Productivity

blockmatic Skill

Analyze compilation errors and provide fixes to resolve all errors. Use when the user types /fix-compile-errors.

blockmatic Skill

Retrieve GitHub Actions logs with gh, analyze failures, and fix CI errors locally. Use when the user types /fix-github-actions.

blockmatic Skill

Measure bottlenecks with repository tools, then recommend or apply evidenced optimizations. Use when the user types /optimize-performance.

blockmatic Skill

Comprehensive onboarding process to get new developer up and running quickly. Use when the user types /onboard-new-developer.

blockmatic Skill

Execute full test suite and systematically fix any failures, ensuring code quality and functionality. Use when the user types /run-all-tests-and-fix.

blockmatic Skill

Perform quick quality pass on current diffs to surface risky areas, ensure polish, and flag follow-up actions for deeper review. Use when the user types /light-review-existing-diffs.

mahdtech Skill

Keep one-off, experimental, or temporary scripts and files out of the source tree by writing them to a single, consistent session scratch location, then cleaning them up. Use when creating throwaway, experimental, or temporary scripts/files during a task.

mahdtech Skill

Route to the right skill for the task at hand - a map of every skill in this collection and when to reach for it.

mahdtech Skill

Final pass to identify missed items, edge cases, and risks before considering a scope done. Use as a final breadth pass before calling a scope or task done - to catch missed items, overlooked requirements, edge cases, and risks after the core work is complete and reviewed.

mike007jd Skill

Use when deciding development mode, quality target, task granularity, or refactor policy for game work.

mike007jd Skill

Use when the user wants a persistent requirements/spec/design/tasks workflow, asks for OpenSpec-style planning, or needs durable change artifacts in the target repo.

bitranox Bundle

Use when installing, configuring or running bmk - the bitranox cross-OS build/test/release task runner - in a project (bootstrapping it with uv, deploying its Makefile via bmk install, running make test / push / bump / release / ship, fixing missing external tools with bmk ensure, reading its JSON-by-default vs --human output, layered config with --profile / --set, or defining custom staged pipelines). Works on Linux, macOS and Windows.

gannonh Bundle

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep watching open PRs so fresh review feedback is surfaced promptly. Use when the user asks Codex to monitor a PR, watch CI, handle review comments, or keep an eye on failures and feedback on an open PR.

gannonh Bundle

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for ps-arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.

gannonh 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 ps-figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.

afine907 Bundle

【Git工作流】一键完成 Git 工作流：分支→暂存→commit→push→PR。 触发时机：用户说"帮我提PR"、"提交代码"、"git flow"。 智能判断 git 状态，自动执行需要的步骤。

afine907 Bundle

Transform meeting transcripts into structured minutes with decisions and action items. Trigger: user says "帮我整理会议纪要"、"写会议记录"、"meeting notes".

asdc163 Bundle

Turn an AI workflow demo, validation, or pilot into an evidence-bounded Explore, Validate, Pilot, Scale, Narrow, Hold, or Retire decision using accepted outcomes, guardrails, reliability, cost, demand, capacity, ownership, rollout, and rollback.

asdc163 Bundle

Turn one AI workflow into an evidence-bounded value-to-investment brief with a successful-work unit, full cost ledger, dependability, value assumptions, scenarios, sensitivity, capacity, and an Invest, Test, Narrow, Hold, or Stop decision.

asdc163 Bundle

Turn a tested AI workflow into an evidence-bounded operating package that another person can repeat, review, support, maintain, change, or retire without overstating adoption, value, safety, or production readiness.

asdc163 Bundle

Turn a tested AI workflow into an evidence-bounded team introduction and adoption plan with a real work moment, support and fallback, enablement, evidence ownership, feedback-to-change, and a continue, revise, pause, stop, or broader-use decision.

asdc163 Bundle

Diagnose why one tested AI workflow is not becoming repeatable useful work, separate observed behavior from assumed cause, and choose the smallest evidence-bounded intervention or escalation. Use when adoption is stalled or uneven across a real team or workflow; do not turn usage, attendance, or a single quote into an adoption, value, quality, safety, or causality claim.

asdc163 Bundle

Use when an AI product must turn a content policy into a reviewable moderation workflow with a bounded taxonomy, severity and action matrix, timing, human review, appeals, false-positive and false-negative slices, privacy controls, and a ship, pilot, hold, or rollback decision. It separates provider capability from product evidence and does not implement or prove a moderation classifier.

asdc163 Bundle

Turn several AI workflow or capability candidates into an evidence-bounded portfolio sequence with value models, foundations, dependencies, capacity, concurrency limits, stage gates, and Start, Next, Parallel, Hold, Stop, or Retire decisions.

asdc163 Bundle

Decide whether one real AI workflow candidate is ready to test now, needs more validation, should be sequenced later, or should be avoided for now. Use the supplied job, owner, value, complexity, risk, dependencies, user and technical readiness, human boundary, support, and smallest-test evidence without inventing adoption, value, safety, or production claims.

envoydev Bundle

Converts a day's raw work notes (Ukrainian, English, or mixed) into a structured, past-tense English work log - ticket IDs normalized, time totalled, tasks grouped by project or prefix across one or more days. Fires only on the exact keyword 'dev-log' - do not use it for general note-taking, meeting minutes, commit messages, or status updates, which are not this format.

envoydev Bundle

.NET hosted-service and worker conventions - the long-running background work the generic host runs. Covers the host shapes (worker binary, in-web-app task, Windows Service), IHostedService versus BackgroundService versus IHostedLifecycleService, the ExecuteAsync exception trap, scoped services from the singleton host, PeriodicTimer over Task.Delay, graceful shutdown, and System.Threading.Channels queues - plus references/ for 24/7 I/O hardening, scheduling/leader election, deployment/signals. Floors at .NET 8 / C# 12. Load when writing a worker service, BackgroundService or IHostedService, a periodic job, a bot/daemon host, or any in-process background task hung off the host. Companions: dotnet-messaging, dotnet-web-backend, csharp. Do NOT load for the broker side of a consumer (dotnet-messaging; the consumer's host process is still this skill), HTTP endpoints, or reactive in-memory streams.

envoydev Bundle

Build a new application or major module from scratch - greenfield design, scaffolding, and build orchestration, before code exists. DESIGN runs IN-SESSION on this skill's opus/xhigh pinned turn: the spec becomes 2-3 reasoned architecture options and the user picks - nothing is scaffolded before that pick. Then the stack's real new-project command + baseline wiring, then the build slice by slice - through the domain seats or in-session, per the run-start ask. Not for changing an existing codebase - a feature inside a live app is `project-solve-cross-task`, a new module in an existing repo is the project-architecture-analyzer capture plus that stack's solution-designer. Triggers on build from scratch, new project, greenfield, scaffold, start a new app.

envoydev Skill

The deliberate test-coverage capture: detect each stack's test-and-coverage tooling, run the instrumented suite ONCE per surface in the main session, analyze per surface (seats on a first capture, inline on an update), and judge against the USER's % bar - asked at first capture, recorded in the doc - writing <docs-path>/test-coverage/COVERAGE.md (verdicts, per-module data, weak points tiered small/substantial/structural with a simplify-testing action each) plus the raw results under raw/. Re-run to refresh: both reconciled in place. Triggers on 'measure the test coverage', 'capture the coverage baseline', or 'how covered is this project'. Manual, /-only - or Read-loaded as project-test-coverage-loop's ANALYZE step; never mid-build, never a flow gate. NOT for fixing the gaps it finds (project-test-coverage-loop), writing a task's tests (every build flow's own done bar), or architecture capture (project-architecture-analyzer).

envoydev Bundle

The deliberate architecture analyze-assess-improve loop. Runs the project-architecture-analyzer capture, works the ASSESSMENT's weaknesses by tier - small to a domain implementer, substantial through a designer -> implementers -> verifier (plan approved first), structural flagged for a user decision and never auto-applied - prunes the fixed weaknesses from the ASSESSMENT itself (one capture reconcile at stop, not per round), and loops until the fixable cons resolve or plateau. Manual, /-only. Triggers on 'run the architecture quality loop' or 'analyze and improve the architecture'. NOT for a code-quality polish (project-quality-loop), a single feature build (project-solve-cross-task), or a capture-only run with no fixes (/project-architecture-analyzer alone).

kaiohenricunha Skill

Project-aware git workflow: conventional commits, PR creation, safe pushes, PR merges, and branch naming suggestions. Triggers on: "conventional commit", "create PR", "push changes".

bitranox Bundle

Use when the same guidance is copy-pasted across many CLAUDE.md (or other always-loaded doc) files in a tree and has drifted - a section repeated in 20 repos, a rule stated at three levels, a table that no longer matches the tool it documents. Covers measuring the duplication, verifying each claim against ground truth before keeping it, converging the variants to one correct text, and lifting it to the true common ancestor without leaving a reader meeting the same heading twice.

bitranox Bundle

Use when you have a spec or requirements for a multi-step task and want an implementation plan before touching code

bitranox Bundle

Use when completing a task, finishing a major feature, before merging to main, when stuck, or after fixing a complex bug, and you want a code review of the changes

drmoisan Skill

GitHub Actions PowerShell workflow authoring rules.

drmoisan Skill

Coordinate a feature or bug request from intake through promotion, planning, execution, validation, and review by selecting the correct small or large path and delegating to migrated Codex specialists when available.