Productivity

alexanderop Skill

Review current changes with parallel subagents

alexanderop Skill

Interview me about the plan

alexanderop Skill

Review CodeRabbit comments on current PR and implement valid fixes

cluesmith Skill

Save an architect's state, clear its context, and re-init automatically — the packaged save→clear→re-init refresh cycle. Use when the owner directs a context refresh, or says "/arch-save", "save and clear", "refresh your context". Runs on the owner's direction; an architect does not invoke it autonomously mid-task. Counterpart to /arch-init, which recovers the state this writes.

cluesmith Skill

Refresh a builder's own context at a protocol boundary — save working state, verify it, clear, and re-orient. Use when porch emits a context-refresh task, or the builder is told to "refresh your context" / "run a self-refresh". A builder does not invoke this autonomously mid-task; porch chooses the moment. Counterpart to the architect's /arch-save.

contextgo Skill

Testing workflow and quality standards for writing and running tests. Use when: (1) Writing new tests, (2) Adding a new feature that needs tests, (3) Modifying logic that has existing tests, (4) Before claiming a task is complete.

contextgo Skill

Use when you have a written implementation plan to execute in a separate session with review checkpoints

contextgo Bundle

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

contextgo Bundle

Use when you have a spec or requirements for a multi-step task, before touching code

contextgo Skill

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification

contextgo Bundle

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

contextgo Bundle

Use when implementing any feature or bugfix, before writing implementation code

contextgo Skill

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

contextgo Bundle

Use when executing implementation plans with independent tasks in the current session

dlt-hub Skill

Improve existing skills based on the current session. Use at the end of a session (or when the user asks) to capture new debugging patterns, data issues, data validation tracks, querying techniques, doc references, or workflow improvements learned during the session. Keeps skills lean and personalized.

epam Skill

Execute the implementation planning workflow using the plan template to generate design artifacts.

epam Skill

Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.

green-pt Skill

Decide when to delegate to Honey's read-only subagents (hive-scout, hive-reviewer) instead of working inline, so the expensive tokens — large file reads and review passes injected back into the orchestrator's context — come back compressed (Honey Lever 3). Use when a task is search-heavy or review-heavy, spans many files, or you want to keep the orchestrator's context small. Not for trivial one-file work.

green-pt Skill

Rewrite a memory or context file (CLAUDE.md, AGENTS.md, a todo or notes file) into Honey-terse form so it costs fewer input tokens every session, without losing meaning. Backs up the original first. Use when asked to shrink or compress context files, trim CLAUDE.md, or cut per-session input cost. Prose only — never code, config, or data.

alexanderop Bundle

Use when you have a spec or requirements for a multi-step task, before touching code

cdeistopened Bundle

Write authentic, human-sounding emails that build relationships and drive action. This skill should be used when drafting welcome emails, follow-ups, newsletters, announcements, outreach, or any email communication. Integrates with human-writing principles to avoid AI tells. Particularly suited for community building, movement organizing, and personal relationship management contexts.

cdeistopened Skill

Structure an argument or position for maximum clarity and persuasive power using Zakery Kline's communication architecture from How to Think. Use when someone says 'help me make this argument', 'how do I persuade someone of X', 'structure this pitch', 'make this more convincing', 'I need to communicate this clearly', 'how do I present this case', 'help me write a persuasive email', 'build an argument for X', 'how do I convince my team', or 'what's the best way to present this'. Walks through progressive disclosure, rhetorical triangle balancing, and preemptive objection handling.

tfcbot Skill

Orchestrate Vidjutsu's tenant-scoped short-form clone workflow: stage a social source, check cloneability, create or reuse a character, compose the first frame, render with Kling 3.0, run QA, and finish post-production.

tfcbot Skill

Create a one-page channel spec — character, handle, format, niche, and 30-day content calendar for a managed account.

tfcbot Skill

Submit and monitor a Kling 3.0 Motion Control clone through Vidjutsu using a staged source video, a generated starting image, and a Vidjutsu-owned task ID.

thaitype Skill

Plan a new milestone or extend an existing one step-by-step with review gates. Starts with a grill-design session to clarify requirements, then walks through goal → contract → todo → task specs, pausing for user approval at each step.

xiaoyaotsyx-dotcom Skill

店小秘速卖通上品完整工作流——从采集箱到发布的所有模块编排、调用顺序、区域调价、保存发布

justmichael-80 Bundle

Use when you have a spec or requirements for a multi-step task, before touching code

atman-33 Skill

Guided onboarding for OpenSpec - walk through a complete workflow cycle with narration and real codebase work.

atman-33 Skill

Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.

atman-33 Skill

Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.

atman-33 Skill

Continue working on an OpenSpec change by creating the next artifact. Use when the user wants to progress their change, create the next artifact, or continue their workflow.

cachemoney Bundle

Task management for AI agents across context windows. Use when agents need to track work, log progress, hand off state, and maintain context across sessions. Includes workflows for single-issue focus, multi-issue work sessions, and structured handoffs. Essential for AI-assisted development where context windows reset between sessions.

charlesxjyang Skill

Use when the user is working with MACE machine-learning interatomic potentials (MLIPs), equivariant force fields, MACE-MP/MPA/OMAT/MATPES/OFF foundation models, ASE calculators from mace.calculators, MLIP geometry optimization, molecular dynamics, descriptors, fine-tuning, or training from extended XYZ energies and forces. Prefer MACE over generic neural-network or sklearn code when the task is atomic energy/force prediction with equivariant ML potentials.

charlesxjyang Skill

Use when the user is constructing automated materials-science workflows with jobflow, especially VASP, force-field, phonon, defect, elastic, or equation of state workflows around pymatgen Structures. Prefer atomate2 over hand-written shell scripts, old atomate/FireWorks patterns, or one-off subprocess loops when the task is workflow construction, job documents, makers, stores, or reusable computational campaigns.

charlesxjyang Skill

Use when the user is doing materials informatics, composition/structure featurization, Magpie-style descriptors, matbench-like tabular ML, or converting pymatgen compositions/structures into machine-learning features. Prefer matminer over hand-written periodic-table lookups or generic sklearn preprocessing when the task depends on materials-aware feature definitions, citations, or featurizer provenance.