Jordan’s Toolkit
GitHub
← All bundles

11 CANONICAL SKILLS · V0.2.0

Web Research and Source Access

Route sources, qualify connector access, read bounded public content, compare feeds, and produce timestamped research evidence.

Inspect the selection

Run from a full toolkit checkout. This prints a file manifest, not an installer.

node tools/bundle.mjs resolve web-research
View manifest ↗
Original

Source Access Routing

Select a source-specific read, search, feed, or transcript path without confusing URL recognition, configured tools, and actual authorized access.

Web and researchexperimental
Original

Connector Health Diagnostics

Diagnose each source operation using separate installation, execution, connectivity, authentication, permission, and live-result evidence.

Web and researchexperimental
Original

Public Web Reading

Read an explicitly authorized public page into a bounded, source-linked, untrusted evidence packet without executing its content or crossing private-network boundaries.

Web and researchexperimental
Original

Feed Change Tracking

Compare feed snapshots by stable item identity and content while distinguishing updates, window expiry, pagination, and malformed or incomplete captures.

Web and researchexperimental
Original

Transcript Evidence Extraction

Turn authorized caption files into timestamped evidence with declared language/origin and clear separation between speech, descriptions, and visual content.

Web and researchexperimental
Original

Authenticated Source Access

Use private or logged-in source connectors with verified identity, narrow operations, explicit data recipients, and access-aware fallback decisions.

Web and researchexperimental
Original

Multi-source Research

Build a claim-oriented research record from independent primary sources, bounded discovery, exact revisions, and explicit disagreements or access gaps.

Web and researchexperimental
Original

Connector Setup Review

Review connector installation and upgrade plans for exact provenance, scoped mutations, credential exposure, operation tests, and recoverable removal.

Web and researchexperimental
Original

Browser Session Isolation

Assign browser contexts and account state to explicit agent lanes, verify readiness and isolation, and preserve evidence before releasing only owned resources.

Web and researchexperimental
Original

Structured Web Extraction

Extract records against an independent field contract, rejecting decoy matches, wrong cardinality, and unsupported adaptive recovery while preserving source evidence.

Web and researchexperimental
Original

Bounded Crawl Planning

Specify finite, authorized multi-page collection with persistent cooldowns, deduplication, freshness and recovery rules, without treating a plan as an executing crawler.

Web and researchexperimental

Tailor context, not a second copy.

Pick the skill needed for the current task. A private adapter supplies project-specific roots, command IDs, accepted contracts, and policy. It should pin and verify the public revision before exposing guidance to an internal agent.

Skill effectiveness remains experimental. Package validation and content hashes do not establish host compatibility, artifact authenticity, or permission to execute.

Read the private-adapter boundary ↗