New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Flashrag Evidence

by foryourhealth111-pixel in foryourhealth111-pixel/Vibe-Skills

Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.

Apache-2.0Auto-check passed

Install Flashrag Evidence

skills CLI
$ npx skills add foryourhealth111-pixel/Vibe-Skills --skill flashrag-evidence -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install foryourhealth111-pixel/Vibe-Skills flashrag-evidence --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/foryourhealth111-pixel/Vibe-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/bundled/skills/flashrag-evidence .claude/skills/flashrag-evidence && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
flashrag-evidence
GitHub stars
3.6k
Token cost
~685 tokens
SKILL.md length
299 words
Files
2 (incl. scripts)
Skills in repo
81
Repo updated
First seen
Licence
Apache-2.0

At a glance

Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.

  • Works in 3 steps: VCO core docs/config inside… → Skills catalog… → (Optional) Project-local VCO overlays…
  • SKILL.md covers When to use, Inputs, Default corpus (evidence plane) and Workflow (Lite, no heavy deps), plus 2 more sections
  • Runs Python scripts from its folder; calls python, pwsh and rg

What it does

Flashrag Evidence is an agent skill from foryourhealth111-pixel/Vibe-Skills. Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/flashrag_evidence.py`).

The repository describes itself as: Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE. The licence is Apache-2.0.

Example prompts

  • “/flashrag-evidence”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

  1. VCO core docs/config inside ~/.codex/skills/vibe/
  2. Skills catalog (~/.codex/skills/**/SKILL.md) for tool capability evidence
  3. (Optional) Project-local VCO overlays under the current workspace, if present

What it can do on your machine

Read from SKILL.md and the folder at commit ddcaa2a. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • python
    • pwsh
    • rg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Flashrag Evidence loads about 685 tokens when it runs. Until then it costs about 41 tokens; SKILL.md has 299 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~41
When it runs · the whole SKILL.md, loaded when a task matches
~685

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from foryourhealth111-pixel/Vibe-Skills at commit ddcaa2a, republished under its Apache-2.0 licence (© foryourhealth111-pixel). 299 words, ~685 tokens.

Download SKILL.mdSave it as .claude/skills/flashrag-evidence/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
flashrag-evidence
description
Local 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)

  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).

© foryourhealth111-pixel, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (scripts) in bundled/skills/flashrag-evidence of foryourhealth111-pixel/Vibe-Skills.

  • SKILL.md
  • scripts/flashrag_evidence.py

Open the folder on GitHubat commit ddcaa2a

Compare with similar skills

Flashrag Evidence next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Flashrag Evidence compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Flashrag Evidence this skillforyourhealth111-pixel/Vibe-Skills3.6k—~685Automated safety check: PassApache-2.0
Iterative Retrievalaffaan-m/ECC277k7 repos~1.6kAutomated safety check: PassMIT
Vibe Delegatesickn33/agentic-awesome-skills47k1 repos~1.8kAutomated safety check: PassMIT
Iterative Retrievalaffaan-m/ECC277k2 repos~1.1kAutomated safety check: PassMIT
Iterative Retrievalaffaan-m/ECC277k2 repos~1.3kAutomated safety check: PassMIT
Iterative Retrievalaffaan-m/ECC276k1 repos~1.1kAutomated safety check: PassMIT

Similar skills

  • Iterative Retrieval

    affaan-m/ECC

    Pattern for progressively refining context retrieval to solve the subagent context problem.

    277k GitHub starsUsed in 7 repos~1.6k tokens
    Agent WorkflowsAuto-check passed

  • Vibe Delegate

    sickn33/agentic-awesome-skills

    Delegate coding tasks to the Mistral Vibe CLI (vibe) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.

    47k GitHub starsUsed in 1 repo~1.8k tokens
    Auto-check passed

  • Iterative Retrieval

    affaan-m/ECC

    サブエージェントのコンテキスト問題を解決するために、コンテキスト取得を段階的に洗練するパターン. An agent skill from affaan-m/ECC.

    277k GitHub starsUsed in 2 repos~1.1k tokens
    Auto-check passed

  • Iterative Retrieval

    affaan-m/ECC

    서브에이전트 컨텍스트 문제를 해결하기 위한 점진적 컨텍스트 검색 개선 패턴. An agent skill from affaan-m/ECC.

    277k GitHub starsUsed in 2 repos~1.3k tokens
    Auto-check passed

  • Iterative Retrieval

    affaan-m/ECC

    逐步优化上下文检索以解决子代理上下文问题的模式

    276k GitHub starsUsed in 1 repo~1.1k tokens
    Auto-check passed

  • Retrieval Reflex

    garrytan/gbrain

    When/what to retrieve — open the brain page for a salient entity before answering from memory.

    31k GitHub stars~735 tokensUpdated yesterday
    Auto-check passed

More from foryourhealth111-pixel/Vibe-Skills

All 81 skills in this repo

  • Market Research Reports

    foryourhealth111-pixel/Vibe-Skills

    Produces long consulting-style market research and industry reports covering market sizing, competitive landscape, market entry and investment theses.

    3.6k GitHub stars~2.5k tokensUpdated 1 mo ago
    Auto-check: notes

  • Academic Venue Templates

    foryourhealth111-pixel/Vibe-Skills

    Supplies venue-specific LaTeX templates and formatting rules for journals, conferences and posters, and checks a manuscript against page limits and submission requirements.

    3.6k GitHub stars~3.9k tokensUpdated 1 mo ago
    Auto-check: notes

  • Digital Brain

    foryourhealth111-pixel/Vibe-Skills

    This skill should be used when the user asks to "write a post", "check my voice", "look up contact", "prepare for meeting", "weekly review", "track goals", or mentions personal brand, content…

    3.6k GitHub stars~1.7k tokensUpdated 1 mo ago
    Auto-check passed

  • Smart File Writer

    foryourhealth111-pixel/Vibe-Skills

    Diagnoses why a file write failed (permissions, disk space, path length, locks, read-only mounts) before retrying, instead of repeating the same call blindly.

    3.6k GitHub stars~2.6k tokensUpdated 1 mo ago
    Auto-check passed

  • Automated Video Studio

    foryourhealth111-pixel/Vibe-Skills

    Turns footage, audio and a storyboard plan into a finished short video with FFmpeg jump-cuts, subtitle burn-in and a final polish pass.

    3.6k GitHub stars~838 tokensUpdated 1 mo ago
    Auto-check passed

  • Citation Management

    foryourhealth111-pixel/Vibe-Skills

    Turns DOIs, PMIDs and arXiv IDs into clean BibTeX, searches Google Scholar and PubMed, and checks and deduplicates a reference list.

    3.6k GitHub stars~7.6k tokensUpdated 1 mo ago
    Auto-check: notes

Questions about Flashrag Evidence

What does Flashrag Evidence do?

Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors. Flashrag Evidence is an agent skill from foryourhealth111-pixel/Vibe-Skills. Local evidence retrieval (FlashRAG-style) for VCO/vibe: search protocols/config/skills docs and return citeable snippets with file+line anchors.

How do I install Flashrag Evidence in Claude Code?

Run `npx skills add foryourhealth111-pixel/Vibe-Skills --skill flashrag-evidence -a claude-code`. Or copy the skill folder (bundled/skills/flashrag-evidence in foryourhealth111-pixel/Vibe-Skills) into .claude/skills/flashrag-evidence in your project. Claude Code loads it when a task matches its description.

How do I install Flashrag Evidence in Codex?

Run `npx skills add foryourhealth111-pixel/Vibe-Skills --skill flashrag-evidence -a codex`. Or copy the skill folder (bundled/skills/flashrag-evidence in foryourhealth111-pixel/Vibe-Skills) into .agents/skills/flashrag-evidence in your project. Codex loads it when a task matches its description.

Can I use Flashrag Evidence in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add foryourhealth111-pixel/Vibe-Skills --skill flashrag-evidence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/flashrag-evidence, .gemini/skills/flashrag-evidence, .github/skills/flashrag-evidence and .opencode/skills/flashrag-evidence in your project.

What does Flashrag Evidence need to run?

Going by SKILL.md and its folder, Flashrag Evidence needs Python for the scripts in its folder and the command-line tools its instructions call (python, pwsh and rg). Our summary lists: Python 3.

Does Flashrag Evidence access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Flashrag Evidence safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Flashrag Evidence use?

Flashrag Evidence is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Flashrag Evidence use?

About 685 tokens (SKILL.md is roughly 2.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Flashrag Evidence?

Skills that share tags, products or a category with Flashrag Evidence: Iterative Retrieval (affaan-m/ECC, 277k stars), Vibe Delegate (sickn33/agentic-awesome-skills, 47k stars), Iterative Retrieval (affaan-m/ECC, 277k stars) and Iterative Retrieval (affaan-m/ECC, 277k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Flashrag Evidence?

foryourhealth111-pixel (a GitHub user) maintains it in foryourhealth111-pixel/Vibe-Skills, which has 3,627 GitHub stars. The repository holds 81 skills in this directory. The repository was last updated on August 31, 2026.

Source: foryourhealth111-pixel/Vibe-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.