vamseeachanta
vamseeachanta/workspace-hub
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/vamseeachanta/workspace-hub --skill wiki-context命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Write outbound email and external messages in Vamsee Achanta's voice — a subtle offer to help, never bold or rash claims. Load before drafting ANY email, LinkedIn/Collide reply, proposal note, or outreach sent under his name.
Save/publish analysis or computation results from ANY ecosystem repo to Hugging Face as a queryable, viewer-renderable dataset. Use when the user wants to "save results to hugging face", "publish dataset to HF", "hugging face data saving", "save analysis results", "hf dataset", "make results queryable", or "render via datasets-server API". Reshapes nested results into flat parquet tables, writes a dataset card with a viewer `configs:` block and provenance, applies license/public-vs-private routing, enforces a domain data-quality gate (faithful-to-source != correct), publishes to `aceengineer/<repo>-<projection>`, and verifies via the datasets-server API.
Clone, create, fork, configure, and manage GitHub repositories. Manage remotes, secrets, releases, and workflows. Works with gh CLI or falls back to git + GitHub REST API via curl.
基于 SOC 职业分类
正在显示 SKILL.md
| name | wiki-context |
| description | Auto-query llm-wiki domains for relevant context before executing domain tasks |
| version | 1.0.0 |
| metadata | {"hermes":{"tags":["wiki","context","retrieval","knowledge"],"category":"research","related_skills":["llm-wiki","engineering-issue-workflow"]}} |
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).
domain:knowledge-management or domain:knowledge# 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
Extract 3-5 keywords from the current task. Include:
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.
Take the top 3 results and use them as background context for your task:
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 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) |
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.
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.