feat(library): move research job from standard to library (#274)

The research job is a domain-specific workflow, not a core framework job.
Moving it to the shared library so users can optionally adopt it rather
than having it auto-installed for everyone.

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Author: ncrmro

library/jobs/README.md

@@ -40,6 +40,23 @@ library/jobs/
 │       ├── audit_milestones.md
 │       ├── audit_boards.md
 │       └── doctor_report.md
+├── research/
+│   ├── job.yml              # Job definition (name, steps, workflows)
+│   ├── readme.md            # Job-specific documentation
+│   ├── AGENTS.md            # Agent context and learnings
+│   └── steps/
+│       ├── scope.md
+│       ├── choose_platforms.md
+│       ├── gather.md
+│       ├── gather_quick.md
+│       ├── synthesize.md
+│       ├── summarize.md
+│       ├── report.md
+│       ├── parse.md
+│       ├── file.md
+│       ├── ingest_material.md
+│       ├── analyze.md
+│       └── plan.md
 └── spec_driven_development/
     ├── job.yml              # Job definition (name, steps, workflows)
     ├── readme.md            # Job-specific documentation

…eepwork/standard_jobs/research/AGENTS.md library/jobs/research/AGENTS.mdsrc/deepwork/standard_jobs/research/AGENTS.md renamed to library/jobs/research/AGENTS.md src/deepwork/standard_jobs/research/AGENTS.md renamed to library/jobs/research/AGENTS.md

@@ -1,6 +1,6 @@
 # Project Context for research
 
-This is the source of truth for the `research` standard job.
+This is a **library job** — a reusable research workflow that users can optionally adopt.
 
 ## Purpose
 
@@ -9,10 +9,9 @@ material ingestion into notes, and reproduction planning for engineering handoff
 
 ## Location
 
-This job lives in the DeepWork package source at `src/deepwork/standard_jobs/research/`.
-It is loaded directly at runtime by the multi-folder job discovery system — there is no
-separate "working copy" in `.deepwork/jobs/`. The MCP server returns the job directory path
-as `job_dir` in workflow responses so agents can find templates and scripts.
+This job lives in `library/jobs/research/`. It is NOT auto-installed — users adopt it
+via `DEEPWORK_ADDITIONAL_JOBS_FOLDERS`, the `shared_jobs` workflow, or by copying it
+into their project's `.deepwork/jobs/` directory.
 
 ## File Organization
 
@@ -21,6 +20,7 @@ research/
 ├── AGENTS.md              # This file
 ├── CLAUDE.md              # Symlink to AGENTS.md
 ├── job.yml                # Job definition with 4 workflows
+├── readme.md              # User-facing documentation
 └── steps/
     ├── scope.md           # Define research scope (shared: deep + quick)
     ├── choose_platforms.md # Select AI platforms (deep only)
@@ -38,9 +38,8 @@ research/
 
 ## Editing Guidelines
 
-- Source of truth is ALWAYS in `src/deepwork/standard_jobs/research/`
-- NEVER edit installed copies in `.deepwork/jobs/` directly
-- After editing, run `deepwork install` to sync
+- Source of truth is `library/jobs/research/`
+- Edit files here directly — changes benefit all adopters
 - Step instruction files live in `steps/` and are referenced by `instructions_file` in job.yml
 
 ## Workflows
@@ -64,5 +63,5 @@ research/
 
 ## Last Updated
 
-- Date: 2026-03-21
-- From conversation about: Initial creation of research standard job
+- Date: 2026-03-23
+- From conversation about: Migrated from standard job to library job

…eepwork/standard_jobs/research/CLAUDE.md library/jobs/research/CLAUDE.mdsrc/deepwork/standard_jobs/research/CLAUDE.md renamed to library/jobs/research/CLAUDE.md src/deepwork/standard_jobs/research/CLAUDE.md renamed to library/jobs/research/CLAUDE.md

@@ -0,0 +1,60 @@
+# Research
+
+A multi-workflow research suite for deep investigation, quick summaries, material ingestion, and reproduction planning.
+
+## Overview
+
+This job provides four workflows covering the full research lifecycle — from scoping a question to producing a polished report, importing external material into your notes, or creating an engineering reproduction plan.
+
+## Workflows
+
+### research (Deep Investigation)
+
+Full multi-platform research with 8+ sources, cross-platform validation, and comprehensive report with bibliography.
+
+```
+scope → choose_platforms → gather → synthesize → report
+```
+
+**Platform support**: Local (WebSearch/WebFetch), Gemini Deep Research, ChatGPT, Grok, Perplexity
+
+### quick (Fast Summary)
+
+Local-only research producing a concise summary from 3+ sources.
+
+```
+scope → gather_quick → summarize
+```
+
+### ingest (Material Import)
+
+Import external research material (markdown, papers, URLs) into your notes system with frontmatter metadata and tags.
+
+```
+parse → file
+```
+
+Requires `NOTES_DIR` or `NOTES_RESEARCH_DIR` environment variables.
+
+### reproduce (Reproducibility Planning)
+
+Ingest research material, analyze for reproducible claims, and create an engineering plan with optional issue creation.
+
+```
+ingest_material → analyze → plan
+```
+
+## Prerequisites
+
+- For **research** workflow: Browser tool access if using external platforms (Gemini, ChatGPT, etc.)
+- For **ingest/reproduce** workflows: `NOTES_DIR` environment variable set to your notes root directory
+
+## Research Types
+
+science, business, competitive, market, technical
+
+## Output Locations
+
+- **research/quick**: `research/[topic_slug]/` in the working directory
+- **ingest**: `$NOTES_RESEARCH_DIR/[topic_slug]/` with frontmatter tags
+- **reproduce**: reproduction plan in working directory + optional issue creation