analyze-intervention

Apply an intervention/do-style graph modification and propagate predicted directional effects while recording assumptions.

Skill by yogsoth-ai

IndexedApache-2.0★ 505

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/yogsoth-ai-analyze-intervention

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.

About

Apply an intervention/do-style graph modification and propagate predicted directional effects while recording assumptions.

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 and code. Checked Oct 26, 2026.

Tools: No tools found
Secrets: None asked for
Install scripts: None found

Network hosts it talks to 1

codeload.github.com · found in install command

Files it touches

~/.claude/skills/analyze-intervention

What's inside

Skill name: analyze-intervention
Description: Apply an intervention/do-style graph modification and propagate predicted directional effects while recording assumptions.
License: Apache-2.0
Instructions: 45 lines in SKILL.md · view on GitHub

Files (1)

SKILL.md

SKILL.md (first lines)

# analyze-intervention

## Purpose

Analyze an intervention's target, mechanism, implementation conditions, and observed effects.

## Input contract

```yaml
required: [intervention, target_system, outcome_records]
optional: [implementation_records, comparator, mechanism_hypotheses]
constraints: [effect interpretation must retain implementation and comparison conditions]
```

## Procedure

1. Define intervention components, dose, timing, and target mechanism.
2. Map implementation fidelity and deviations to observed conditions.
3. Compare outcomes with the declared comparator and plausible alternatives.
4. Summarize mechanism evidence, effect heterogeneity, and unresolved attribution.

If the intervention analysis yields a causal attribution that needs an explicit validity check, consider `validate-causal-link` as the next tactic.

## Output contract

```yaml
produces: [intervention_map, implementation_profile, outcome_comparison, mechanism_assessment, attribution_limits]
delta_fields: [findings, evidence_updates, uncertainties, decisions, open_questions]
```

## Quality gates

- Intervention components and implementation are separated.
- Comparator and outcome conditions are explicit.

## Failure and counterexamples

Do not attribute an effect to the intervention when co-interventions or implementation changes are untracked.

## Provenance map

- `resolved: analyze-intervention`

From yogsoth-ai/de-anthropocentric-research-engine, Apache-2.0.

Signals

Stars: 505
Forks: 43
Open issues: 1
Last commit (this folder): Sep 23, 2026 (1 month ago)
Last release: Oct 23, 2026 (5 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License: Apache-2.0
Repository: github.com/yogsoth-ai/de-anthropocentric-research-engine
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: GitHub github-graphql

More from yogsoth-ai

Cite this page

analyze-intervention skill. Agent Mart. https://agentmart.dev/skills/yogsoth-ai-analyze-intervention (last updated 2026-10-24)