openplanter
Investigate datasets and resolve entities using OpenPlanter methodology — cross-reference heterogeneous sources, build Admiralty/ACH confidence-tiered evidence chains, and apply OSINT tradecraft. Triggers on entity resolution, cross-reference datasets, evidence chain, OSINT investigation, structured investigation.
npx skills add majiayu000/claude-skill-registry --skill openplanter --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Guides an agent through cross-dataset investigation, entity resolution, and construction of evidence-backed chains following the OpenPlanter methodology. It focuses on cross-referencing heterogeneous sources, building confidence-tiered evidence chains, and applying structured OSINT tradecraft. Triggers on entity resolution, cross-reference datasets, evidence chain creation, OSINT investigation, and structured investigation.
How it works
- Initialize workspace with the provided script path.
- Drop datasets into the datasets/ folder.
- Write an investigation plan under plans/plan.md.
- Run entity resolution across datasets using the specified Python script.
- Cross-reference linked entities with the cross_reference.py script.
- Validate the evidence chain with evidence_chain.py.
- Score confidence with confidence_scorer.py.
- Produce outputs in JSON (findings/) and Markdown (findings/).
- Maintain provenance for each dataset (source URL/path, access timestamp, transformations).
- Follow the Epistemic Discipline and the Entity Resolution Protocol as outlined in the methodology, including normalization, blocking, comparison, scoring, clustering, and review stages, plus the Evidence Chain Construction format and confidence tiers.
When to use it
Use for cross-referencing heterogeneous datasets, resolving entities across inconsistent names, building evidence-backed chains with provenance, and conducting structured OSINT investigations that require traceable source records and confidence assessments.
What it can touch
Scripts and tools explicitly named: init_workspace.py, entity_resolver.py, cross_reference.py, evidence_chain.py, confidence_scorer.py, and the related data folders (datasets/, plans/, findings/). All references to these files and scripts are the ones listed in the skill documentation.
Caveats
The skill describes a methodology with explicit steps and scripts but does not guarantee outcomes. It relies on the availability of datasets and external data fetchers as described, and on correct use of the pipeline. Provisions for provenance, confidence tiers, and evidence-appendices are required by the output standards.
# OpenPlanter — Investigation Methodology Skill Epistemic framework for cross-dataset investigation, entity resolution, and evidence-backed analysis. Extracted from the [OpenPlanter](https://github.com/ShinMegamiBoson/OpenPlanter) recursive investigation agent and enriched with professional OSINT tradecraft (Admiralty System, ACH, FollowTheMoney schema, intelligence cycle methodology). Claude Code already has the tools. This skill provides the **methodology**. ## When to Use - Cross-referencing heterogeneous datasets (corporate registries, campaign finance, lobbying, property records, contracts) - Entity resolution across datasets with inconsistent naming - Building evidence chains with provenance and confidence tiers - Structured OSINT investigations requiring epistemic discipline - Any analysis where claims need to trace to cited source records ## Quick Start ```bash # 1. Initialize workspace python3 ~/.claude/skills/openplanter/scripts/init_workspace.py /path/to/investigation # 2. Drop datasets into datasets/ cp campaign_finance.csv lobbying.json corporate_registry.csv /path/to/investigation/datasets/ # 3. Write an investigation plan # → plans/plan.md (see references/output-temp
- When to Use
- Quick Start
- Investigation Methodology
- Epistemic Discipline
- Entity Resolution Protocol
- Evidence Chain Construction
- Confidence Tiers
- Verification Principle
- Analysis Output Standards
- Integration Modes
- RLM Delegation — Provider-Agnostic
- Scripts Reference
- Core Analysis
- Data Collection & Enrichment
python3 ~/.claude/skills/openplanter/scripts/init_workspace.py /path/to/investigation cp campaign_finance.csv lobbying.json corporate_registry.csv /path/to/investigation/datasets/ python3 ~/.claude/skills/openplanter/scripts/entity_resolver.py /path/to/investigation python3 ~/.claude/skills/openplanter/scripts/cross_reference.py /path/to/investigation python3 ~/.claude/skills/openplanter/scripts/evidence_chain.py /path/to/investigation python3 ~/.claude/skills/openplanter/scripts/confidence_scorer.py /path/to/investigation Anthropic (default) python3 scripts/delegate_to_rlm.py --objective "..." --workspace DIR --model claude-sonnet-4-5-20250929 OpenAI python3 scripts/delegate_to_rlm.py --objective "..." --workspace DIR --model gpt-4o
What does the openplanter skill do?
Investigate datasets and resolve entities using OpenPlanter methodology — cross-reference heterogeneous sources, build Admiralty/ACH confidence-tiered evidence chains, and apply OSINT tradecraft. Triggers on entity resolution, cross-reference datasets, evidence chain, OSINT investigation, structured investigation.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill openplanter --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.