Research

Execute the implementation planning workflow using the plan template

Use when you want to autonomously improve a SKILL.md's quality by running iterative experiments. Triggers on "autoresearch 돌려줘", "스킬 품질 올려줘", "이 스킬을 자동으로 개선해줘", "run autoresearch on this skill", or any request to automatically improve a skill's eval pass rate through repeated experimentation. Applies Karpathy's autoresearch technique - fixed-budget iterative loop with single-metric hill-climbing and automatic keep/discard decisions.

Runs a milestone retrospective after validation passes and updates the roadmap. Use when the user says "/taskforge-retro", "let's do a retro", "retrospective", "what did we learn", "update the roadmap", or when a milestone validation has just passed and the next milestone hasn't started yet.

Design surveys with question types, skip logic, and templates. Use when adding questions, setting logic, laying out forms, checking contrast, spacing elements.

Subpoena law reference — types of subpoenas, service requirements, compliance obligations, and motion to quash. Use when issuing, receiving, or responding to subpoenas in legal proceedings.

Help with coursework. Use when taking notes, summarizing readings, formatting citations, outlining essays, or calculating GPA.

Legal statutes reference — statutory interpretation, legislative process, types of statutes, and citation formats. Use when researching laws, understanding statutory construction, or analyzing legislative text.

Legal precedent reference — stare decisis, case law hierarchy, distinguishing, overruling, persuasive authority. Use when researching binding case law, analyzing judicial reasoning, or building legal arguments.

Generate official documents with format checking, tone validation, and templates. Use when drafting official letters, checking format, applying templates.

Generate journal prompts for gratitude, reflection, and weekly review writing. Use when starting journals, writing gratitude entries, or finding new prompts.

Create SVG diagrams with shapes, layers, and multi-format export. Use when generating graphics, building diagrams, arranging layouts.

Generate structured presentation outlines for any topic or product. Use when planning slides, building pitch decks, creating training materials, or outlining technical talks.

Generate falsifiable trade strategy hypotheses from market data, trade logs, and journal snippets. Use when you have a structured input bundle and want ranked hypothesis cards with experiment designs, kill criteria, and optional strategy.yaml export compatible with edge-finder-candidate/v1.

Adversarial brainstorming using agent teams for multi-perspective analysis. Use when users want thorough idea exploration with real debate between independent perspectives. Triggers on "team brainstorm", "adversarial brainstorm", "brainstorm with team", "debate this idea", or when the user explicitly requests team-based analysis. Higher token cost but significantly deeper analysis than single-agent brainstorm.

Pull real SEO metrics for any domain using Apify scrapers for Semrush and Ahrefs data. Gets domain authority, organic traffic estimates, keyword rankings, backlink profiles, top performing pages, and auto-discovers competitors from keyword overlap. No Semrush/Ahrefs subscription needed — uses Apify actors that scrape public pages.

Comprehensive SEO footprint analysis that orchestrates site-content-catalog, seo-domain-analyzer, and brand-voice-extractor into a single deep-dive report. Catalogs all content, pulls real SEO metrics, runs competitor analysis, builds topic/keyword and content-type gap matrices, extracts brand voice, and produces a prioritized recommendations report. The complete SEO audit for any company.

Use BEFORE and AFTER running trading engine simulations. Helps with: (1) SETUP - choosing configs, selecting segments via segment collections, batch sizing (recommend 2,000-3,000 runs); (2) EXECUTION - running batch simulations with --collection; (3) ANALYSIS - comprehensive diagnostics after runs. Triggers on: 'run simulations', 'test configs', 'batch simulation', 'analyze sim results', 'which configs to test', 'how many segments', 'simulation setup'.

Reproduce and investigate a bug using logs, console inspection, and browser screenshots

Use this agent when you need to conduct thorough research on a repository's structure, documentation, and patterns. This includes analyzing architecture files, examining GitHub issues for patterns, reviewing contribution guidelines, checking for templates, and searching codebases for implementation patterns. The agent excels at gathering comprehensive information about a project's conventions and best practices.\\n\\nExamples:\\n- <example>\\n Context: User wants to understand a new repositor...

Identify programmatic SEO page patterns worth building for your product — vs/ pages, integrations/, for-{industry}/, alternatives-to/, use-cases/ — and design the template structure, data model, and priority order. Outputs a complete pSEO blueprint with URL patterns, title templates, content frameworks, and data sources per variable.

Creates, edits, and manages Obsidian vault content including notes, templates, daily notes, and dataview queries. Use when working with markdown files in an Obsidian vault, creating notes, writing templates, building dataview queries, or organizing knowledge management content.

Scan open GitHub issues, PRs, discussions. Produce prioritized triage report with engagement metrics and recommended actions

Audits architectural patterns against best practices. Maintains patterns catalog, calculates 4 scores per pattern. Output: patterns_catalog.md.

Traffic-First opportunity discovery. KILL funnel filters ideas by traffic channel, demand, competition, revenue, interest, MVP-ability. Outputs one idea + one channel recommendation.