Productivity

bkraad47 Skill

Hypothesis-driven fix/change workflow — consults the review-current-state factblock, forms an explicit guess at the root cause and fix, then updates code and tests to verify it scientifically. Use when asked to fix a bug, change behavior, or implement something against a specific target, with a documented, hypothesis-driven process rather than an ad hoc edit.

terrasnail Skill

Sets up a project so pipeshape pipelines run on it. Writes the commands block in CLAUDE.md, checks discipline skills and agents, and prepares the first saved workflow.

terrasnail Skill

Orchestration shapes as workflow script snippets. Use when composing a workflow that fans out, loops on review, routes by kind, verifies adversarially, or repeats until exhausted.

serialexperimentslainnnn Skill

Build and maintain PROJECTMAP.md, the orientation index of whatever repository you are working in, so the same grep/find/read is never paid for twice. Use at the very start of work in ANY repository - before the first substantial task - whenever PROJECTMAP.md is missing, whenever it is stale or contradicted by the repo, whenever you catch yourself searching for where something lives, whenever structure changes (new directory, moved module, different build/test command, new convention), and whenever you hand work over to another session or a subagent. Covers what goes in the map, what must never go in it, how to size it for a code repo versus a content repo, how to generate it cheaply with a script instead of by hand, how to keep it honest, and where to put it so it does not pollute a repository that is not yours.

serialexperimentslainnnn Skill

PHP engineering standards (modern PHP, Laravel, Symfony). Use when working with .php files, composer.json/composer.lock, artisan commands, phpunit.xml, phpstan.neon, psalm.xml, Blade/Twig templates, or any Laravel/Symfony project task (code, review, refactor, tests, CI).

serialexperimentslainnnn Skill

Derive and invoke the skills a task actually activates, before writing anything. Use at the start of every substantial task, and again whenever the work turns - the files being touched change family, a new layer enters (data, network, identity, money, personal data), the request moves from designing to operating, or you catch yourself asserting a version, flag, threshold or default from memory instead of from a document. Covers deriving the domains from the artefacts in the repo rather than from the words in the request, the always-on set that no request ever names, invoking each skill with the Skill tool rather than reading its file, reconciling several co-activated skills through their §1 boundary lines, declaring a contradiction instead of silently resolving it, and what to do when no skill owns the domain.

serialexperimentslainnnn Skill

Git branching, commit and release process standards. Use when working with branching strategy, Conventional Commits, rebase vs merge, PR size limits, CODEOWNERS, protected branches or rulesets, SemVer tagging, CHANGELOG, release-please/changesets/semantic-release/goreleaser, git-filter-repo, Git LFS, or GPG/SSH commit signing.

boxlogodev Bundle

This skill handles SAP PM (Plant Maintenance / 설비보전) including Equipment Master (IE01/IE02/IE03), Functional Location (IL01/IL02/IL03), Maintenance Notifications (IW21/IW22/IW23), Maintenance Orders (IW31/IW32/IW33), Preventive Maintenance (IP01/IP10/IP30), Task Lists (IA01/IA05), Maintenance Planning, and Plant Maintenance Reporting (IW28/IW29/IW38/IW39). Use when user mentions PM, 설비보전, 설비관리, equipment, 설비, maintenance order, 보전오더, 고장, breakdown, 고장코드, preventive maintenance, 예방보전, functional location, 기능위치, MTBF, MTTR, 점검, 정비, serial number, 시리얼, refurbishment, 재생정비, maintenance planning, maintenance strategy, 정비전략, equipment history, 설비이력, preventive tasks, 예방점검.

serialexperimentslainnnn Skill

.NET Framework 4.x legacy maintenance and the migration decision to modern .NET. Use when a project targets net45/net461/net462/net472/net48/net481, an old-style non-SDK .csproj/.vbproj with <TargetFrameworkVersion> and AssemblyInfo.cs, packages.config, web.config or app.config with system.web/system.serviceModel/machineKey/bindingRedirect sections, Global.asax, .aspx/.ascx/.asmx/.svc files, ASP.NET WebForms or MVC5 on System.Web, WCF ServiceHost and ServiceContract on the server side, Windows Workflow Foundation, .NET Remoting, AppDomain.CreateDomain, BinaryFormatter, the GAC and gacutil, COM interop with tlbimp/regasm, msbuild.exe with v4.0.30319 or Visual Studio 2019 solutions, and when deciding on .NET Upgrade Assistant, try-convert, SDK-style migration, PackageReference, .NET Standard 2.0 shims or CoreWCF.

ono-sendai-labs Skill

Drive an implementation plan to completion with the awo workflow orchestrator. Loops over plan steps, generating code tasks per step and running the awo implementer/reviewer loop on each task, bookmarking every produced change for PR generation and keeping a work log. Handles an escalated task by repairing the specification and task file in a separate, auditable commit interposed below the implementation, then resuming awo in rework mode — never by silently patching the divergence in code.

ono-sendai-labs Bundle

Autonomously implement a code task using test-driven development, following an Explore, Plan, Code, Commit workflow. Takes a structured code task file (from plan-to-tasks or interactive-coding-task) and produces a complete, tested implementation in a described jj change. Escalates to the user only when blocked by issues that require revisiting the task, plan, or design.

ono-sendai-labs Skill

Generate structured code task files from an implementation plan. Processes one plan step at a time, breaking it into logical code tasks with acceptance criteria. Use when the user has an implementation plan (from design-to-plan or similar) and wants to generate code task files for the next step.

ono-sendai-labs Skill

Convert a detailed design document into a structured, incremental implementation plan with a progress checklist. Use when the user has a completed design document and wants to create an actionable implementation plan, or when transitioning from the interactive-design workflow to implementation.

zerofaultlabs Bundle

Reconcile and run Spring Hills Church production work that is due or was missed while a Mac, ChatGPT desktop app, or local project was unavailable. Use for scheduled or manual Spring Hills heartbeats, offline catch-up, feedback collection, Sunday sermon processing, Tuesday inspiration scouting, deduplication, retrying incomplete work, and maintaining per-workflow checkpoints. Coordinate the installed Spring Hills content skills without replacing their editorial instructions.

ono-sendai-labs Skill

Interactively create structured code task files from rough descriptions, ideas, or ad-hoc requests. Use for smaller, well-scoped changes that don't need a full design-to-plan workflow — e.g., "address the TODO at auth.rs:45", "add input validation to the signup form", or "refactor the logging module to use structured logs".

peterson-benhame Bundle

Spec-driven feature work that freezes obligations instead of the plan: one human-reviewed plan with EARS criteria, path, entities, interface and one-way doors, then proof-backed checks, then build, then an independent Verifier. Use when the user says "pbs-spec-lean", "plan feature", "specify feature", "write the checks", "build this plan", or "verify work". Do NOT use for standalone design documents unattached to a feature, architecture decomposition analysis, or work that already has a task list or checklist to execute.

atomachinskiy Bundle

Работа с Яндекс.Календарём через CalDAV. Список календарей, события за период, поиск встреч. Auth через login + общий yandex-auth токен (как Basic). Triggers: yandex calendar, яндекс календарь, caldav, события, встречи, расписание, календарь.

vaibtan Bundle

Rebuild current working context for a topic from scoped Codex task history, repository state, and available shared records. Use for $recall, catch-me-up requests, or resuming earlier work.

vaibtan Bundle

Review a completed or long-running task for reusable workflow lessons and propose focused skill improvements. Use only when the user asks to reflect or capture lessons.

vaibtan Bundle

Run a rigorous pstack engineering workflow in Codex. Use when the user invokes $poteto-mode or asks for pstack-style investigation, implementation, verification, review, shipping, or sustained autonomous work.

xjli360 Bundle

Walk a new FBA inbound shipment through hazmat and battery declaration, prep ownership, packing type, quantity consistency, carton size and weight limits, carton sturdiness and shipment-label placement, reading back each field against the current Seller Central workflow before the cartons leave the factory. Use for FBA 货件怎么建、带电池要不要申报、预处理方选谁、混装还是原厂包装、外箱尺寸限制、箱子被压变形多收费、箱标和快递单区别、轻小商品计划条件. Do not use for first-leg forwarder selection or customs paperwork, and never to game split-shipment allocation by misreporting quantities.

vaibtan Bundle

Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for $figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

maystroh Bundle

Generate breast-region and nipple-location masks for sagittal breast MRI NIfTI files, including folder batches, inspect every slice in 3D Slicer, and export timestamped Astra labelmaps. Compare user-reviewed annotation folders with original exports and update learned preferences. Use for this user's breast MRI annotation and correction workflow.

tiennguyen1203 Skill

Implements a plan, spec, or design doc by breaking it into small digestible chunks — working with the user to clarify, implement, and verify each one before moving on. Visualizes every change so the user stays fully informed and understands what was built and why. Use this skill whenever a user wants to implement a plan and you want to make sure they understand everything being built. Trigger on phrases like "implement the plan", "let's build this step by step", "execute this plan", "start implementing", "work through the design doc", or when picking up a plan from docs/plans/. Also use proactively when a task involves building multiple files or modules from a written spec. This skill exists specifically to prevent vibe-coding — where AI does a large batch of work the user ends up not understanding.

rmazrim Skill

Before multi-step toolkit workflows, pings the live tool (via schema-style endpoints / search tools) and diffs against my cached schema; on mismatch, rewrites the workflow plan, never the cached assumptions silently.

rmazrim Skill

Scaffolds a complete reactive Textual terminal Todo application with header, input, DataTable, footer, status label, custom keybindings and CRUD handlers, and includes a fully written Go Bubbletea counter alternative.

rmazrim Skill

Before each new task in a long session, re-runs the last N passing checkpoints captured by verify-orchestrator as a smoke suite, catching regressions caused by recent edits before they compound.

jawahars07 Skill

The working discipline for heavy tasks - building agents or systems, multi-hour features, large refactors, complex debugging. An eight-phase loop numbered from zero, with a verification requirement in every phase and a single approval gate before anything irreversible. Load it BEFORE starting any task expected to take more than about ten tool calls.

damiankawerski Skill

Use when writing a pull request description, PR body, or PR title for a branch — including "write me a PR description", "create a PR according to the git workflow", or preparing a branch for review.

steffencarlsen Skill

Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).

useagenthq Skill

Track multi-step work in useAgent's durable task manager, with .useagent/tasks.md as an explicit repo-local or offline fallback.

steffencarlsen Bundle

Plan and execute ambiguous, cross-cutting, or long-running work through evidence-based decomposition, bounded delegation, verification, and iteration. Use when a task has multiple independent investigations or implementation tracks, needs a robust strategy before editing, or the user asks Codex to orchestrate agents.

steffencarlsen Bundle

Catalog of MSBuild anti-patterns with detection rules and fix recipes. Only activate in MSBuild/.NET build context. USE FOR: reviewing, auditing, or cleaning up .csproj, .vbproj, .fsproj, .props, .targets, or .proj files. Each anti-pattern has a symptom, explanation, and concrete BAD→GOOD transformation. Covers Exec-instead-of-built-in-task, unquoted conditions, hardcoded paths, restating SDK defaults, scattered package versions, and more. DO NOT USE FOR: non-MSBuild build systems (npm, Maven, CMake, etc.), project migration to SDK-style (use msbuild-modernization).

steffencarlsen Bundle

Use when TaF asks for practical repo maintenance across their active checkouts, especially CI failures, failing tests, PR reviews, changelogs, docs updates, release prep, deployment workflow fixes, debugging evidence, package visibility, or focused repo triage.

steffencarlsen Skill

Guide for interpreting ResolveProjectReferences time in MSBuild performance summaries. Only activate in MSBuild/.NET build context. Activate when ResolveProjectReferences appears as the most expensive target and developers are trying to optimize it directly. Explains that the reported time includes wait time for dependent project builds and is misleading. Guides users to focus on task self-time instead. Do not activate for general build performance -- use build-perf-diagnostics instead.

steffencarlsen Skill

Discover and suggest relevant plugins, inspect app permissions and dependencies, and manage plugin connections or removal. Use when the user asks about plugins or when a task would materially benefit from an external app, account, service, or data source that available tools cannot access.