Agent skill

Evidence Binder

by WILLOSCAR in WILLOSCAR/research-units-pipeline-skills

Bind addressable evidence IDs from papers/evidencebank.jsonl to each subsection (H3), producing outline/evidencebindings.jsonl.

No licenceAuto-check passed

Install Evidence Binder

skills CLI
$ npx skills add WILLOSCAR/research-units-pipeline-skills --skill evidence-binder -a claude-code

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

GitHub CLI
$ gh skill install WILLOSCAR/research-units-pipeline-skills evidence-binder --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/WILLOSCAR/research-units-pipeline-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.codex/skills/evidence-binder .claude/skills/evidence-binder && 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
evidence-binder
GitHub stars
513
Token cost
~1.6k tokens
SKILL.md length
701 words
Files
2 (incl. scripts)
Skills in repo
107
Repo updated
First seen
Licence
None found

At a glance

Bind addressable evidence IDs from papers/evidencebank.jsonl to each subsection (H3), producing outline/evidencebindings.jsonl.

  • Works in 5 steps: Read outline/subsection_briefs.jsonl to… → Read outline/mapping.tsv to know which… → Read papers/evidence_bank.jsonl and… → …
  • SKILL.md covers Triggers & routing, Inputs, Outputs and Output format…, plus 7 more sections
  • Runs Python scripts from its folder; calls uv

What it does

Evidence Binder is an agent skill from WILLOSCAR/research-units-pipeline-skills. Bind addressable evidence IDs from papers/evidencebank.jsonl to each subsection (H3), producing outline/evidencebindings.jsonl.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/run.py`).

The repository describes itself as: Research pipelines as semantic execution units: each skill declares inputs/outputs, acceptance criteria, and guardrails. Evidence-first methodology prevents hollow writing…

Example prompts

  • “/evidence-binder”

Requirements

  • Python 3

Workflow steps

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

  1. Read outline/subsection_briefs.jsonl to understand each H3’s scope/rq/axes.
  2. Read outline/mapping.tsv to know which papers belong to each subsection.
  3. Read papers/evidence_bank.jsonl and select a subsection-scoped set of evidence_id items per H3.
  4. If citations/ref.bib exists, sanity-check that any cite keys referenced by selected evidence items are defined.
  5. Write outline/evidence_bindings.jsonl and outline/evidence_binding_report.md.

What it can do on your machine

Read from SKILL.md and the folder at commit c92912a. 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:

    • uv

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

  • Network

    No URLs in SKILL.md. Its commands use uv, which can reach the network depending on how they are called.

    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

Evidence Binder loads about 1.6k tokens when it runs. Until then it costs about 37 tokens; SKILL.md has 701 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~37
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

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

Without a licence we can't republish the file, so here is its outline and opening line. It has 701 words (~1,578 tokens).

“Goal: convert a paper-level pool into a subsection-addressable evidence plan.”

— opening of SKILL.md by WILLOSCAR
name
evidence-binder

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in .codex/skills/evidence-binder of WILLOSCAR/research-units-pipeline-skills.

  • SKILL.md
  • scripts/run.py

Open the folder on GitHubat commit c92912a

Compare with similar skills

Evidence Binder 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.

Evidence Binder compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Evidence Binder this skillWILLOSCAR/research-units-pipeline-skills513—~1.6kAutomated safety check: PassNone
Hugging Face Paper Pageshuggingface/skills11k3 repos~2.3kAutomated safety check: PassApache-2.0
Papers Skillsickn33/agentic-awesome-skills47k1 repos~2.1kAutomated safety check: PassMIT
Read arXiv Paperkarpathy/nanochat59k1 repos~494Automated safety check: PassMIT
Bgpt Paper SearchK-Dense-AI/scientific-agent-skills48k1 repos~2kAutomated safety check: PassMIT
Paper 2 Webdavila7/claude-code-templates32k12 repos~4kAutomated safety check: NotesMIT

Similar skills

  • Hugging Face Paper Pages

    huggingface/skills

    Official

    Fetches Hugging Face paper pages as markdown and reads paper metadata through the papers API when you share a paper URL, an arXiv link or an arXiv ID.

    11k GitHub starsUsed in 3 repos~2.3k tokens
    Research & ScienceAuto-check passed
  • Papers Skill

    sickn33/agentic-awesome-skills

    Skill for academic research workflows: search Semantic Scholar (200M+ papers), inspect citations, download arXiv PDFs, and extract PDF text.

    47k GitHub starsUsed in 1 repo~2.1k tokens
    Research & ScienceAuto-check passed
  • Read arXiv Paper

    karpathy/nanochat

    Fetches the TeX source of an arXiv paper from its URL, reads it and writes a markdown summary tied to the nanochat project.

    59k GitHub starsUsed in 1 repo~494 tokens
    Research & ScienceAuto-check passed
  • Bgpt Paper Search

    K-Dense-AI/scientific-agent-skills

    Searches BGPT scientific papers by topic or DOI and retrieves claim-level evidence extracted from full text, including experiments, reported statistics, scope, limitations, and provenance.

    48k GitHub starsUsed in 1 repo~2k tokens
    Research & ScienceAuto-check passed
  • Paper 2 Web

    davila7/claude-code-templates

    This skill should be used when converting academic papers into promotional and presentation formats including interactive websites (Paper2Web), presentation videos (Paper2Video), and conference…

    32k GitHub starsUsed in 12 repos~4k tokens
    Documents & OfficeAuto-check: notes
  • Ljg Paper

    lijigang/ljg-skills

    Explain research papers to readers without a specialist background: what the paper studies, what the authors contribute, how the findings follow, and what the evidence does not establish.

    7.5k GitHub stars~798 tokensUpdated yesterday
    Research & ScienceAuto-check passed

More from WILLOSCAR/research-units-pipeline-skills

All 107 skills in this repo
  • Appendix Table Writer

    WILLOSCAR/research-units-pipeline-skills

    Curate reader-facing survey tables for the Appendix (clean layout + high information density), using only in-scope evidence and existing citation keys.

    513 GitHub stars~1.8k tokensUpdated 4 days ago
    Auto-check passed
  • Artifact Contract Auditor

    WILLOSCAR/research-units-pipeline-skills

    Audit one research Workspace for declared Unit outputs and Pipeline target Artifacts, writing output/CONTRACTREPORT.md; use for mid-Run coverage snapshots or final delivery completeness, not deep…

    513 GitHub stars~918 tokensUpdated 4 days ago
    Auto-check passed
  • Arxiv Search

    WILLOSCAR/research-units-pipeline-skills

    Retrieve arXiv paper metadata with keyword queries or import an offline arXiv export, and save results as JSONL (papers/papersraw.jsonl).

    513 GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check passed
  • Chapter Lead Writer

    WILLOSCAR/research-units-pipeline-skills

    Write H2 chapter lead blocks (sections/S<secidlead.md) that preview the chapter's comparison lens and connect its H3 subsections, without adding new facts.

    513 GitHub stars~1.5k tokensUpdated 4 days ago
    Auto-check passed
  • Chapter Skeleton

    WILLOSCAR/research-units-pipeline-skills

    Build a retrieval-informed chapter skeleton (outline/chapterskeleton.yml) from taxonomy/core scope before stable H3 decomposition.

    513 GitHub stars~475 tokensUpdated 4 days ago
    Auto-check passed
  • Dedupe Rank

    WILLOSCAR/research-units-pipeline-skills

    A skill your agent uses when a broad paper candidate pool needs deterministic deduplication and a stable core set.

    513 GitHub stars~438 tokensUpdated 4 days ago
    Auto-check passed

Questions about Evidence Binder

What does Evidence Binder do?

Bind addressable evidence IDs from papers/evidencebank.jsonl to each subsection (H3), producing outline/evidencebindings.jsonl. Evidence Binder is an agent skill from WILLOSCAR/research-units-pipeline-skills.jsonl.

How do I install Evidence Binder in Claude Code?

Run `npx skills add WILLOSCAR/research-units-pipeline-skills --skill evidence-binder -a claude-code`. Or copy the skill folder (.codex/skills/evidence-binder in WILLOSCAR/research-units-pipeline-skills) into .claude/skills/evidence-binder in your project. Claude Code loads it when a task matches its description.

How do I install Evidence Binder in Codex?

Run `npx skills add WILLOSCAR/research-units-pipeline-skills --skill evidence-binder -a codex`. Or copy the skill folder (.codex/skills/evidence-binder in WILLOSCAR/research-units-pipeline-skills) into .agents/skills/evidence-binder in your project. Codex loads it when a task matches its description.

Can I use Evidence Binder 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 WILLOSCAR/research-units-pipeline-skills --skill evidence-binder -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evidence-binder, .gemini/skills/evidence-binder, .github/skills/evidence-binder and .opencode/skills/evidence-binder in your project.

What does Evidence Binder need to run?

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

Does Evidence Binder access the network?

SKILL.md contains no URLs. Its commands use uv, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Evidence Binder 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 Evidence Binder use?

No licence was found for Evidence Binder or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Evidence Binder use?

About 1.6k tokens (SKILL.md is roughly 6.3k 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 Evidence Binder?

Skills that share tags, products or a category with Evidence Binder: Hugging Face Paper Pages (huggingface/skills, 11k stars), Papers Skill (sickn33/agentic-awesome-skills, 47k stars), Read arXiv Paper (karpathy/nanochat, 59k stars) and Bgpt Paper Search (K-Dense-AI/scientific-agent-skills, 48k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Evidence Binder?

WILLOSCAR (a GitHub user) maintains it in WILLOSCAR/research-units-pipeline-skills, which has 513 GitHub stars. The repository holds 107 skills in this directory. The repository was last updated on October 5, 2026.

Source: WILLOSCAR/research-units-pipeline-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.