Productivity

jfcrenshaw Bundle

Ecosystem-level guide to the DESC (Dark Energy Science Collaboration) Python stack. Covers which tools exist, how they fit together, general DESC coding conventions, and how to set up the shared DESC Python environment and Jupyter kernels at NERSC. Use this skill when the user is new to DESC or asks what DESC software exists; asks how DESC packages fit together; asks about cross-package data flow (e.g. TXPipe → sacc → Firecrown, or RAIL inside TXPipe); asks about general DESC coding conventions; needs to choose the right tool for a DESC analysis task; asks how to activate or install the DESC Python environment; asks about desc-python, desc-python-dev, desc-python-bleed, or other DESC Jupyter kernels; or asks a question spanning multiple DESC packages with no single obvious skill to invoke. For questions specific to a single package (ceci, TXPipe, RAIL, pyccl/CCL, pymaster/NaMaster, firecrown, photerr), prefer that package's dedicated skill instead.

dyoshikawa Skill

Commit current changes, push the branch, and create or update its pull request. Use when asked to commit, push, open a PR, update a PR, or complete that combined workflow.

mikiagent Bundle

Diagnose user-reported failures such as "this failed", "this sucks", "that didn't work", "wrong result", or repeated correction requests, then ask only high-value follow-up questions, inspect the failed trajectory and relevant Skill files, generate multiple evidence-grounded root-cause hypotheses, route the verified failure to the smallest owning layer, patch the owning Skill/reference/script/router when justified, validate the revision, rerun or forward-test the failed scenario, and record the lesson for future runs. Use when a Codex task or Skill produced a bad result and the user wants the system to learn from the failure rather than merely retry the same task.

bex-co Bundle

Ship pending changes on main by pulling with rebase, committing intentionally, and pushing to origin/main. Use only when the user explicitly invokes $ship or asks to ship or publish the current main branch.

opsmill Skill

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

opsmill Skill

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

mmlong818 Bundle

Design, refine, and package Codex skills from a user goal, an existing workflow, or a source repository. Use when Codex needs to create a new skill, improve an existing skill, turn repeated work into a reusable process, or adapt an external skill idea into a Codex-native format.

qoli Skill

Use when designing, reviewing, or editing code paths that might add fallback behavior. This project prefers explicit failure over hidden fallback; fallback code is forbidden unless the user explicitly requests it in the current task.

qoli Bundle

Forward the user's current task to a subagent running gpt-5.6-luna with max reasoning effort, then coordinate and verify its result. Use when the user explicitly invokes this skill or asks Codex to delegate, forward, or hand off a task to a Luna Max subagent.

vignesh-nagarajan-vn Bundle

Write or read a HANDOFF.md so a new session starts from a short state summary instead of re-exploring the repo. Use when wrapping up, when the user says handoff, pause, stop here, or continue later, when context is running out mid-task, and at the start of a session in a repo that already has a HANDOFF.md.

wzyn20051216 Skill

MATLAB R2026a testing, validation, and CI workflow for matlab.unittest, MATLAB Test, Simulink Test, coverage, artifact generation, GitHub Actions, and open-source reproducibility. Use whenever MATLAB work needs verification, regression tests, CI, GitHub publication, or acceptance criteria.

wzyn20051216 Skill

MATLAB R2026a robotics and autonomy workflow for ROS Toolbox, Robotics System Toolbox, Navigation Toolbox, UAV Toolbox, sensor fusion, trajectory planning, simulation, and reproducible robot experiments. Use for ROS/ROS 2 bags, robot models, path planning, SLAM, state estimation, and autonomy prototyping.

wzyn20051216 Skill

MATLAB R2026a workflow for control systems, system identification, robust control, MPC, Simulink Control Design, parameter tuning, constrained optimization, and numerical validation. Use whenever the user asks for controllers, transfer functions, state-space models, tuning, identification, optimal control, or solver-based engineering.

caiyujie007 Skill

Xilinx Vivado tool workflow for project-mode RTL synthesis with preserved Vivado projects, DRC/timing/utilization reports, xvlog/xelab/xsim simulation, WDB waveform database generation and scripted querying, WCFG waveform view generation or cleanup, and Vivado Tcl automation. Use only when the task explicitly involves Vivado, xsim, xvlog, xelab, WDB, WCFG, Vivado Tcl, Vivado project-mode synthesis, or Vivado reports; pair with circuit-design-verification for tool-independent verification methodology.

caiyujie007 Skill

Open-source RTL checking and simulation workflow using Verilator, Yosys, Icarus Verilog, and GTKWave. Use when Codex needs to run or set up lightweight RTL syntax/lint checks, Yosys structural sanity checks, Icarus Verilog simulations, VCD/GTKWave waveform handoff, macOS Homebrew installation notes for these tools, or a reproducible open-source verification flow; pair with circuit-design-verification for tool-independent RTL intent and debugging methodology. Do not use for Vivado/xsim/WDB/WCFG flows.

caiyujie007 Skill

General digital circuit and RTL design/verification workflow for any EDA toolchain. Use for RTL design discipline, reusable primitive/library selection, synthesis/lint sanity checks, simulation timeout policy, deadlock diagnosis, TB-vs-RTL responsibility decisions, waveform evidence review, and per-test waveform organization; tool-independent across Vivado, VCS, DC, Verdi, and similar tools.

lza6 Skill

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

lza6 Skill

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

nmnmcc Bundle

Study deeply before anything. Use at the start of every task and again whenever the work reaches an important unknown, before answering, planning, judging, designing, coding, changing, deciding, or acting. Learn the real object, purpose, context, constraints, history, evidence, alternatives, and failure modes deeply enough for the stakes. Inspect primary material and actual behavior instead of relying on memory, first impressions, or fluent guesses. Keep study brief for clear, low-risk, reversible work; broaden and deepen it for unfamiliar, complex, contested, costly, or irreversible work. Continue learning from action and feedback.

nmnmcc Bundle

Just do it — and enjoy it! Use in every scenario and at every stage; recommended as the default for every task. Spot what matters, take the next useful step with a light heart, care for real risks, and celebrate a job well done.

s-hiraoku Skill

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Focuses on recently modified code unless instructed otherwise. This skill should be used when code-quality checks pass but the code would benefit from structural cleanup — deduplication, branching simplification, naming improvements, or dead-code removal. Invoked as a subagent from /code-quality or directly via the Task tool.

lipu-jpg Skill

Use when user wants to check writing progress, manage workflow stages, or resume interrupted tasks. Triggers include "工作流", "进度", "阶段", "写作流程".

rsign1279 Skill

Executes a single unit of delegated work that needs real per-instance judgment, multi-step tool use, or synthesis — but doesn't need frontier-level review. Use for the half of a delegated task too var­iable for bulk-executor but not important enough to keep at the orchestrator level — implementing a specified change per file where each file's context differs, reviewing content against a rubric that needs understanding rather than pattern-matching, or similar.

rsign1279 Skill

Executes a single, fully-specified, repetitive unit of work handed down from an orchestrator — an identical transform applied across many files, fixed-field extraction, classification against a set rubric, or similar pattern-following tasks with no open judgment calls. Use for the mechanical, high-volume half of a delegated task, never for anything requiring synthesis or ambiguity resolution.

0x0w1 Skill

Use for ordinary implementation tasks in this repository that should start from develop, create a feature/fix/chore branch, complete changes and tests, squash-merge the branch back into develop locally, and push develop. No pull requests.

postpartum-genushyacinthus29 Bundle

Maintain or assess Workflow Foundation-based solutions on .NET Framework, especially where long-lived process logic or legacy designer artifacts still matter.

aborroy Skill

Workflow BPMN Validator

zaxbyhub Skill

Mandatory publication protocol for the GitHub Copilot coding agent and custom Copilot agents in ragappv3. Load when assigned to an issue or when committing, pushing, opening/updating/readying a PR, or closing out remote CI. Routes to the single canonical commit-pr source of truth.

neversight Bundle

Diagnose NeverC runtime tests that fail only or intermittently in CI. Use for platform-specific crashes, signals, nondeterminism, or local/runner divergence; not ordinary build errors or workflow configuration failures.

sethdford Skill

Spin up a native Claude Code Teams fleet to tackle a multi-step task — lead orchestrates, specialists work in parallel worktrees, critic + verifier loop guards quality. Use when the task has 3+ independent sub-tasks, when you need different specialists, or when isolation between concerns is required. Triggers on /team, "spin up a team", "fan out", "fleet this".

different-ai Bundle

Enforce a worktree-per-task workflow with regular commits and pushes. Triggers when user mentions: - "create a worktree" - "commit regularly" - "push changes"

dceoy Skill

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

dceoy Skill

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

bcgov Bundle

BC Gov hardening patterns for GitHub Actions workflows — deny-all `permissions: {}` baseline with per-job step-ups, first-party tag vs third-party SHA pinning, fork-gate, single results-aggregator required check, pinned ubuntu-24.04 runners, script-injection-safe env handling, and signed-commit ruleset interaction. Covers `.github/workflows/*.yml`, `dependabot.yml`, and the branch-protection / repository-ruleset settings that pair with them. Use when authoring or reviewing a workflow in a BC Gov repo, debugging permission-denied errors, or onboarding Dependabot.

bhoon716 Bundle

Use when the user needs a specific repeatable workflow. Describe the trigger clearly. Do not use for unrelated tasks, simple factual Q&A, or requests that should be handled directly without this workflow.

dansnow Skill

Systematically debug a problem using a four-phase workflow