FlashRAG Evidence (VCO)
Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.
MCP get_skill({ skillId: "flashrag-evidence-vco-165292c5" })Use this skill with your agent
Create a free account and connect via MCP
# 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)
1. VCO core docs/config inside `~/.codex/skills/vibe/`:
- `protocols/`, `config/`, `references/`, `scripts/router/`
2. Skills catalog (`~/.codex/skills/**/SKILL.md`) for tool capability evidence
3. (Optional) Project-local VCO overlays under the current workspace, if present
## Workflow (Lite, no heavy deps)
1. Run the evidence retriever script:
- Windows PowerShell:
- `python C:\Users\羽裳\.codex\skills\flashrag-evidence\scripts\flashrag_evidence.py --query "…" --topk 8`
2. (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.ps1` auto-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`
3. 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)
4. If coverage is low:
- Expand `--roots` to include the project workspace
- Increase `--topk`
- Fallback: targeted `rg -n` on the most likely file(s)
## Outputs
The script prints ranked evidence items:
- `path` + `line` (1-based) for quick navigation
- `score` for ranking
- `snippet` (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
More skills in Data, AI & Research
Ablation Planner
Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent designs ablations from a reviewer's perspective; the local executor reviews feasibility and implements.
Ablation Planner
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
About
Provides information about the bitwize-music plugin, its version, and its creator. Use when the user asks about the plugin, its purpose, version, or capabilities.
Ab Test Analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
Academic Search
Search and analyze academic literature. Find papers, understand research methodologies, and synthesize academic findings for research projects.
Adaptyv
How to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.
Explore Other Categories
Skills from other categories with shared topics
Prompt Lookup
Activates when the user asks about AI prompts, needs prompt templates, wants to search for prompts, or mentions prompts.chat. Use for discovering, retrieving, and improving prompts.
Algorithmic Art
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
cancel-ralph
Codex-compatible cancel command for Ralph loop state, preserving the original command name.