Research Toolkit

Use for industry, market, company, product, technology, policy and ecosystem research, including sourced briefs, long reports, revisions and source updates. Simple factual questions usually do not need the full workflow. Choose Lite when author checks fit the use; choose Full when selected reviews, revision decisions and delivery need to stay bound to the current version. Length does not cap either profile, and Full does not automatically mean independent review.

Read the bundled research instructions first. Keep research in a separate task directory; the execution tools return its location.

Use the bundled research tools when available. The CLI fallback uses the same implementation at ../../scripts/research_workflow.py; pass a JSON request through stdin or --request <file>. Read the usage guide for setup.

1. Assemble concrete coverage, questions to answer and expected results from the conversation. Choose the profile using the bundled instructions, then call research_start with that explicit profile, brief and a short task ID. Resume an existing task through research_status, which preserves its saved profile. Treat returned missing_fields and clarification_questions as guidance for the agent, not a form to forward. Fill inferable details and record non-critical defaults as proposals; ask only about consequential choices that cannot be inferred, explaining the actual alternatives. Merge resolved details by calling start again with the saved profile while the task is in the brief stage. For Full, inspect review_readiness before collecting evidence: resolve blocked dependencies or login, and verify access for a custom reviewer command. A local login check does not establish model availability or quota. Lite skips reviewer setup.
2. Call research_status as the task moves through collection, analysis and drafting. Read the current stage guidance once; reuse unchanged guidance and existing task-relative source/report paths. Save source texts in the returned task directory. Use research_save for source/claim/requirement objects and draft saves; handle its field errors yourself. Register the first complete draft using its existing path. Read research_status.activity for observed attempts, timing and returned usage. Users decide research scope and use; do not ask them to manage CSV or review JSON. The tools do not search or write the report for you.
3. Lite follows the returned compact stage methods and skips research_review. For Full, call research_review with the report path, full evidence paths and correct purpose. For local self-review, use include_assignment: false and read the frozen assignment_ref under task_directory; reuse already-read unchanged evidence while checking the complete current report. Callers unable to read local files keep the default complete response. Ordinary reports use the configured content reviewer without a compulsory second audit context. Retain original responses and resume missing work. Evaluations and explicitly configured audits retain their declared requirements.
4. For Full, resume only missing reviews/audits after a recoverable failure. A valid negative review is complete. Preserve original evaluation reports and judgments; use findings to improve the Toolkit. Carry out authorized report repairs in separately saved versions and review those versions. A frozen evaluation uses a separate repair task linked to the same research question; an ordinary report uses research_review with revision: true. Already authorized corrections do not need another confirmation. Reconcile changed research scope in the task records first.
5. Call research_finish with the intended delivery message. Lite returns its six-item author checklist; perform the checks and submit actual results with concrete evidence. For Full, first record any evidenced no-change decisions in the existing review log using the record guide. The tool creates terminal state only if the selected profile's checks pass. If it fails, work on the concrete remaining items and keep the task nonterminal.

Use research_guide with an explicit profile to read a stage's methods without creating a task. Chinese guidance is available with language: "zh".

If MCP is unavailable, invoke the corresponding CLI action (start, save, status, review, finish, guide) from the plugin, retaining the selected profile. Never present Lite author checks or a degraded Full self-review as independent review. These tools enforce their own completion conditions; they do not certify semantic truth or prevent every possible host-agent mistake.