Research

The route-researcher skill uses a hybrid architecture combining:

Research-backed guidance for AI-augmented ideation.

The **Specific Aims page** is the most important page of your entire NIH grant application. It's the first thing reviewers read, often determines their initial impression, and may be the only page read by some panel members before scoring begins.

Produce publication-quality essays indistinguishable from the best human essayists. Uses 5-agent heavy analysis, anti-slop enforcement calibrated to 2026 reader skepticism, adaptive essay-type detection, and a self-scoring rubric across 6 dimensions. Use when asked to "write an essay", "essay about", or "/essay".

Writing self-loop for surveys: run the strict section-quality gate, then rewrite only the failing `sections/*.md` files until the report is PASS. **Trigger**: writer self-loop, writing loop, quality gate loop, rewrite failing sections, 自循环, 反复改到 PASS. **Use when**: per-section files exist but C5 is FAIL/BLOCKED (thin sections, missing leads/front matter, citation-scope violations, generator voice). **Skip if**: you are still pre-C2 (NO PROSE), or evidence packs are incomplete (fix C3/C4 first...

When the user wants to analyze Google Search Console data, use GSC API, or interpret search performance. Also use when the user mentions "GSC," "Search Console," "indexing report," "Core Web Vitals," "Enhancements," "Insights report," "search performance," "impressions," "CTR," "average position," "index coverage," "title tag," "meta description," or "searchanalytics.query."

Use when working, planning, or closing a backlog item. Bridges BACKLOG.md to the SAM planning pipeline with optional GitHub Issue/Project/Milestone tracking. No args: interactive browser. With '#N': load item directly from GitHub Issue #N (labels and milestone are canonical status). With title substring: auto-grooming, RT-ICA gate, GitHub issue sync, SAM planning, plan reference recorded. '--auto {title}': fully autonomous mode — no AskUserQuestion calls, derives missing data from research fi...

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.

Create a structured discovery workspace with research questions, hypotheses, and a research plan for a given topic. ---

The directory layout that works for product manager projects. ---

This reference covers multi-level IR analysis for detecting compiler-optimized zeroization (dead-store elimination of wipes) and interpreting results. Read this during Step 7 (IR comparison) and Step 9 (semantic IR analysis) in `task.md`. For flag extraction and pipeline setup, refer to the compile-commands reference (loaded separately from SKILL.md). ---

You are an AI product research specialist that synthesizes user interview insights into actionable product recommendations.

You are an AI product ops specialist that tracks and drives feature adoption.

You are an AI support specialist that suggests optimal resolutions for support tickets by leveraging historical cases, knowledge base content, and pattern recognition.

Use when exploring websites, proving hypotheses about web application behavior, automating browser interactions, or generating E2E tests - investigates page structure through accessibility snapshots, tests assumptions systematically, and coordinates Playwright MCP tools with tenacity to complete complex multi-step investigations

Tracked features, ideas, and deferred work for grooming and future sessions. ---

Tracked features, ideas, and deferred work for grooming and future sessions. ---

Tracked features, ideas, and deferred work for grooming and future sessions. ---

Tracked features, ideas, and deferred work for grooming and future sessions. ---

Tracked features, ideas, and deferred work for grooming and future sessions. ---

Tracked features, ideas, and deferred work for grooming and future sessions. ---

This reference provides detailed patterns for extracting expertise through strategic questioning and active listening. The goal is to transform implicit knowledge into explicit, documented expertise.

> Conducted: 2026-02-02 > Scope: Workflow commands, command docs, guides, YAML definitions, and cross-references > Method: Full read of all files in scope, cross-referencing YAML definitions against docs ---

This skill should be used when the user asks to recall, search, or continue past conversations. Triggers on "what did we discuss", "continue where we left off", "remember when", "as I mentioned", "you suggested", "we decided", "search my conversations", "find the conversation where", "what did we work on". Also triggers on implicit signals like past-tense references ("the bug we fixed"), possessives without context ("my project"), or assumptive questions ("do you remember").