Product & Planning

tools-only Bundle

Groom backlog items — trigger /groom-backlog-item <title|section|all> — fact-checks item claims against primary sources, runs RT-ICA per item, then spawns @backlog-item-groomer agents. Writes groomed content into per-item files in .claude/backlog/. Use when preparing backlog items for planning or execution.

tools-only Bundle

Groom backlog items — trigger /groom-backlog-item <title|section|all> — fact-checks item claims against primary sources, runs RT-ICA per item, then spawns @backlog-item-groomer agents. Writes groomed content into per-item files in .claude/backlog/. Use when preparing backlog items for planning or execution.

tools-only Bundle

Provides AWS CloudFormation patterns for ECS clusters, services, and task definitions. Use when creating ECS infrastructure with CloudFormation, configuring container definitions, scaling policies, service discovery, load balancing integration, and implementing template structure with Parameters, Outputs, Mappings, Conditions, cross-stack references, and blue/green deployments with CodeDeploy.

tools-only Bundle

Extract product ideas through guided questions and generate PRD

tools-only Bundle

ChIP-seq quality control metrics including FRiP (Fraction of Reads in Peaks), cross-correlation analysis (NSC/RSC), library complexity, and IDR (Irreproducibility Discovery Rate) for replicate concordance. Use to assess experiment quality before downstream analysis. Use when assessing ChIP-seq data quality metrics.

tools-only Bundle

Orchestrates specialized agents to create high-quality Claude Code plugins. Delegates to plugin-assessor agent for domain research and code discovery, general-purpose agents for official docs verification, validation scripts for schema checks, and review agents for quality assessment. Use when creating new plugins or improving existing ones.

tools-only Bundle

Use when assigning backlog items to a GitHub milestone. Args: {milestone-number} [P0|P1|P2|title-filter]. Uses backlog list to load items, shows items with GitHub Issue status, lets user select which to assign. Creates missing GitHub Issues for selected P0/P1 items, assigns all to the milestone, updates Project V2 Status to Backlog. Use after create-milestone to populate a sprint or release.

tools-only Bundle

Generate professional GitHub project README.md with standard structure including project intro, features, installation, usage, documentation, FAQ, contact info, donation, statistics, roadmap, and license. Auto-detects project type and tech stack.

tools-only Bundle

Selects informative features for biomarker discovery using Boruta all-relevant selection, mRMR minimum redundancy, and LASSO regularization. Use when identifying biomarkers from high-dimensional omics data.

tools-only Bundle

Researches feature requests and existing architecture documents to produce discovery context. Explores codebase patterns, identifies ambiguities, documents use scenarios, and surfaces questions for orchestrator resolution. Does NOT make technical implementation decisions.

tools-only Bundle

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 files, logs all decisions, skips interactive GitHub prompts; suitable for agent use without human in the loop. 'close {title}': verifies plan checklist 100% complete, closes GitHub issue, marks DONE. 'resolve {title}': marks item no longer applicable with reason. 'setup-github': initializes labels, creates project and first milestone. STOPS if item has existing Plan field or RT-ICA returns BLOCKED.

tools-only Bundle

MCPToolBench++ evaluates AI agents on MCP tool discovery, selection, invocation, and result interpretation across 45+ categories with accuracy-threshold-based evaluation.

tools-only Bundle

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 files, logs all decisions, skips interactive GitHub prompts; suitable for agent use without human in the loop. 'close {title}': verifies plan checklist 100% complete, closes GitHub issue, marks DONE. 'resolve {title}': marks item no longer applicable with reason. 'setup-github': initializes labels, creates project and first milestone. Optional '--language {python|typescript|...}' and '--stack {python-fastapi|python-cli|...}' select Layer 1/2 profile. STOPS if item has existing Plan field or RT-ICA returns BLOCKED.

tools-only Bundle

AI-powered ranking of Dex system improvement ideas

tools-only Bundle

Create a new item in .claude/BACKLOG.md. No args: guided intake via AskUserQuestion. With 'quick {title}': inline capture from user description. With '--auto {title}': fully autonomous — derives all fields from research files and task context, skips all AskUserQuestion calls, logs decisions made. Writes item to correct priority section, updates frontmatter counts, offers GitHub Issue creation for P0/P1. Enforces required fields (title, priority, description) and duplicate detection before writing.

tools-only Bundle

Single interface for BACKLOG.md and GitHub Issues. All backlog CRUD goes through the backlog script — no direct edits. Use when create-backlog-item or work-backlog-item invoke it, or when syncing P0/P1 to GitHub.

tools-only Bundle

Perform in silico gene knockout analysis and synthetic lethality screens using COBRApy single and double deletions. Predict essential genes and identify synthetic lethal pairs for drug target discovery. Use when identifying essential genes or finding synthetic lethal drug targets.

tools-only Bundle

Expert guidance for ffuf web fuzzing during authorized penetration testing. Covers directory discovery, subdomain enumeration, parameter fuzzing, authenticated fuzzing with raw requests, auto-calibration, and result analysis. Use when running ffuf scans, analyzing ffuf output, or building fuzzing strategies for web targets.

tools-only Bundle

Verify claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that MUST use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Triggers on "fact check", "verify claims", "check against primary sources", or when backlog items are marked UNVERIFIED.

tools-only Bundle

Implements nested cross-validation and stratified splits for unbiased model evaluation on biomedical datasets. Prevents data leakage and overfitting in biomarker discovery. Use when validating classifiers or optimizing hyperparameters on omics data.

tools-only Bundle

Detects circadian and ultradian rhythms in time-series omics data using CosinorPy cosinor models, MetaCycle (JTK_CYCLE, ARSER), and RAIN non-parametric tests. Fits cosine models to estimate phase and amplitude, tests rhythmicity significance at pre-specified periods. Use when testing for 24-hour or other known-period oscillations in circadian, feeding-fasting, or light-dark cycle experiments. Not for unknown-period discovery (see temporal-genomics/periodicity-detection).

tools-only Bundle

End-to-end gene regulatory network inference pipeline from processed single-cell data to regulon discovery and perturbation simulation. Supports RNA-only (pySCENIC) and multiome (SCENIC+) paths. Use when building gene regulatory networks from single-cell transcriptomic or multiome data.

tools-only Bundle

Provides Azure defaults for naming, regions, tags, AVM-first modules, security baselines, WAF criteria, governance discovery, and pricing guidance across all agents.

tools-only Bundle

Orchestrates specialized agents to create high-quality Claude Code plugins. Delegates to researcher agents for domain knowledge, Explore agents for code discovery, validation agents for official docs verification, and review agents for quality checks. Use when creating new plugins or improving existing ones.

tools-only Bundle

Researches domain ecosystems and technology landscapes before roadmap creation. Supports three modes — Ecosystem discovery, Feasibility assessment, and Comparison analysis. Use when exploring new domains, evaluating technology choices, or comparing implementation approaches. Requires MCP research servers (Ref, exa, context7, or firecrawl) — BLOCKs if none available.

tools-only Bundle

Bridges BACKLOG.md to the SAM planning pipeline — use when you want to pick a backlog item and move it into a SAM plan. No args shows interactive backlog browser with grooming status; with args finds item by title substring, auto-grooms if needed, runs RT-ICA to BLOCK on missing inputs before SAM planning, invokes add-new-feature, then updates backlog with plan reference. STOPS if item already has a Plan field or RT-ICA returns BLOCKED.

tools-only Bundle

Produce a context manifest for a backlog item — discovers related skills, agents, prior work, and dependency graph; performs RT-ICA assessment if not pre-computed by orchestrator. Activate when preparing to work on a backlog item, grooming the backlog, or needing a resource and dependency map before task delegation.

tools-only Bundle

Produce groomed content for a backlog item — discovers related skills, agents, prior work, and dependency graph; performs RT-ICA assessment; outputs groomed item template for writing into .claude/backlog/{priority}-{slug}.md. Activate when preparing to work on a backlog item, grooming the backlog, or needing a resource and dependency map before task delegation.

tools-only Bundle

Azure governance discovery subagent. Queries Azure Policy assignments via REST API (including management group-inherited policies), classifies policy effects, and returns structured governance constraints. Isolates heavy REST API work from the parent Bicep Plan agent's context.

thedixitjain Bundle

When the user wants to plan, design, or implement an A/B test or experiment, or build a growth experimentation program. Also use when the user mentions "A/B test," "split test," "experiment," "test this change," "variant copy," "multivariate test," "hypothesis," "should I test this," "which version is better," "test two versions," "statistical significance," "how long should I run this test," "growth experiments," "experiment velocity," "experiment backlog," "ICE score," "experimentation program," or "experiment playbook." Use this whenever someone is comparing two approaches and wants to measure which performs better, or when they want to build a systematic experimentation practice. For tracking implementation, see analytics. For page-level conversion optimization, see cro.

tools-only Bundle

Define explicit triggers for escalating to human at each stage (not just Discovery). When should agents block and ask vs attempt repair vs fail?

tools-only Bundle

Current architecture has BACKLOG.md as primary source of truth with GitHub Issues as a secondary mirror. This is inverted — only works for one agent in one repo clone. A second session, different machine, or teammate sees stale markdown files. Redesign so GitHub Issues + Projects are the backend (available from anywhere) and local .claude/backlog/ files are a derived read cache rebuilt on demand. Key changes: (1) add creates GitHub Issue first, writes local cache from response, (2) list queries gh issue list with label filters, caches locally for speed, (3) update does gh issue edit first then updates cache, (4) close happens via Fixes #N in PR — GitHub auto-closes on merge, no manual skill workflow needed, (5) status lives in GitHub labels not markdown fields, (6) priority lives in GitHub labels not markdown section headers, (7) plan artifacts attached as issue comments or linked in body, (8) groomed content written into issue body expandable sections. Add pull/push commands: backlog.py pull fetches all open

thedixitjain Skill

Code To Prd

thedixitjain Bundle

When the user wants to generate, iterate, or scale ad creative — headlines, descriptions, primary text, or full ad variations — for any paid advertising platform. Also use when the user mentions 'ad copy variations,' 'ad creative,' 'generate headlines,' 'RSA headlines,' 'bulk ad copy,' 'ad iterations,' 'creative testing,' 'ad performance optimization,' 'write me some ads,' 'Facebook ad copy,' 'Google ad headlines,' 'LinkedIn ad text,' 'static ads,' 'static ad concepts,' 'ad templates,' 'iMessage ad,' 'chat reveal ad,' 'fake DM ad,' 'ChatGPT ad,' 'Apple Notes ad,' 'AirDrop ad,' 'creative strategy,' 'creative roadmap,' 'creative retro,' 'hook writing,' 'creative review page,' 'present ad creative for approval,' 'motion video ad,' 'faceless video ad,' 'animated explainer ad,' 'motion collage ad,' or 'I need more ad variations.' Use this whenever someone needs to produce ad copy at scale...

thedixitjain Bundle

When the user wants to plan a content strategy, decide what content to create, or figure out what topics to cover. Also use when the user mentions "content strategy," "what should I write about," "content ideas," "blog strategy," "topic clusters," "content planning," "editorial calendar," "content marketing," "content roadmap," "what content should I create," "blog topics," "content pillars," or "I don't know what to write." Use this whenever someone needs help deciding what content to produce, not just writing it. For writing individual pieces, see copywriting. For SEO-specific audits, see seo-audit. For social media content specifically, see social.

thedixitjain Skill

Azure API Center SDK for .NET. Centralized API inventory management with governance, versioning, and discovery.