TypingMindTypingMindThe best frontend for AI
Evidence Draft logo

Evidence Draft

Community
WILLOSCAR
evidence-draft

Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.

Overview

PublisherWILLOSCAR
Repositoryresearch-units-pipeline-skills
Skill nameevidence-draft
Stars
513
Forks
39
Bundled files
10
Links
Skill sourceRepository
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 10 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by WILLOSCAR on GitHub. Read the source before you install it.

Installation

Install the Evidence Draft AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/evidence-draft
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/WILLOSCAR/research-units-pipeline-skills.git /tmp/research-units-pipeline-skills
mkdir -p .claude/skills
cp -r /tmp/research-units-pipeline-skills/.codex/skills/evidence-draft .claude/skills/evidence-draft
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Evidence Draft in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Evidence Draft on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Evidence Draft is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Evidence Draft

Triggers & routing

  • Trigger: evidence draft, evidence pack, claim candidates, concrete comparisons, evidence snippets, provenance, 证据草稿, 证据包, 可引用事实.

Build deterministic outline/evidence_drafts.jsonl packs from briefs + notes + optional evidence bindings.

Compatibility mode is active: this migration preserves the existing JSONL contract while moving evidence-quality policy, sparse-evidence routing, and evaluation-anchor rules into references/ and assets/.

Load Order

Always read:

  • references/overview.md
  • references/evidence_quality_policy.md

Read by task:

  • references/block_vs_downgrade.md when deciding whether thin evidence should block drafting or only downgrade claim strength
  • references/evaluation_anchor_rules.md when evaluation tokens, protocol context, or numeric claims are weak
  • references/examples_sparse_evidence.md for evidence-thin pack calibration
  • references/source_text_hygiene.md when paper self-narration or generic result wrappers are leaking into pack snippets / claim candidates

Machine-readable assets:

  • assets/evidence_pack_schema.json
  • assets/evidence_policy.json
  • assets/source_text_hygiene.json
  • repo-wide assets/limitation-signals.json — shared polarity rules that keep resolved failures and positive improvements out of limitation slots

Inputs

Required:

  • outline/subsection_briefs.jsonl
  • papers/paper_notes.jsonl
  • citations/ref.bib

Optional but recommended:

  • papers/evidence_bank.jsonl
  • outline/evidence_bindings.jsonl

Outputs

Keep the current output contract:

  • outline/evidence_drafts.jsonl
  • optional human-readable mirrors under outline/evidence_drafts/

Script Boundary

Use scripts/run.py only for:

  • deterministic joins across briefs / notes / evidence bank / bindings
  • snippet extraction and provenance assembly
  • policy-driven blocking_missing / downgrade_signals / verify_fields materialization
  • pack validation and Markdown mirror generation

Do not treat run.py as the place for:

  • filler bullets that make thin evidence look complete
  • hidden sparse-evidence judgment that is not inspectable from references/ / assets/
  • reader-facing narrative prose

Output Shape Rules

Keep these stable:

  • preserve the existing top-level pack fields already used by downstream survey pipelines
  • claim_candidates must remain snippet-derived
  • concrete_comparisons must remain genuinely two-sided; if one cluster has no usable highlight, drop the card and surface thin evidence upstream instead of fabricating an A-vs-B contrast
  • snippet sampling should stay cluster-aware: when a subsection has explicit clusters, evidence selection should avoid collapsing onto one route just because its abstracts contain louder result sentences
  • sparse evidence should surface as explicit blockers / downgrade signals / verify fields, not filler bullets
  • citation keys must remain constrained to citations/ref.bib

Compatibility Notes

Current mode is reference-first with deterministic compatibility:

  • assets/evidence_policy.json defines pack thresholds and sparse-evidence routing
  • assets/evidence_pack_schema.json documents/validates the stable pack shape
  • assets/source_text_hygiene.json owns this Skill's wrapper cleanup, while the repo-wide assets/limitation-signals.json owns limitation polarity across paper-notes, evidence-draft, and writer-context-pack
  • scripts/run.py still materializes the existing JSONL + Markdown outputs, but no longer pads sparse sections with generic caution prose

Quick Start

  • uv run python .codex/skills/evidence-draft/scripts/run.py --workspace <workspace>

Execution Notes

When running in compatibility mode, scripts/run.py currently reads:

  • outline/subsection_briefs.jsonl
  • papers/paper_notes.jsonl
  • citations/ref.bib
  • optionally papers/evidence_bank.jsonl and outline/evidence_bindings.jsonl
  • assets/evidence_policy.json and assets/evidence_pack_schema.json

Script

Quick Start

  • uv run python .codex/skills/evidence-draft/scripts/run.py --workspace <workspace>

All Options

  • --workspace <dir>
  • --unit-id <id>
  • --inputs <path1;path2>
  • --outputs <path1;path2>
  • --checkpoint <C*>

Examples

  • uv run python .codex/skills/evidence-draft/scripts/run.py --workspace <workspace>

Troubleshooting

  • If packs look complete despite thin evidence, inspect assets/evidence_policy.json and references/block_vs_downgrade.md before changing Python.
  • If evaluation bullets are generic, inspect references/evaluation_anchor_rules.md and the policy asset.
  • If claims are strong but evidence is abstract/title-only, downgrade via downgrade_signals and verify_fields rather than adding narrative caveats.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Evidence Draft AI skill do?

Create per-subsection evidence packs (NO PROSE): claim candidates, concrete comparisons, evaluation protocol, limitations, plus citation-backed evidence snippets with provenance.

Why use Evidence Draft on TypingMind?

Because you install it once and use it with any model. Evidence Draft is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Evidence Draft in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WILLOSCAR/research-units-pipeline-skills/tree/main/.codex/skills/evidence-draft. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Evidence Draft?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Evidence Draft?

As many as you like. As long as a model supports skills, you can use Evidence Draft with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Evidence Draft AI skill free?

It is published on GitHub by WILLOSCAR. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Related AI Skills

View all
affaan-m logo

Deep Research

affaan-m
CommunityPopular

Multi-source deep research using firecrawl and exa MCPs. Searches the web, synthesizes findings, and delivers cited reports with source attribution. Use when the user wants thorough research on any…

40.4K
270.2K
1 files
View
affaan-m logo

Exa Search

affaan-m
CommunityPopular

Neural search via Exa MCP for web, code, and company research. Use when the user needs web search, code examples, company intel, people lookup, or AI-powered deep research with Exa's neural search…

40.4K
270.2K
1 files
View
mattpocock logo

Wayfinder

mattpocock
CommunityPopular

Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.

22.3K
264.4K
1 files
View
NousResearch logo

Creative Ideation

NousResearch
OrganizationPopular

Generate ideas via named methods from creative practice.

53.5K
250.4K
27 files
View

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇