex-consolidate
Run memory maintenance — decay old memories, compress stale content, consolidate episodic memories into semantic knowledge, and run sleep-like replay. Use when the user says 'clean up memories', 'consolidate', 'run maintenance', 'compress old memories', 'memory cleanup', or
Open skill - /cortex-debug-memory
Debug and fix memory system issues — validate memories, rate quality, manage protection, forget bad memories, and restore from checkpoints. Use when the user says 'fix memory', 'bad memory', 'wrong memory', 'delete this', 'protect this', 'this memory is wrong', 'memory quality',
Open skill - /cortex-explore-memory
Explore the memory system's state, find gaps in knowledge, assess coverage, and get diagnostic information. Use when the user asks 'what does my memory look like', 'show me memory stats', 'what am I missing', 'how good is my knowledge', 'memory health', 'show coverage', 'find
Open skill - /cortex-import
Import memories from other AI memory systems into Cortex. Supports claude-mem (SQLite), Claude Desktop sessions, ChatGPT web export (JSON), Gemini Takeout (JSON), Cursor conversations, and Claude Code JSONL. Use when the user says 'import from claude-mem', 'migrate memories',
Open skill - /cortex-navigate-knowledge
Navigate the knowledge graph — trace entity relationships, explore causal chains, drill into memory clusters, and traverse co-access paths. Use when the user asks 'how are these related', 'what connects X to Y', 'show me the knowledge graph', 'trace the relationship', 'what
Open skill

