Product & Planning

dragoon0x Skill

Keep the backlog useful instead of letting it become a graveyard of ideas nobody will build. Covers backlog hygiene, grooming practices, and knowing when to kill items. Use when the backlog has hundreds of stale items, sprint planning takes forever, or the team doesn't trust the backlog.

dragoon0x Skill

Get buy-in and drive alignment when you have no direct power over the people you need to move. Covers stakeholder framing, pre-wiring decisions, and building credibility over time. Use when pushing for a direction without exec authority, navigating disagreements, or when a proposal keeps getting blocked.

dragoon0x Skill

Score and rank product initiatives using RICE, ICE, and value-effort frameworks. Makes prioritization transparent and defensible while acknowledging that math doesn't remove all judgment. Use when the backlog is growing, stakeholders disagree on priorities, or you need to justify decisions to leadership.

metagit-ai Skill

CLI-only shortcuts for metagit agents — workspace catalog, discovery, prompts, sync, layout, and config. Use instead of MCP or HTTP API when operating from a shell or agent_mode session.

metagit-ai Bundle

Use when generating or refining local .metagit.yml files using deterministic discovery plus MCP sampling or CLI-only fallbacks.

metagit-ai Skill

Refresh or bootstrap `.metagit.yml` using deterministic discovery and validation flows. Use when configuration is missing, stale, or incomplete for workspace operations.

sandeco Bundle

Orquestrador greenfield do Reversa: da ideia em linguagem natural a brainstorm, personas, PRD e specs SDD em `_reversa_sdd/`. Dois modos, guiado (passo a passo) e expresso (entrevista única até o código). Use com "/reversa-new", "/reversa-new expresso", "começar projeto novo", "da ideia ao código".

sandeco Bundle

Esboça a abordagem técnica como delta sobre o legado, gerando roadmap, investigation, data-delta, onboarding e interfaces da feature ativa. Terceiro skill do ciclo forward, depois de `/reversa-requirements` e (opcionalmente) `/reversa-clarify`.

sandeco Bundle

Editor-chefe do Time Reversa Docs. Gera index.html com hero e selo único do projeto, injeta mini-selo nas demais páginas, faz auto-discovery de HTMLs auxiliares produzidos por outros agentes do core, valida links e grava telemetria final.

snowflake-labs Bundle

Analyzes workloads to be migrated to Snowflake using SnowConvert assessment reports. Routes to specialized sub-skills for high-quality assessments. Use this skill when user wants to do an assessment of their code or ETL workload, waves generation, object exclusion, effort estimates, anti-patterns, discovery (SQL Server), sql dynamic and/or ETL analysis (SSIS)

snowflake-labs Bundle

Builds SQL Server Discovery from Extended Events `.xel` files by running `scai assessment workload-insights --input <file>`. SQL Server only. Reads captures in place.

snowflake-labs Bundle

Phase-based orchestrator for fixing SnowConvert ETL conversion gaps in ETL-to-Snowflake migrations (SSIS, Informatica, and other platforms). Analyzes units holistically, creates a ROADMAP with test strategies, and executes fixes through phased TDD with cross-phase learning. Use when user says "fix ETL unit", "fix SSIS conversion", "fix Informatica conversion", "resume ETL fixing", "run next phase", or when processing a converted ETL unit folder containing orchestration SQL, optional dbt sub-projects, and the original source definition file (e.g., DTSX for SSIS, XML for Informatica). Do NOT use for non-ETL migrations or greenfield dbt projects.

snowflake-labs Bundle

Generate AAA orchestration tests (isolated or grouped) for ETL-to-Snowflake elements. Scoped to elements assigned to the current phase in ROADMAP.md. Use when the stabilization skill invokes test generation for an orchestration phase.

dtsong Bundle

Use when turning a hunch into a shipped change here, deciding if a claim survives adversarial refutation before trusting it, writing a predicted number/exit-code/pass-rate before running an experiment or eval, tracing an idea through council deliberation, PRD non-goals, a numbered acceptance contract, gated /ship or /looper execution, to verified or retired, or picking settings.local.json as the experiment lane instead of settings.json. Not for measurement techniques (mcs-analysis-toolkit) or formal evidence tiers and AC mechanics (mcs-validation-and-qa).

dtsong Skill

Use when producing a repository health dashboard covering CI, issues, and PR backlog status.

timdevai Skill

prd-builder

lgwanai Skill

Review and promote backlog items to active milestone

clawic Skill

Change the public agent-facing CLI surface while preserving registry-backed discovery, JSON envelopes, aliases, docs, and tests.

jaechang-hits Skill

Cloud quantum chemistry platform with Python SDK. Run geometry optimization, conformer generation, torsional scans, and energy minimization (DFT/semiempirical), and retrieve properties (dipole, partial charges, frontier orbitals) — no local QC software or HPC needed.

jaechang-hits Bundle

Deep learning for drug discovery. 60+ models (GCN, GAT, AttentiveFP, MPNN, ChemBERTa, GROVER), 50+ featurizers, MoleculeNet benchmarks, HPO, transfer learning. Unified load-featurize-split-train-evaluate API. For fingerprints use rdkit-cheminformatics; for featurization-only use molfeat.

jaechang-hits Skill

Diffusion-based docking that predicts protein-ligand poses without a predefined site. Use for blind docking, when traditional docking fails, or exploring multiple binding modes. Pipeline: prep protein (PDB) and ligand (SMILES/SDF), run inference, analyze confidence-ranked poses.

jaechang-hits Skill

PyTorch-based ML platform for drug discovery: graph molecular representation learning, property prediction (ADMET, activity), retrosynthesis, drug-target interaction (DTI), and pretraining on large molecular datasets. Provides GNN layers (GraphConv, GAT, MPNN), pretrained models, and benchmark datasets.

jaechang-hits Skill

Query openFDA REST API for adverse events (FAERS), labeling, product info, recalls, enforcement. Search by drug name, ingredient, MedDRA, or NDC. 1k req/day no key; 120k with free key. For trials use clinicaltrials-database-search; for structures use drugbank-database-access or chembl-database-bioactivity.

jaechang-hits Skill

Query the ZINC22 virtual compound library (CartBlanche API, billions of make-on-demand + purchasable molecules). Look up substances by ZINC ID, resolve a SMILES to its ZINC ID (exact match), inspect purchasability/catalogs, and assemble compound sets for docking. Property (MW/logP) filtering is done locally with RDKit. For bioactivity use chembl-database-bioactivity; for approved drugs use drugbank-database-access.

jaechang-hits Skill

Retrieve mouse phenotype data from the Jackson Laboratory Mouse Phenome Database (MPD) via its REST API. Browse 520+ projects, look up per-project measure metadata, pull strain-level means (raw or LS-mean adjusted) and per-animal values, find measures by MP/VT ontology terms, and resolve strain nomenclature or gene coordinates. Use for QTL support, cross-strain comparison, mouse model selection, and ontology-driven phenotype discovery. Use monarch-database for disease-gene-phenotype knowledge graphs; ensembl-database for mouse genome annotations.

systempromptio Skill

Build standalone CLI extension binaries for systemprompt.io with clap, manifest discovery, and subprocess integration

jylhis Skill

Turn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.

jylhis Skill

Update, create, or reprioritize your product roadmap. Use when adding a new initiative and deciding what moves to make room, shifting priorities after new information comes in, moving timelines due to a dependency slip, or building a Now/Next/Later view from scratch.

jylhis Skill

Plan a sprint — scope work, estimate capacity, set goals, and draft a sprint plan. Use when kicking off a new sprint, sizing a backlog against team availability (accounting for PTO and meetings), deciding what's P0 vs. stretch, or handling carryover from the last sprint.

charlesmu99 Bundle

---

edmundmiller Bundle

Starts isolated Codex worktree threads for dependency-aware Beads work. Use when explicitly asked to split a Beads backlog into separate implementation threads.

epicenterhq Bundle

Audit Codex tasks and preserve unowned outcomes in `BACKLOG.md` while closing completed or superseded chats. Use when Codex task ownership or archive state needs cleanup, not generic issue-tracker or project-backlog work.

peopleforrester Skill

Patterns for Claude Code to learn from project context and improve over time. Covers CLAUDE.md refinement, error pattern recognition, codebase conventions discovery, and feedback incorporation. Use to optimize Claude Code's effectiveness across sessions.

redpanda-data Skill

Turn current context into a PRD and publish it to issue tracker.

redpanda-data Skill

Break PRD or plan into tracker issues as thin vertical slices.

redpanda-data Bundle

Install planning/project management skills -- PRD creation, implementation planning, issue breakdown, bug triage, code review. Use when setup project planning workflows or creating PRDs.