wiki-context
Auto-query llm-wiki domains for relevant context before executing domain tasks
Best use case
wiki-context is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Auto-query llm-wiki domains for relevant context before executing domain tasks
Teams using wiki-context should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/wiki-context/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How wiki-context Compares
| Feature / Agent | wiki-context | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Auto-query llm-wiki domains for relevant context before executing domain tasks
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Wiki Context Retrieval Query the llm-wiki knowledge base for relevant context before executing engineering domain tasks. Bridges the gap between wiki knowledge and agent execution per the retrieval contract (#2208). ## When This Skill Activates - Before any engineering domain task (OrcaFlex, mooring, pipeline, structural, CFD, naval architecture) - When an agent needs background knowledge for issue planning or execution - When the retrieval contract (#2208) requires consulting wiki sources - When working on issues labeled `domain:knowledge-management` or `domain:knowledge` ## Quick Usage ```bash # Query across all domain wikis bash scripts/knowledge/wiki-query-context.sh "mooring line failure HMPE" # Query specific domains only bash scripts/knowledge/wiki-query-context.sh "pipeline integrity corrosion" --domains engineering,marine-engineering # JSON output for programmatic use bash scripts/knowledge/wiki-query-context.sh "OrcaFlex VIV analysis" --json ``` ## How to Use in Agent Workflows ### Step 1: Identify Query Keywords Extract 3-5 keywords from the current task. Include: - Domain terms (mooring, pipeline, structural, hydrodynamic) - Tool names (OrcaFlex, OrcaWave, AQWA, OpenFOAM) - Standards codes (DNV-RP-C205, API 2SK, OCIMF MEG4) ### Step 2: Run Wiki Query ```bash bash scripts/knowledge/wiki-query-context.sh "<keywords>" --domains <relevant_domains> ``` The script queries each wiki domain via `llm_wiki.py query` and checks the cross-links JSONL store for entity matches. Results are ranked by relevance. ### Step 3: Inject Context Take the top 3 results and use them as background context for your task: - Read the referenced wiki page(s) for detailed knowledge - Note any cross-wiki links that connect to other domains - Cite wiki pages in your output (e.g., "per wiki:engineering/concepts/pipeline-integrity") ### Step 4: Log Consultation Record which wiki pages were consulted in your output: ``` Wiki sources consulted: - engineering/concepts/pipeline-integrity-assessment (score: 0.85) - marine-engineering/entities/pipeline-integrity (score: 0.72) - cross-link: shared entities [API 579, DNV-RP-F101] ``` ## Domain Wiki Map | Domain | Wiki Path | Typical Topics | |--------|-----------|---------------| | engineering | `knowledge/wikis/engineering/` | Methodology, compound patterns, standards | | marine-engineering | `knowledge/wikis/marine-engineering/` | Offshore, mooring, riser, hydrodynamics | | naval-architecture | `knowledge/wikis/naval-architecture/` | Ship design, stability, seakeeping | | maritime-law | `knowledge/wikis/maritime-law/` | Legal frameworks, cases, regulations | | personal | `knowledge/wikis/personal/` | Career learnings (rarely queried by agents) | ## Cross-Links Store The JSONL cross-link store at `knowledge/wikis/cross-links.jsonl` contains inter-wiki relationships with typed evidence (slug-similarity, shared-tags, entity-coref, shared-provenance, standards-chain). Use it to discover related pages across domains. ## Integration with Retrieval Contract (#2208) The retrieval contract requires minimum 3 consulted sources per issue plan. Wiki context counts as a consulted source. Record findings in the "Resource Intelligence Summary" section of plans.
Related Skills
llm-wiki-weekly-freshness
Class-level governance workflow for keeping llm-wiki-style markdown knowledge bases current, public-safe, graph/index-valid, and useful for code development. Use when reviewing llm-wiki architecture/content, scanning new LLM concepts, maintaining public knowledge graphs, producing an issue roadmap, or running recurring freshness cadence.
llm-wiki-source-extraction-coverage
Doc-type-aware extraction contract for llm-wiki source ingestion with measurable coverage and source-anchored traceability. Use when (1) ingesting a PDF, DOCX, XLSX, PPTX, HTML, or scanned-image source into a wiki `sources/` page, (2) computing the pre-extraction estimate (what fraction of the source we expect to recover) and post-extraction yield (what fraction we actually recovered), (3) anchoring wiki claims back to specific page / paragraph / cell / slide positions in the source so a reviewer can re-verify or revise against the actual document, (4) deciding whether OCR fallback or manual transcription is needed. Codifies workspace-hub's existing OCR fallback chain and python-docx / openpyxl / trafilatura patterns into a format-specific routing table. Companion to research/llm-wiki-page-shape-contract (Rule 7 input-layer pages) and research/llm-wiki — this skill is the defense against silent extraction failure.
llm-wiki-public-private-routing
Firewall between the public llm-wiki repo (vamseeachanta/llm-wiki, MIT + CC-BY-4.0) and per-client private wikis (vamseeachanta/llm-wiki-<client>, e.g. llm-wiki-mkt-a per #2746). Use when (1) deciding whether a converted wiki page lands in public or private surface, (2) applying the project-name abstraction rule to public-bound content, (3) evaluating the public- availability exception that lets actual project names pass through unmodified, (4) promoting content from private to public after sanitization. Encodes the 2026-05-20 user routing directive verbatim: exact client results → private; abstracted (project-name only) → public; project name + all key data publicly available → exception applies. Companion to research/llm-wiki-page-shape-contract (which calls this skill at Rule 8) and research/llm-wiki-source-extraction-coverage (which produces the source pages this skill decides where to send).
llm-wiki-page-shape-contract
Enforce the page-shape contract when a repo-side document or analysis output gets converted into an llm-wiki page. Use when (1) running `scripts/knowledge/llm_wiki.py ingest`, (2) writing or rewriting a wiki page from docs/reports/*, docs/handoffs/*, scripts/review/results/*, or calc citation outputs, (3) deciding whether a page should be split into a folder of sub-pages, (4) reviewing wiki PRs for length / diagram / divide-and-conquer compliance. Codifies the Karpathy + Astro-Han + lewislulu page rules applied to workspace-hub's domain-wiki layout under /mnt/local-analysis/llm-wiki/wikis/<domain>/. Sibling to research/llm-wiki (which owns the CLI ops) — this skill is the quality gate every converted page must clear before commit.
llm-wiki-cadence-governance
Weekly governance workflow for keeping an llm-wiki repository current, code-development-useful, and connected to actionable GitHub issue planning.
llm-wiki-audit-feedback-loop
Durable feedback loop for correcting llm-wiki pages without losing the correction to chat history. Use when (1) a human notices a wiki page is wrong, outdated, or contradicts a source, (2) processing the `audit/` inbox of a domain wiki, (3) reviewing what feedback has been resolved vs deferred, (4) needing to leave a comment on a specific text range that survives line- number drift. Implements the anchored-text audit file pattern from lewislulu/llm-wiki-skill, adapted for workspace-hub's domain-wiki layout under /mnt/local-analysis/llm-wiki/wikis/<domain>/. Extends the 5-op model (compile/ingest/query/lint) from research/llm-wiki with the missing `audit` op. Never silently delete feedback — rejected audits stay archived with rejection rationale.
oss-wiki-development-arc
Three-phase methodology (Substrate → Depth → Quality) for building open-source engineering wikis efficiently. Skip 70%+ of empirical iteration cost by pre-loading the pattern.
context-compaction-handoff
Guardrails for resuming work after context compaction or transcript handoff blocks; prioritize the latest real user request over stale summarized tasks and verify before answering.
client-llm-wiki-factory
Operator checklist for instantiating a new per-client private llm-wiki repo under workspace-hub [#2746](https://github.com/vamseeachanta/workspace-hub/issues/2746) + [#2731](https://github.com/vamseeachanta/workspace-hub/issues/2731) D4 (amended) naming convention `llm-wiki-<client>`.
metadata-only-wiki-sweep-workflow
Disciplined inventory process for cataloging documents by filename/path without content claims, using parent-centric grouping to prevent stub proliferation
exclude-wiki-Codex-md-from-harness-line-limit-hook
Fix false-positive pre-commit failures where workspace-hub's AGENTS.md line-limit hook blocks edits to auto-generated wiki schema files under knowledge/wikis/.
repair-legacy-llm-wiki-frontmatter-dates
Diagnose and repair legacy llm-wiki source pages that have ingested timestamps but are missing required added/last_updated frontmatter dates.