foryourhealth111-pixel/Vibe-Skills / bundled/skills/flashrag-evidence
flashrag-evidence
VerifiedLocal evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.
FlashRAG Evidence (VCO)
When to use
Use this skill when you need grounded, citeable evidence from local documentation/configuration to support VCO decisions or recommendations, especially for:
- VCO routing / pack selection rationale
- Protocol compliance (think/do/review/team/retro)
- Config semantics (thresholds, overlays, governance)
- “Show me where this rule comes from” / “give me the exact snippet”
This skill is not a replacement for GitNexus (code dependency graph) or web search. It focuses on local docs and config.
Inputs
- Query: what you’re trying to verify (short, concrete)
- Optional: corpus root(s) to search (defaults below)
Default corpus (evidence plane)
- VCO core docs/config inside
~/.codex/skills/vibe/:protocols/,config/,references/,scripts/router/
- Skills catalog (
~/.codex/skills/**/SKILL.md) for tool capability evidence - (Optional) Project-local VCO overlays under the current workspace, if present
Workflow (Lite, no heavy deps)
-
Run the evidence retriever script:
- Windows PowerShell:
python C:\Users\羽裳\.codex\skills\flashrag-evidence\scripts\flashrag_evidence.py --query "…" --topk 8
- Windows PowerShell:
-
(Optional) Enable a faster FlashRAG-style BM25 backend (
bm25s)- Preflight (checks vendoring + env; does NOT read secrets):
pwsh C:\Users\羽裳\.codex\skills\vibe\scripts\ruc-nlpir\preflight.ps1
- Manually create an isolated venv for the vendored runtime and install only the minimal packages you need. The old
install-upstreams.ps1auto-install path has been removed on purpose. - Use bm25s engine:
C:\Users\羽裳\.codex\_external\ruc-nlpir\.venv\Scripts\python.exe C:\Users\羽裳\.codex\skills\flashrag-evidence\scripts\flashrag_evidence.py --engine bm25s --query "…" --topk 8
- Preflight (checks vendoring + env; does NOT read secrets):
-
Use the returned snippets as P5 evidence:
- [Command] the exact command you ran
- [Output] the top snippets (path + line anchor)
- [Claim] the conclusion you draw (only what the evidence supports)
-
If coverage is low:
- Expand
--rootsto include the project workspace - Increase
--topk - Fallback: targeted
rg -non the most likely file(s)
- Expand
Outputs
The script prints ranked evidence items:
path+line(1-based) for quick navigationscorefor rankingsnippet(short, safe to quote)
Notes (non-redundancy)
- If you need code call chains / blast radius, use GitNexus overlays (not this).
- If you need latest web facts, use web search / deep research tools (not this).
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |