Coding & Dev Tools

muhammadali-k Bundle

Extract time-to-event clinical-trial outcomes into per-comparison OS, DFS/PFS, and RFS evidence tables. Use when the user provides outcome workbooks plus publications and needs treatment-vs-control hazard ratios with 95% CIs, events and denominators per arm, landmark event-free rates, arm names, endpoint mapping, and provenance. Handles overall-population multi-arm comparisons, HR inversion, figure-only estimates, and original-vs-follow-up coding through independent source-bounded extraction and verification. Produces new filled workbooks, provenance, and strict QC. Use itable-extraction for wide baseline/characteristics tables. Response and pCR templates are out of scope.

prashantdivate Bundle

Official-doc-first BitBake metadata support for AI coding agents. Use when inspecting, creating, editing, or debugging BitBake recipes, appends, classes, include files, configuration, tasks, variables, overrides, fetchers, signatures, sstate, dependency graphs, parse errors, QA errors, or files ending in .bb, .bbappend, .bbclass, .inc, .conf, plus metadata inside conf/, classes/, recipes-*/, and layer.conf.

prashantdivate Bundle

Yocto CI, reproducible build, and release engineering skill for AI coding agents. Use for kas, repo manifests, Git submodules, containerized builds, CI runners, downloads and sstate caches, hash equivalence, PR build gates, QEMU tests, hardware smoke tests, artifact publishing, SDK releases, SBOM/license manifests, release notes, and version pinning.

prashantdivate Bundle

Yocto BSP and board bring-up skill for AI coding agents. Use for vendor BSP import, machine configuration, layer dependencies, bootloader recipes, trusted firmware, U-Boot, Linux kernel recipes, device trees, defconfigs, KERNEL_DEVICETREE, COMPATIBLE_MACHINE, virtual/kernel providers, storage variants, serial console, first boot, and hardware enablement.

prashantdivate Bundle

Advanced Yocto Project build and debug skill for AI coding agents. Use for BitBake parse failures, fetch failures, patch/configure/compile/install/package failures, QA errors, missing providers, layer dependency errors, sstate/hash/signature problems, long build times, disk pressure, host dependency issues, TMPDIR confusion, and commands such as bitbake, bitbake-layers, bitbake -e, bitbake -g, bitbake-diffsigs, devtool, oe-pkgdata-util, runqemu, and testimage.

prashantdivate Bundle

Yocto image analysis skill for AI coding agents. Use to explain why a package is in an image, estimate image size impact, compare manifests, inspect package data, analyze dependencies, answer what-if package changes, reduce image footprint, inspect buildhistory, or use oe-pkgdata-util, bitbake -g, image manifests, license manifests, and installed package lists.

prashantdivate Bundle

Yocto recipe maintenance skill for AI coding agents. Use for creating, updating, auditing, or reviewing .bb and .bbappend files; package version bumps; dependency, license, PACKAGECONFIG, configure flag, patch, CVE, runtime dependency, package split, and cross-distro packaging comparisons against OpenEmbedded, Alpine, Buildroot, Debian, or upstream sources.

ysyecust Skill

日本語翻訳：このファイルは nestjs-patterns 用の日本語翻訳が必要です

scouzi1966 Skill

Build AFM from scratch — submodules, patches, webui, and Swift build. Use when user types /build-afm, asks to build afm, or needs a fresh build from a clean clone.

scouzi1966 Skill

Test a pre-built afm binary at any path — runs pre-flight safety checks, then any combination of unit tests, assertions, smart analysis, promptfoo evals, batch validation, OpenAI compat, GPU profiling. Use when user wants to validate a binary post-build, after code changes, or before release.

scouzi1966 Bundle

Use when user wants to build a PyPI wheel from an existing compiled afm binary and publish to PyPI. Covers staging assets, building the wheel, and providing the uv publish command. Only for official stable releases, not nightly builds.

scouzi1966 Skill

test-afm-assertions

scouzi1966 Bundle

Use when promoting afm to a stable release — builds from main HEAD or a nightly commit, verifies patches, updates Homebrew stable tap (afm.rb), builds a PyPI wheel, updates README and version files, and verifies both brew install and pip install work. Repo admin only.

scouzi1966 Bundle

Build, test, and publish an afm-next nightly release — full from-scratch build, user testing pause, GitHub release, and Homebrew tap update. Use when user types /build-afm-nightly-publish or asks to publish a nightly build.

scouzi1966 Skill

Run and review the Promptfoo-based AFM agentic evaluation suite. Use when the user wants structured-output, tool-calling, grammar, guided-json, streaming, concurrency, or agentic QA coverage for AFM, and especially when they want help choosing harness options or interpreting failures.

soujava Bundle

Simplify, modernize, refactor, and beautify Java code to produce clean, idiomatic Java. Use when asked to distill, simplify, modernize, upgrade, refactor, clean up, beautify, or improve Java code. Triggers on "distill this Java", "modernize this code", "simplify this Java", "upgrade to modern Java", "refactor to Java 21+", "clean up this code", "make this idiomatic", "beautify this Java", or when Java code needs transformation to current standards. Not for writing new code from scratch — use an appropriate Java development skill for that.

soujava Bundle

Plan and execute incremental migrations of existing projects to Boundary-Control-Entity (BCE/ECB) architecture. Use when the user wants to port, migrate, refactor, restructure, reorganize, or convert an existing codebase to BCE, Boundary-Control-Entity, ECB, business components, or boundary/control/entity layers. Always use this before changing code for BCE migration requests, even when another stack skill such as SBCE, SDD4J, Java, Spring, Quarkus, web components, or MicroProfile will also be needed.

soujava Bundle

Use this skill when the user wants to create, review, migrate, troubleshoot, or explain Quarkus applications using the Quarkus JNoSQL extension, Eclipse JNoSQL, Jakarta NoSQL, or Jakarta Data repositories.

soujava Bundle

Versioned Java coding conventions for writing, generating, or reviewing Java code. Use when the user asks about Java style, Java conventions, idiomatic Java, modern Java, Java 25, or when writing/reviewing Java code where context-specific skills do not already cover style. Triggers on "Java conventions", "Java style", "Java code style", "modern Java", "Java 25", "idiomatic Java", or any request to write or review Java code. Composes with framework- and architecture-specific skills; when a composed skill specifies a rule, that rule wins.

soujava Bundle

Generate parameterized (table-driven) tests from EARS requirement statements — the deterministic transform that turns an SDD4J capability spec's `## Requirements` into one parameterized test per requirement group and one labeled row per statement id. Stack-neutral; owns only the EARS→table mapping and the spec↔test trace, and delegates the test syntax to the composed stack skill (JUnit 5). Use whenever turning EARS requirements, acceptance criteria, or an SDD4J/`/sdd4j` spec into tests; whenever you see "When/While/If…then, the … shall …" statements that need covering; or when asked for table-driven, data-driven, or parameterized tests from a requirement group. Trigger on "SDD4J tests", "EARS", "parameterized tests", "table-driven tests", "data-driven tests", "tests from requirements", "tests from the spec", "cover requirement Rn", "generate tests for this capability", "acceptance criteria to tests".

soujava Bundle

Analyzes git diffs and commits staged changes using Conventional Commits v1.0.0.1. Use when the user asks to commit, craft a commit message, stage changes, or split work into multiple commits.

tandregbg Bundle

Operations Framework

tandregbg Skill

Inbox Skill

tandregbg Skill

Lifecycle management for outgoing material in `_outbox/`. List pending items, archive completed ones into the relevant contact/project folder, and keep manifest, CHANGELOG, and tasks in sync. Use when an outbox item has been sent, replied to, or otherwise resolved -- and the central `_outbox/` should be cleaned up.

tandregbg Skill

Capture a bounded subject from the current conversation as a frozen, self-contained snapshot in `.handoff/` — context a different work session can pick up cold. Written once, indexed nowhere, acted on only by a human. Use when a conversation surfaces something that belongs to a different piece of work.

tandregbg Skill

Knowledge extraction manager and skill evolution engine. Backfills _insights.yaml from historical corpus, compiles execution feedback into patterns, and proposes SKILL.md improvements.

tandregbg Bundle

Manage skill repo updates, symlink health, and installation. Fetches from multiple remotes with version safety, creates symlinks for new skills, audits symlink state.

tandregbg Bundle

Daily Dashboard

tommasobbianchi Skill

Error detection + post-error slowing (ACC). Invocala immediatamente quando hai appena commesso un errore — exit code !=0, exception, output inatteso, contraddizione con un'asserzione precedente, l'utente segnala uno sbaglio. Use right after detecting your own mistake to STOP, diagnose root cause, prevent the same class of error within the same session. Triggers anche su "hai sbagliato", "no, non è così", "non hai capito", reazione frustrata dell'utente.

tommasobbianchi Skill

Compress an accumulated body of facts into one claim plus a few structured principles, then use them to PREDICT rather than to record. The companion to `codemap` — codemap builds the map, this decides what the map MEANS and what to do next. Use after mapping a codebase, before choosing what to work on, when notes have piled up and are being consulted instead of used, or when the same system surprises you twice. Triggers on "synthesise", "synthesize", "what does this all mean", "I lack overview", "step back", "big picture", "make sense of this", "fai sintesi", "sintesi", "visione d'insieme", "fai un passo indietro", "intuizione", "cosa significa tutto questo", "manca la visione globale".

tommasobbianchi Skill

Outcome evaluation (OFC/striatum). Invocala dopo aver completato un'azione concreta, prima di considerarla chiusa. Use after each substantive action to verify it produced the expected effect — not "should have", actually did. Triggers anche su "fatto X", "completato Y", "il comando è andato a buon fine?", quando hai un risultato ma non l'hai ancora confrontato con l'aspettativa.

tommasobbianchi Skill

Verifica che l'ambiente sia stato lasciato pulito dopo le tue azioni. Invocala dopo operazioni che toccano filesystem, processi, container, nodi remoti via SSH/scp, file in /tmp. Use after work to confirm working trees clean, no orphan processes, no stale temp files — the user's next pull/run must hold no surprises. Triggers anche su "lascia pulito", "non dimenticare residui", quando hai usato `scp`/`cp` invece di git per propagare modifiche.

tommasobbianchi Skill

Cognitive-Stop

tommasobbianchi Skill

Cognitive-Spawn — sentinelle in background

agnik47 Bundle

Dynamically adapts design, UX, visual hierarchy, and interaction principles based on product type, audience, and business context to avoid generic AI-generated experiences.

agnik47 Skill

Forces Claude to behave like a senior software engineer by planning architecture, identifying edge cases, designing tests, and validating assumptions before generating production code.