Skip to content
Agentmart
Submit a tool

evidence-compiler

Convert multi-source research, audits, fact checks, and consequential analyses into a typed dependency graph whose conclusions can be retracted when premises…

Skill by serhiipriadko2-sys

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/serhiipriadko2-sys-evidence-compiler

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Convert multi-source research, audits, fact checks, and consequential analyses into a typed dependency graph whose conclusions can be retracted when premises fail or expire. Use when a result depends on several claims, sources conflict, freshness matters, or confidence must be bounded by evidence. Record source identity, observation time, validity window, content hash, dependencies, confidence ceiling, and falsifier. Return a concise evidence map, not hidden chain-of-thought.

Use cases: writing, research

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Python package

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/evidence-compiler

What's inside

Skill name
evidence-compiler
Description
Convert multi-source research, audits, fact checks, and consequential analyses into a typed dependency graph whose conclusions can be retracted when premises fail or expire. Use when a result depends on several claims, sources conflict, freshness matters, or confidence must be bounded by evidence. Record source identity, observation time, validity window, content hash, dependencies, confidence ceiling, and falsifier. Return a concise evidence map, not hidden chain-of-thought.
License
MIT
Instructions
13 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Files (5)

  • SKILL.md
  • openai.yaml · agents/
  • icon.svg · assets/
  • schema.md · references/
  • claim_dag.py · scripts/

SKILL.md (first lines)

# Evidence Compiler

1. Extract only claims that can change the decision.
2. Label each claim `FACT`, `INTERP`, `HYP`, `UNKNOWN`, or `CONFLICT`.
3. Attach source identity, observation time, validity window, and content hash when available.
4. Record dependency IDs and a falsifier for each derived claim.
5. Reject cycles and confidence above the weakest verified dependency.
6. Recheck temporal validity before action; invalidate descendants of false, conflicted, or expired premises.
7. Return claim IDs, evidence, dependencies, status, confidence ceiling, and evidence needed.

Use `scripts/claim_dag.py` for deterministic graph validation. See [references/schema.md](references/schema.md).

From serhiipriadko2-sys/parallax, MIT.

More from serhiipriadko2-sys/parallax

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 28, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/serhiipriadko2-sys/parallax
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from serhiipriadko2-sys

Cite this page

evidence-compiler skill. Agent Mart. https://agentmart.dev/skills/serhiipriadko2-sys-evidence-compiler (last updated 2026-10-24)