Productivity

jamie-bitflight Skill

Implementation phase for stinkysnake workflow. Use when tests are written and plan is ready. Implements functions following the modernization plan, runs tests until passing.

jamie-bitflight Skill

Guided workflow for adding new features to Python projects. Use when planning a new feature implementation, when adding functionality with proper test coverage, or when following TDD to build features incrementally.

jamie-bitflight Skill

Use when building async APIs, concurrent systems, or I/O-bound Python applications requiring non-blocking operations. Covers asyncio, async/await patterns, task scheduling, synchronization primitives, and high-performance concurrent programming.

oliver-kriska Bundle

Choose Phoenix review, plan, debug, or test command. Use when user asks which phx-* command or plugin skill handles a task; do not route only to a domain skill. NEVER for bare /help; NOT for ambiguous requests (use intent-detection) or a plugin tour.

oliver-kriska Bundle

Walk through the Elixir/Phoenix plugin commands, workflow, and features in 6 interactive sections. Use when a new user wants to learn what the plugin offers or needs a refresher on available commands.

stanfish06 Skill

Testing Python code with pytest — fixtures, parametrization, markers, mocking, coverage, and configuration. Use when writing or running Python tests, setting up a test suite, debugging failing tests, adding fixtures or parametrized cases, measuring coverage, or configuring pytest in pyproject.toml. Pairs with test-driven-development for the workflow/methodology.

stanfish06 Bundle

Use when working with LaminDB, the open-source lineage-native lakehouse for biological datasets and models. Covers setup, artifact registration, query/search, lineage tracking, validation, ontology-backed annotation with Bionty, collections, branches, storage, and workflow integrations.

panaversity Skill

The release deep-workflow and runbook — how the changesets airlock works (main is releasable, never auto-released), how to test the real artifact before publishing, snapshot releases, and the diagnosis for every way the Release workflow goes red (org PR-permission, npm trusted publisher). Use when a Release run fails, when a Version Packages PR appears, when asked how/when ksor publishes, or when testing a build before release. Baseline policy lives in AGENTS.md → Changesets; this goes deeper.

deadmade Skill

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

stanfish06 Skill

Browse and install community skills from the BioClaw Skills Hub. Use when a user's task is not covered by built-in skills, or when the user asks about available skills, advanced workflows, or specialized analysis pipelines. Triggers on "skills hub", "more skills", "install skill", "community skills", "find a skill for".

stanfish06 Bundle

Route early browser-game work. Use when the user needs stack selection and workflow planning across design, implementation, assets, and playtesting before moving to a specialist skill.

stanfish06 Bundle

Turborepo expert guidance. Use when setting up or optimizing monorepo builds, configuring task caching, remote caching, parallel execution, or the --affected flag for incremental CI.

stanfish06 Bundle

Use for authorized multi-stage attack-path planning and orchestration when a task spans reconnaissance, initial access, privilege escalation, lateral movement, or impact assessment. Route single-stage tasks directly to their specialist skill.

stanfish06 Bundle

Differential expression analysis for label-free quantitative (LFQ) intensity data with standard MaxQuant and DIA-NN output. Workflow includes preprocessing, imputation, and statistical testing.

stanfish06 Bundle

Shotgun metagenomics workflow with host-depletion-aware QC, taxonomic profiling, functional profiling, AMR follow-up, and reproducible community output tables.

stanfish06 Bundle

Vercel Queues guidance (public beta) — durable event streaming with topics, consumer groups, retries, and delayed delivery. $0.60/1M ops. Powers Workflow DevKit. Use when building async processing, fan-out patterns, or event-driven architectures.

stanfish06 Bundle

Primary W&B skill for broad or mixed Weights & Biases work: project overviews, W&B runs and artifacts, Weave traces and evaluations, Reports, and Launch workflows. Use when the task spans multiple W&B surfaces or the user asks generally what is happening in a W&B project.

stanfish06 Bundle

Comprehensive toolkit for survival analysis and time-to-event modeling in Python using scikit-survival. Use this skill when working with censored survival data, performing time-to-event analysis, fitting Cox models, Random Survival Forests, Gradient Boosting models, or Survival SVMs, evaluating survival predictions with concordance index or Brier score, handling competing risks, or implementing any survival analysis workflow with the scikit-survival library.

stanfish06 Bundle

Analyze data using MATLAB. Use when the task involves tables, timetables, time-series data, numeric arrays, sensor matrices, or gridded data — including but not limited to exploring, filtering, sorting, cleaning, transforming, aggregating, smoothing, padding, trimming, and answering questions about data. MATLAB provides extensive, easy-to-use built-in functions for these workflows with no additional products required.

stanfish06 Bundle

Provides reverse engineering techniques. Use when the main job is to understand how a compiled, obfuscated, packed, or virtualized target works before exploiting or solving it, including binaries, APKs, WASM, firmware, custom VMs, bytecode, malware-like loaders, and anti-debug or anti-analysis logic. Do not use it when the vulnerability is already understood and the remaining task is exploitation; use pwn instead. Do not use it for pure web workflows, log or disk forensics, or standalone crypto problems unless reversing the implementation is the real blocker.

stanfish06 Skill

Diagnose MSBuild build performance bottlenecks using binary log analysis. USE FOR: identifying why builds are slow by analyzing binlog performance summaries, detecting ResolveAssemblyReference (RAR) taking >5s, Roslyn analyzers consuming >30% of Csc time, single targets dominating >50% of build time, node utilization below 80%, excessive Copy tasks, NuGet restore running every build. Covers timeline analysis, Target/Task Performance Summary interpretation, and 7 common bottleneck categories. Use after build-perf-baseline has established measurements. DO NOT USE FOR: establishing initial baselines (use build-perf-baseline first), fixing incremental build issues (use incremental-build), parallelism tuning (use build-parallelism), non-MSBuild build systems.

stanfish06 Bundle

Expert-thinking profile for Computational Scientist (computational / dry / simulation, UQ, and reproducible workflows): Reasons from Roache code/solution verification and ASME V&V 10/20/40 credibility through MMS/GCI, UQ ensembles, and Snakemake/Nextflow/CWL pipelines with conda-lock/Apptainer provenance while treating environment drift, workflow cache staleness, and validation-vs-calibration conflation as first-class failure modes.

stanfish06 Bundle

Expert-thinking profile for Precision Agriculture Specialist (site-specific crop management / VRT prescriptions / remote & proximal sensing / RTK-GNSS & ISOBUS / yield-map QA): Reasons from management-zone heterogeneity, the spatial 4R (right input, rate, place, time), and per-zone margin maps through SSURGO/ECa zone delineation, NDVI/NDRE indices, RTK-GNSS georeferencing, and ISOBUS Task Controller as-applied logs while treating planned-versus-applied divergence, NDVI saturation...

stanfish06 Bundle

Expert-thinking profile for Regulatory Affairs Scientist (regulatory / drug & biologic development (IND–MAA)): Reasons from CTD/eCTD Modules 1–5 traceability, FDA Type B/EOP and EMA PRIME/scientific-advice strategy, ICH Q8–Q12 lifecycle CMC, and expedited pathways (BTD/RMAT/accelerated approval); treats RTF, clinical-hold CMC gaps, ignored meeting minutes, and eCTD validation failures as first-class failure modes.

max-786 Skill

Skill per materiali, texture e UV in Blender. Copre: materiali Principled BSDF procedurali (noise, bump, SSS, Fresnel), UV unwrap (Smart Project, angolo-based, manuale), baking AO/Normal/Diffuse su immagine, texture painting via vertex paint o image stamp, PBR workflow con immagini reali (albedo + roughness + normal map). Usa questa skill quando devi assegnare materiali realistici, fare baking, UV unwrap, o costruire un node tree di materiale complesso da zero.

yannick-bottino Bundle

Quality gate for AI output before it ships, adapted for consulting deliverables. Flags AI slop, false facts, off-voice writing, structural anti-patterns, and off-strategy claims in a single scorecard table. Detects and suggests only; never edits or rewrites unless explicitly asked ("fix it" / "applique" / "corrige"). Use when the user says "de-slop", "de-slop this", "check this before it ships", "is this good to send", "run de-slop", "slop check", "relis ce texte", "ca fait trop IA", "humanise ca", "stop slop", "clean this up", "remove AI tells", "does this sound human", "edit this email", "relecture redactionnelle", "rends ca plus naturel", "c'est trop corporate", "ca sonne genere", or has produced an email, post, deck, reply, proposal, exec summary, or doc and wants it checked first. Also trigger when the user pastes text and says "mieux" or "ameliore". Even without an explicit trigger, apply this skill when Claude produces prose destined for a client or external publication.

yannick-bottino Skill

Point d'entrée pour initialiser et reprendre la mémoire persistante partagée d'une mission de conseil, en Cowork ou en projet Claude Code. Crée le pilote de session (CLAUDE.md) et le suivi de tâches (claude_tasks/TODO.md), et délègue à project-memory le substrat de mémoire 3 couches (_memory/). Utiliser dès qu'on ouvre un nouveau projet et qu'on veut un suivi partagé, ou quand l'utilisateur dit : "initialise le projet", "crée la mémoire projet", "setup projet", "init projet", "mets en place le suivi", "on part de zéro sur ce dossier", "prépare le dossier pour bosser à plusieurs", "mémoire partagée", "session handoff". Déclencher aussi sur "reprenons" ou "on en était où" dans un dossier contenant déjà un CLAUDE.md : dans ce cas, ne pas réinitialiser mais lire l'existant et faire le point.

austek Skill

Shepherd your own open PR on a personal/OSS repo to mergeable: poll CI, pull failing-check logs, fetch reviewer feedback (inline threads + review verdicts), draft fixes, push after confirmation, reply to and resolve the threads that fix actually addresses, re-checking for docs drift each loop. Use for "check my PR", "is my PR green", "address the review comments", or "land this PR".

austek Skill

Open a pull request on a personal or open-source GitHub repo: fork/upstream detection, repo's own contribution conventions (CONTRIBUTING.md, PR template, DCO/CLA sign-off), a docs-drift check, branch naming, and check monitoring. Use for "create/open a PR" or "push & open PR" on a non-Collibra repo.

austek Skill

Review a PR on a personal or open-source GitHub repo. No CODEOWNERS/team scoping — reviews the full diff, detects languages, applies the repo's own CONTRIBUTING.md/CLAUDE.md rules + language persona skills, checks DCO/CLA sign-off, and delegates to pr-review-toolkit:review-pr.

yannick-bottino Bundle

Transforme un transcript brut de reunion en un compte-rendu structure et professionnel. Utilise ce skill des qu'un utilisateur partage un transcript de reunion, des notes de call, ou demande un resume/compte-rendu de reunion. Fonctionne avec n'importe quel format de transcript (Fathom, Otter, Fireflies, Teams, Google Meet, notes manuelles, etc.). Trigger aussi quand l'utilisateur mentionne "meeting notes", "compte-rendu", "resume de reunion", "transcript", "call summary", ou uploade un fichier qui ressemble a un transcript. Trigger egalement quand l'utilisateur demande un "resume email" ou une "synthese a envoyer" a partir d'un transcript ou d'un compte-rendu deja produit.

ccronca Skill

Use Google Gemini for parallel code reviews, complex task validation, and second opinions. Runs Gemini CLI non-interactively to provide alternative perspectives on code quality, implementation decisions, and technical solutions.

yannick-bottino Bundle

Relentless process interviewer that extracts a complete, unambiguous plan from the user's head before any building begins. Use when the user wants to plan a complex task, design a process, build a skill, create a workflow, scope a project, or says things like "I want to build", "let's plan", "help me think through", "I have an idea for", "scope this out", "interview me", "help me figure out the process", "I need a skill that", or any variation where the user has a fuzzy idea that needs to be sharpened into a concrete plan. Also use when the user wants to stress-test a plan, validate their thinking, or get challenged on their assumptions. If the user's goal is to build a skill, this interviewer will automatically create it after the interview is complete. ALWAYS use this skill before jumping into building anything complex. Even if the user seems confident, the interview reveals gaps they didn't know they had.

dwikiramdani-root-dev Skill

Standard workflow for feature work and bug fixes in any repo - stress-tested plan, then TDD implementation, then a review gate and a draft PR. Use when starting a new feature or bug fix, or when the user types /dev-flow.

navinspire-ia Skill

Read, search, draft and reply to email using a connected Google or Microsoft account. Use for mailbox work and email follow-up through the accounts tool.

tticom Bundle

Determine and dispatch the next authorised action in a governed project. Locates the project's configured task authority, inspects live task, PR, and review state, identifies the responsible role, and either runs the project's configured dispatcher or produces a concrete handoff. Stops when configuration or authority is missing, conflicting, or records that no task is approved. Use only when the user explicitly asks to continue, advance, dispatch, or run the next governed task.