12,528 skills found · Page 417 of 418
OutlineDriven / fuzzingUse when planning an end-to-end fuzzing program for a project: engine and target selection, corpus management, and CI or nightly wiring. Not for harness design: use fuzz-harness-writing. Not for engine operation or triage: use libfuzzer. Not for sanitizer flag reference: use sanitizers.
OutlineDriven / makeUse when writing or debugging Makefiles, understanding pattern rules and automatic dependency generation, managing CFLAGS/LDFLAGS, or diagnosing incremental build, phony targets, or recursive make.
OutlineDriven / cudaUse when writing CUDA kernels, managing the thread, block, and grid hierarchy, tiling shared memory, using streams, setting nvcc flags, or using Thrust. Not for kernel debugging: use cuda-debugging.
OutlineDriven / tasteUse when asking "overkill?", "elegant?", "audit", or "taste-test this", or setting a taste register. Not for tasks that require source or remote-system changes.
OutlineDriven / ninjaUse when diagnosing Ninja build failures, tuning parallelism, interpreting verbose output, or working with build.ninja files as a CMake-generated low-level build executor.
OutlineDriven / deslopUse when the user says deslop, debloat, tidy, simplify, clean a diff, cleanup codebase, or deslop branch diff, or remove dead code or config. Not for remote, credential, publish, deploy, or irreversible changes.
OutlineDriven / commitUse when asked to commit changes, create a typed branch, format history for a changelog, or rewrite messages of HEAD or an unpushed range. Not for pushing or a PR: use commit-push-pr.
OutlineDriven / principlesUse when a request names a working principle (subtract before you add, idempotent operations, never block on the human) or asks which principle applies. Not for running a repair: use strike-the-root.
OutlineDriven / workUse when implementing from a plan, spec, clear build request, or settled ticket, orchestrated or standalone. Don''t use for open-ended debugging (figure-it-out), exploration, or read-only research.
OutlineDriven / sagaUse when a user runs saga or asks to autonomously build a sizable feature. Not for executing a given plan: use subagent-driven.
OutlineDriven / reviewUse when asked to review a pull request, examine code changes, find bugs, or audit a branch, in standard or depth mode. Not for an iterative review-and-fix loop: use audit-project.
OutlineDriven / unslopUse when prose is drafted or edited, reviewed for AI tells, or the user asks to remove AI patterns, humanize, or add voice. Offers dedash and detool modes. Not for code debris: use deslop.
OutlineDriven / resolveUse when addressing review feedback in analyze or reception mode, or handling GitHub PR feedback in autonomous, interactive, or summary mode for a named PR target. Classifies, applies, replies, or summarizes comments.
OutlineDriven / divergeUse when the user wants to expand a decision field with additional options and dimensions. Not for selecting or applying an option: use decide. No source or remote-system changes.
OutlineDriven / loop-meUse when the user says "loop me" or asks to design a recurring workflow. Don''t use for remote, credential, publish, deploy, or irreversible changes.
OutlineDriven / catchupUse when the human returns after a gap, cannot follow the project, asks what happened, or wants a visual HTML recap page. Not for onboarding: use onboard. Not for handoff: use handoff.
OutlineDriven / wontfixUse when the user wants to elicit refused directions, generalize them, and close matching tracker items as not planned. Not for duplicates, spam, or items closed as completed or obsolete.
OutlineDriven / save-mdUse when asked to save a URL, file, or pasted text as a .md file with frontmatter, without summarizing. Not for remote, credential, publish, deploy, or irreversible changes.
OutlineDriven / to-specUse when settled conversation decisions need synthesis into an agent-ready implementation spec, stopping before publication. Not for turning plans into tickets: use to-tickets.
OutlineDriven / offenseUse when a human says "overhaul", "rebuild this subsystem", or "rewrite it from scratch". Not for thin-slice features: use incremental-implementation. Not for root-cause repair: use strike-the-root.
OutlineDriven / autoplanUse when the user runs /autoplan on a plan or idea. Reviews, amends, and derives task IDs with a final human approval gate. Not for remote, credential, publish, deploy, or irreversible changes.
firespring / gs-prInvoke the fs-pr plugin skill with givesource context.
firespring / gs-planInvoke the fs-plan plugin skill with givesource context.
firespring / gs-loopInvoke the fs-loop plugin skill with givesource context.
firespring / gs-storyInvoke the fs-story plugin skill with givesource context.
firespring / gs-reviewInvoke the fs-review plugin skill with givesource context.
DioxusLabs / ios-simulator-accessibilityReading the iOS Simulator accessibility tree and hit testing it — bridge delegate tokens, full-screen backdrops, app-scoped versus display-scoped results, and reaching web content that the tree cannot see
architects-toolkit / fix-compilation-messagesSmartHopper is an open-source project that implements third-party AI APIs to provide advanced features for Grasshopper3D.
DuqueOM / security-auditProduction-grade MLOps platform: 3 end-to-end ML projects with CI/CD, Terraform (GCP GKE) (AWS EKS), Kubernetes, MLflow, Docker, and 90-96% test coverage
SamsterZero / gh-stackA privacy-first, local-first EPUB library and offline PWA with responsive reading, device-local bookmarks and highlights, built with SvelteKit.
