Product & Planning

kdevos12 Bundle

Use when working with DeepChem for molecular machine learning, drug discovery, quantum chemistry, materials science, or bioinformatics. Handles molecular datasets, featurization strategies, model training/evaluation, and predictions on chemical data.

kdevos12 Bundle

Use when working with TorchDrug for graph-based drug discovery and molecular ML. Covers molecular property prediction, protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, and GNN architectures on chemical data.

kdevos12 Bundle

Use when computing free energy differences for drug discovery. Covers FEP/TI/BAR/MBAR theory, alchemical transformations with OpenMMTools, relative binding free energy (RBFE) protocols, absolute binding free energy (ABFE), pymbar analysis, convergence diagnostics, and standard state corrections.

kdevos12 Bundle

Use when working with pharmacophore modeling for drug discovery. Covers feature types (HBD/HBA/AR/HYD/POS/NEG), RDKit 2D/3D pharmacophore fingerprints and matching (Pharm2D, Pharm3D, ChemicalFeatures), structure-based pharmacophore from protein-ligand complexes, ligand-based pharmacophore from active sets, and pharmacophore-based virtual screening workflows.

deanpeters Bundle

A descriptive model of a person (user, stakeholder, team member, etc), this tool is most often used to help a team define and understand the needs of its customer.

deanpeters Bundle

Look across stakeholders and categorize them according to key variables (e.g., interest, influence, impact).

deanpeters Bundle

Use this canvas to quickly categorize and prioritize which stakeholders to engage based on power and impact. Highlight impacted stakeholders and ideate on how to elevate their roles on the effort

deanpeters Bundle

Ideate a more comprehensive & representative set of relevant stakeholders to your project.

deanpeters Bundle

A quick way to begin developing a plan for effectively engaging a stakeholder.

happier-dev Bundle

Implement, change, build, fix, refactor, migrate, or apply accepted review findings in the Happier repositories with canonical-owner discovery, scope-preserving solution economy, TDD, efficient execution, affected-corridor completeness, risk-appropriate QA, and evidence-backed closeout. Use for repository source changes whether or not they are backed by an approved plan; pair with happier-implement-plan when executing an approved repository plan.

huang-sir1 Bundle

Use when designing or auditing an LLM Agent that automates medical-imaging research tasks such as literature and dataset discovery, protocol planning, evidence-grounded RAG, analysis orchestration, reporting checks, manuscript workflows, and reproducible artifact handling. Covers tools, multi-agent roles, memory, state, checkpoints, human approval, prompt injection, data exfiltration, citation accuracy, task-success evaluation, cost, and latency. Excludes autonomous clinical diagnosis, treatment recommendation, and patient-specific decision-making.

itsjavi Bundle

Author plans and native records for existing Backlog.md projects, using their configured MCP or CLI workflow. Use for planning requests or task, milestone, decision, and doc updates only when the project already contains a backlog/ directory belonging to Backlog.md. Does not apply without that directory and does not initialize Backlog.md.

karasukaigan Skill

将当前对话上下文转换为 PRD 并将其发布到项目问题跟踪器。当用户想要从当前上下文创建 PRD 时使用。

karasukaigan Skill

沿两个轴审查自固定点（提交、分支、标签或合并基础）以来的更改——标准（代码是否遵循此仓库记录的编码标准？）和规范（代码是否符合原始 issue/PRD 的要求？）。在并行子代理中运行两个审查并并排报告它们。当用户想要审查分支、PR、进行中的更改或要求"审查自 X 以来"时使用。

karasukaigan Skill

使用示踪弹垂直切片将计划、规范或 PRD 分解为项目问题跟踪器上可独立获取的问题。当用户想要将计划转换为问题、创建实施工单或将工作分解为问题时使用。

karasukaigan Bundle

在 AGENTS.md/CLAUDE.md 中设置 `## Agent skills` 块和 `docs/agents/`，以便工程技能了解此仓库的 issue tracker（GitHub 或本地 markdown）、分类标签词汇和领域文档布局。在首次使用 `to-issues`、`to-prd`、`triage`、`diagnose`、`tdd`、`improve-codebase-architecture` 或 `zoom-out` 之前运行——或者如果这些技能似乎缺少关于 issue tracker、分类标签或领域文档的上下文。

kyu-n Skill

Use when writing libGDX Java/Kotlin code involving gamepad or controller input — gdx-controllers extension, Controller discovery, ControllerListener events, ControllerMapping for cross-controller button/axis mapping, dead zones, or multi-controller support. Use when debugging controller not detected, wrong button mappings, or stick drift.

oegeyilmaz9 Bundle

Measure repeatable AI-search mention, citation, answer accuracy, cited-source share, referral, retrieval traces, citation-to-claim support, uncertainty, and non-causal drift from a frozen, hash-pinned Query Corpus and contract-valid Research Pack. Use for AI visibility baselines, repeated engine/surface observations, citation monitoring, grounding-query or consulted-source capture when disclosed, access-gap reporting, or comparison runs. Do not use for live research, query discovery, optimization, access-control bypass, rankings, guarantees, or causal attribution.

opendatadiscovery Skill

Show current progress of the audit and implementation system — scanner completion, backlog counts, blockers.

opendatadiscovery Skill

Convert raw scanner findings into atomic work items in the backlog. Assigns priority, category, effort, and identifies file conflicts.

opendatadiscovery Skill

Work a batch of backlog items end-to-end as a maintainer — hold the Implementation Quality Bar, run the Pre-authoring stance check, log follow-ups on disk, flip items to `review-ready`, and ship one PR per repo per batch.

pablolira-1982 Skill

OmniRoute exposes an A2A (Agent-to-Agent) JSON-RPC 2.0 server with 5 skills (smart-routing, quota-management, provider-discovery, cost-analysis, health-report). Use when the user wants OmniRoute to act as an agent peer in an A2A network or multi-agent pipeline.

soulmachine Skill

Generate FEATURES.md at the repo root by reading CONTEXT.md and docs/adr/, then enumerating the user-facing features the domain implies. Use after /grill-with-docs has settled the domain language and before /to-prd writes per-feature specs. Bridges the product→engineering gap between domain understanding and feature specification — the missing step that mattpocock's chain doesn't cover natively.

soulmachine Bundle

Orchestrates the full five-stage flow from raw idea to shipped PR — grill-with-docs → to-prd → to-issues → triage → worktree+planning-with-files. Each stage answers one question (What do I want? / What does done look like? / What are the units of work? / What's actionable? / Build it). Use when the user has an idea but no spec yet, wants to plan a feature end-to-end, says "let's PRD this," asks "how do I start on this idea?", or grabs a ready-for-agent issue to implement.

spillwavesolutions Skill

Promote a Discovery, Experiment, or Meeting into a formal Requirement, Feature, Specification, Design, or DecisionRecord while preserving originates_from / informs provenance. Use when informal knowledge is ready to become durable product structure.

spillwavesolutions Skill

Capture Slack/Discord/chat thread paste as Meeting or Discovery. Scrubs secrets/PII. Use when user pastes a conversation.

spillwavesolutions Skill

Capture research, competitive scans, user findings, and discovery notes as OKF Discovery concepts with source, confidence, and informs links. Use for research dumps, market scans, and exploratory findings.

syncable-dev Skill

Use official hosted Memtrace documentation before guessing, web search, or stale local copies. Trigger when the user asks how Memtrace works; how to install, configure, or deploy CLI, MCP, fleet, Cortex, or enterprise MemDB; what tools, skills, or commands exist; wants to find or locate official docs for a topic; or provides/asks to read a full docs page or slug. Routes internally across ask_docs for cited natural-language answers, search_docs for page discovery, and read_doc for complete page text. Separate from memtrace-first, which searches the user's indexed source code.

syncable-dev Skill

Route code discovery, debugging, flow tracing, how-code-works questions, and pre-edit rationale checks in indexed source-code repos to Memtrace graph plus Cortex decision tools. Use first before searching/reading code, and before editing, refactoring, deleting, or re-picking an approach that may have a recorded decision, ban, convention, or contract. Do not use Grep, Glob, rg, find, or manual file browsing for code discovery when Memtrace is indexed. Zero results are not permission to grep; diagnose/reindex with Memtrace.

syncable-dev Skill

Find source code with Memtrace hybrid BM25+semantic search: symbols, functions, classes, types, constants, definitions, implementations, logic, or error strings inside code. Use when the user wants to find, search, locate, or look up code or asks where code lives. Do not use Grep, Glob, rg, find, or manual file search for code discovery. If Memtrace returns 0 results, broaden the Memtrace query and diagnose/reindex; do not switch to grep.

taxueseek Bundle

职业系统——从方向探索到入职转正的完整职业生命周期管理。覆盖不同行业与人群。轻引导、重激活、强收敛。Career system: full lifecycle from direction discovery to onboarding. When to use / 适用场景: 职业规划、找工作、简历、面试、Offer、谈薪资、渠道、内推、入职、试用期、离职、转行、求职失败复盘、面试被拒、投递没回音、跳槽、应届求职、转行、大龄求职、远程工作。 EN: "career planning", "job hunting", "resume", "interview prep", "salary negotiation", "offer decision", "career change", "rejected after interview". Not for / 不适用: 查具体在招岗位（地区/学历/企业类型）→ taxue-job-search。行业分析 → taxue-industry。

jarrydadaens Bundle

Use this skill to turn the story backlog (an unscheduled story inventory, informally "Milestone -1") and the Design doc's Milestones Index into a scored, dependency-ordered story list inside a Milestone document, and to keep the backlog itself alive over time. Use it to pull backlog stories into a fresh milestone's story list, or to refine an existing milestone whose story list has grown past a sensible scope and needs stories shunted into Deferred / Follow-up Work. Calls the rails-grade-cer skill for scoring rather than reimplementing it, and promotes epic-sized backlog items into their own Milestone documents when CER exposes them. Not model-invocable — the user calls this by name when they are ready to plan or refine a milestone's story list; it does not trigger itself on ambient planning conversation.

jarrydadaens Bundle

Use this orchestration skill when turning stories, feature descriptions, backlog items, or design notes into many implementation-plan documents. The Boss builds a durable planning queue, dispatches one subagent per story or feature cluster, writes plans, updates progress, and repeats until complete.

jarrydadaens Bundle

Use this orchestration skill when building a Mermaid diagram of a large object-oriented codebase from a user-supplied entry point or query. The Boss coordinates scout discovery, parallel mapper chunks, validation, aggregation, and artifacts under documentation/workflows/mermaid_mapper.

jarrydadaens Bundle

Use this skill when updating a project derived from Agentic Rails so its project-local context files, templates, front matter, framework metadata, and standard documentation structure stay aligned with a local checked-out agentic_rails_context_starter source of truth. Use when refreshing derived Agentic Rails projects from the current milestone-centric starter without overwriting project-specific design, milestones, backlog stories, historical implementation plans, or provenance. Includes a compatibility layer that migrates projects still on an older, legacy context layout (a single milestones.md, goals files, a tier0/ or Documentation/ root, or a prior generation where milestones only indexed stories kept elsewhere) forward to the current context tier system.

jarrydadaens Bundle

Use this orchestration skill when implementing work from design documents, milestone documents, backlog stories, or implementation plans. The Boss reads the supplied documents, builds a durable story/work queue, dispatches one subagent per story or tightly bound plan slice, enforces specialist agents when required, updates progress, and repeats until the requested work is done or blocked.