Productivity

bkywksj Skill

Git 工作流与版本管理技能，规范分支策略、提交信息和发布流程。 触发场景： - 用户需要创建分支或合并代码 - 用户需要规范提交信息格式 - 用户需要管理版本发布流程 触发词：Git、分支、提交、合并、版本发布

bkywksj Skill

任务跟踪与进度管理技能，管理开发任务的创建、分解、状态更新和归档。 触发场景： - 用户需要创建或查看开发任务 - 用户需要更新任务进度或状态 - 用户需要归档已完成的任务 触发词：任务、进度、待办、TODO、跟踪

lidessen Bundle

Move a non-trivial task through practice, observation, reflection, and the next smallest test without forcing a generic plan or feedback artifact. Use when a phase ends, an implementation or investigation must inform its next move, a prior attempt failed or produced ambiguous evidence, work is being resumed, or the user asks to turn results into the next bounded action. Do not use as a mandatory preflight for routine one-step work or when a more specific methodology already owns the live judgment.

lidessen Bundle

Prepare an evidence-backed strategic recommendation when a project phase has settled, material conditions changed, or a human asks for short-, medium-, and long-horizon direction. Synthesizes verified phase evidence into a proposed Strategy Case with a principal contradiction, strongest preservation case, rolling horizons, mission candidates, and replan signals. It advises only: humans approve commitments, and Work Cells or other owners execute them. Do not use for ordinary task planning, implementation sequencing, or automatic portfolio management.

lidessen Bundle

Run bounded, multi-round improvement of a real product or UI: observe a representative user task, decide whether a complex page or surface is necessary, choose the smallest useful change, implement it through the owning skill, and verify the changed experience in the browser before selecting the next practice. Use when asked to "多轮走查", "迭代改进 UI", "全面检查页面并持续修复", "这个复杂页面是否有必要", or to continue from an earlier product review. Do not use for a single read-only product review, visual direction formation alone, or implementation without live product evidence.

agentsorg Bundle

Use when designing notification surfaces: toasts, badges, push, inbox, frequency and batching, priority, quiet hours, and transactional email layout.

cosmicstack-labs Skill

Git best practices, branching strategies, commit conventions, and code review patterns

deanpeters Bundle

Define AI responsibilities, human judgment, review, decision authority, escalation, and learning in a recurring workflow. Use when human-AI collaboration is vague or unreliable.

deanpeters Bundle

Convert a proven, improved workflow into a governed, reusable skill with context, decisions, examples, guardrails, evaluations, ownership, and maintenance rules.

deanpeters Bundle

Turn a tested human-AI workflow into an inspectable playbook with context, roles, decisions, examples, controls, measures, fallback, and improvement ownership.

deanpeters Bundle

Run a recurring review of AI behavior, workflow, human, outcome, control, incident, and affected-party evidence to continue, change, constrain, roll back, or retire.

deanpeters Bundle

Diagnose role capability, applied learning, workflow adoption, stewardship, and outcome evidence; recommend the next capability-building motion rather than more generic training.

deanpeters Bundle

Review one AI initiative across value, economics, dependencies, workflow, context, evaluation, governance, controls, capability, and recovery before a material decision.

deanpeters Bundle

Identify which product-team decision or productive workflow should be redesigned with AI first, based on outcome value, friction, evidence, consequence, and readiness.

getsentry Skill

Search, fetch, create, update, and move Notion pages and data sources. Use when users ask to look up docs, specs, notes, meeting notes, project context, roadmaps, trackers, or internal references stored in Notion, or when they explicitly ask to create or edit Notion content.

graph-robots Bundle

Segment Anything 3 — text-, point-, and box-prompted instance segmentation, plus a stateful streaming video tracker that carries object identity through SAM3's memory bank. Use when a workflow needs open-vocabulary masks from an RGB image or needs to follow one object across frames.

graph-robots Bundle

Ordered centrelines of deformable linear objects — skeletonises a cable, rope or hose mask, recovers one traversal order through occlusion breaks and self-crossings (TrackDLO's chain merge), back-projects the ordered pixels through depth onto the object's axis as an arc-length-parameterised polyline, and carries a known centreline onto the next frame with motion imputed for hidden stretches. Use when a workflow needs an ordered centreline of a cable, rope or hose from a mask and a depth frame, or must carry one through occlusion between frames.

graph-robots Bundle

NVIDIA cuRobo motion planning — collision-free trajectories to grasp goalsets, transport with an attached object, constrained linear moves, single-pose planning, geometric IK, batch grasp feasibility, and joint-trajectory collision validation. Use when a workflow needs GPU-accelerated, collision-aware arm motion plans.

graph-robots Bundle

Run the openpi π0.5 LIBERO checkpoint (pi05_libero) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSC_POSE action space from agentview + wrist cameras; the policy server is the bundle's own preset (no policy_id). Reads the graph-scoped observation_stream each window and terminates on a gripper open→close→open cycle, a VLM yes/no check, or max_windows. Use when a pick/place (or pick-and-drop-in-container) segment on tabletop rigid LIBERO objects is delegated to a learned policy — best steered (perceive + hover above the target) first. NOT for deformables/cloth folding, articulated objects, non-Franka embodiments, or tasks outside the LIBERO pick-place distribution.

graph-robots Bundle

Grounding DINO zero-shot object detection — natural-language queries to labeled 2D bounding boxes with confidence scores. Use when a workflow needs to locate named objects in an RGB image before segmenting or grasping them.

graph-robots Bundle

Run the MolmoAct LIBERO checkpoint (allenai/MolmoAct-7B-D-LIBERO-0812) as a closed-loop VLA policy for the dexterous pick-and-place segment of a task. Drives a Franka Panda in the LIBERO/robosuite OSC_POSE action space from agentview + wrist cameras, served behind a vLLM-style script speaking the openpi websocket protocol; the policy server is the bundle's own preset (no policy_id). Reads the graph-scoped observation_stream each window and terminates on a gripper open→close→open cycle, a VLM yes/no check, or max_windows. Use when a pick/place (or pick-and-drop-in-container) segment on tabletop rigid LIBERO objects is delegated to a learned policy — best steered (perceive + hover above the target) first; this is the MolmoAct alternative to pi05-libero for the same task family. NOT for deformables/cloth folding, articulated objects, non-Franka embodiments, or tasks outside the LIBERO pick-place distribution.

graph-robots Bundle

Direct IK align-then-descend grasping. The gripper pre-rotates to the grasp orientation at a safe height ABOVE the target before descending straight down, avoiding the twist-while-closing failure mode of a blended rotate+descend. The grasp rotation is rebuilt so the hand's declared closing axis (robot.describe_gripper, composed by robot.grasp_frame) closes across the target's short horizontal axis, and the hover clearance is the hand's own (robot.describe_workspace) unless the workflow pins it. Use when no trajectory planner (curobo) is deployed or the scene is uncluttered enough that a straight-line approach is safe.

graph-robots Bundle

Loop-head perception for pack-all / clean-all-items tasks. From ONE observation it localizes BOTH the destination container (basket, bin, box) AND the next remaining target item, using the pairwise VLM crop tournament with a container-excluding description so the target is never confused with the basket, then makes a clean found / none decision: an item was found (grasp it) or only the container remains (all items packed — exit the loop to done). Use when a workflow must pick up EVERY object and place each into a container in a loop (pack-all / clean-all-items) and each pass must reliably answer "is there still a graspable item, or are we done?" while also exposing a fresh container OBB for the downstream place. This subgraph is self-contained and takes NO inputs (inputs: {}); the container and item phrases are literal strings written inside the perception nodes, never subgraph parameters — do not declare item_name / container_name / item_description as subgraph inputs.

graph-robots Bundle

Discovers a labelled four-compartment destination from RGB-D and repeatedly perceives one remaining source object with its matching metric destination region, using an identity table the graph supplies for what each label looks like and what its graspable part is called. Use when a workflow must sort several visible objects into compartments identified by printed category labels.

graph-robots Bundle

Read a cable's ordered 3D centreline from one RGB-D frame and keep it current across a task — seed it from an unobstructed survey, re-fit it cold whenever the whole rod is in view, and fall back to tracking the carried prior only when the fresh fit comes back short. Use when a manipulation loop needs the current shape of a deformable linear object (a cable, rope, or hose) once per step rather than every frame, from a fixed third-person camera.

jonhill90 Bundle

Find out what has already been said — in transcripts, issues and PRs, the ledger, the notebook, and vault facts — before asking a question or stating a fact as current, and prefer live system state over any stored record when they disagree. Use before acting on a non-trivial request, right where you would otherwise ask something you could answer by looking, or restate a fact without rechecking it. Not for what the user wants (see determine-intent, which runs on the same "before acting" moment but asks the goal, not the record); not a deliberate periodic transcript sweep for new skill candidates (see mine-transcripts, which is scheduled, not per-task); not for judging whether a check or metric can be trusted once you have its verdict (see verify-the-instrument) — this skill decides which signal source to consult and which one wins when two disagree, not whether a given source's zero result is real.

jonhill90 Bundle

Load a large corpus, document set, or codebase the way an index is meant to be used — read the index first, pull individual files or facts in on demand as the task actually needs them, and stop once there is enough to act, instead of reading everything up front. Use before reading many files, an entire directory, or a large document set for a task that plausibly needs only a fraction of it.

jonhill90 Bundle

Turn a task list into groups several agents can execute concurrently without colliding — derive file ownership mechanically, then supply the judgement a file-intersection cannot: shared resources that are not files, dependencies stated only in prose, and what each group's gate must prove. Use when work will be split across concurrent agents or worktrees, or when reviewing such a plan before it runs. Not for deciding how many agents or what each may see (dispatching-subagents), not for testing whether the plan's reasoning holds (sanity-check), and not for whether a step should be a tool at all (mechanize).

jonhill90 Bundle

Ship a mechanism and its caller in the same change, and add the check that fails when a caller disappears — never leave a tested module, script, or gate that nothing invokes. Use when creating any new script, module, hook, workflow, or check, and when reviewing a change that adds one. Not for deciding whether a tool should exist at all (mechanize), whether a tool's verdicts can be trusted (verify-the-instrument), or whether to adopt an existing tool instead of writing one (adopt-or-build) — this is only about the gap between writing a mechanism and something actually calling it.

codejunkie99 Skill

Use when the user wants to draft a focused, action-oriented email and compare two tonal versions. Triggers include "draft an email", "write an email to", "compose an email".

codejunkie99 Skill

Use when the user wants to prepare for a high-stakes meeting with a clear opening, key points, questions, objection handling, and walk-away criteria. Triggers include "prep for a meeting", "meeting strategy", "how should I approach this meeting".

dennydkt Bundle

调用受用户配置约束：高自动、中先确认、低须明确开启；用户指定其他技能时禁止接管。处理会议全流程：判断是否需要开会、议程、主持、决策、纪要和会后追踪。用于会太多没结论、准备会议、整理纪要、推动行动项。触发：$xb-meeting、帮我开会/准备议程/写纪要。

deuxksy Skill

Use when the user asks to commit task-related Git changes while preserving unrelated or pre-staged work.

deuxksy Bundle

Notion [연구소 일정]과 Google Calendar [Life] 일정을 읽어서 Hermes에 동기화하는 단방향 READ 스크립트. 매일 08:00 cron 동기화, 일정 알림은 별도 크론잡.

deuxksy Bundle

Use when synchronizing a local planning/sprint-assignments.json Epic-Story-Task hierarchy to Notion 작업 pages, including dry-run mapping, duplicate detection, 상위 작업 relations, Sprint-derived 우선순위, or an explicitly selected 스프린트 relation.

googlecloudplatform Skill

Workflow for triaging, planning, fixing, and verifying reported provider bugs.