Productivity

manusco Bundle

Compatibility entrypoint for end-to-end software delivery. Use when the user explicitly invokes the software delivery skill or an existing workflow targets its skill ID. Confirms software scope, separates unrelated work, then delegates once to resonance-ops-goal, which owns the goal contract, bounded execution, evidence, review, and ship proposal. Do not select this instead of /goal for a new outcome request.

kody-w Bundle

Run the CSM delegation loop: hand grunt/bulk work (building, drafting, coding, doc generation, deep debugging) to GitHub Copilot CLI GPT-5.6 Sol as a background muscle job, then gate-check the FULL result hands-on with real inputs, fix via --resume rounds until it stands, and add the Fable-only layer last. USE THIS SKILL when Kody says: 'delegate to sol', 'muscle this', 'have sol/copilot build it', 'spawn the muscle', 'send it to the muscle', 'copilot the grunt work', 'ration fable', or whenever a task is bulk artifact generation (code, tests, docs, ports, sweeps) that does not need Fable-level judgment to produce — the output is an artifact, not a decision. Also use when a hands-on verification loop exceeds ~2 probes on the same failure (deep debugging is muscle work).

kody-w Bundle

Manages Obsidian vault as primary note-taking and memory system. Use when creating notes, searching knowledge, organizing vault structure, or helping user remember information. Use proactively for all vault-related tasks.

lucadominguez Skill

Obsidian Vault

yknothing Bundle

Use when a reviewed task is ready for implementation and the team must drive the work by writing failing tests first, especially when contract behavior, brownfield regressions, unsupported flows, or coexistence safety must be proven before code changes.

yknothing Bundle

Use when an operational task or incident needs a concrete step-by-step procedure that another responder can execute safely, especially when rollback, fail-closed containment, coexistence fallback, communication cadence, or evidence capture must be explicit under pressure.

yknothing Bundle

Use when software-development work is underway or likely, so the task routes through the Prodcraft lifecycle-aware entry stack before planning, implementation, quality gates, or workflow selection. Default to Prodcraft for software-development unless the user explicitly chooses another path.

yknothing Bundle

Use when an approved task slice already exists and the team needs a 2-5 minute execution plan with checkpoints, stop conditions, and batch discipline before or during implementation, especially when brownfield seams or review-sensitive changes make ad hoc execution unsafe.

yknothing Bundle

Use when a reviewed task slice has tests or acceptance targets and the team must turn it into a small, mergeable implementation increment without expanding scope, breaking contracts, or hiding release-boundary risk.

yknothing Bundle

Use when about to claim a phase, fix, task, build, or release is complete, fixed, passing, or ready for handoff and fresh evidence must be checked before making the claim or creating a commit, PR, or deployment decision.

yknothing Skill

Use when a reviewed task is ready for implementation and the team must drive the work by writing failing tests first, especially when contract behavior, brownfield regressions, unsupported flows, or coexistence safety must be proven before code changes.

stuffbucket Skill

Git operations and workflows. Use when committing, branching, merging, rebasing, resolving conflicts, writing commit messages, creating PRs, or managing release workflows. Covers conventional commits, branch naming, interactive rebase, conflict resolution, and PR descriptions.

stuffbucket Bundle

Use when authoring the npm-package half of a Tauri v2 plugin — the `guest-js/index.ts` exporting friendly wrappers around `invoke('plugin:my-plugin/cmd_name', args)`, typed `Channel` streaming wrappers, `addPluginListener('plugin-name', 'event-name', cb)` for native-emitted events, the `package.json` `exports` map for dual ESM/CJS, bundling with `tsup` or `rollup`, lockstep versioning with the Rust crate, and the publish workflow.

equinor Skill

EOS parameter regression workflow for fitting equation-of-state models to experimental data. USE WHEN: tuning binary interaction parameters (kij), matching saturation pressures, fitting PVT data (CME, CVD, DL), characterizing C7+ fractions, or validating EOS predictions against lab measurements. Covers SRK, PR, CPA parameter fitting strategies.

equinor Skill

Process safety methodology — barrier management, PSFs/SCEs, HAZOP guidewords, LOPA worksheets, SIL determination per IEC 61511, integrated facility safety response, safety change revalidation, independent benchmarks, bow-tie analysis, risk-matrix scoring, TR3001 overpressure-protection studies, and trapped-liquid fire rupture screening. USE WHEN: a task requires barrier registers, hazard identification, layer-of-protection analysis, safety-integrity-level assignment for an SIF, integrated ESD/compressor-trip/blowdown/relief/flare evidence, safety-study revalidation after change, independent method benchmarks, overpressure relief-cause / governing-case studies, trapped liquid rupture/PFP demand, or quantitative risk evaluation. Anchors on neqsim.process.safety.barrier, neqsim.process.safety.risk, neqsim.process.safety.overpressure, and neqsim.process.safety.rupture classes.

equinor Skill

Structured hazard-identification workflows — HAZOP worksheets with the seven IEC 61882 guidewords, deviation→calculation auto-population that maps each guideword/parameter deviation to the NeqSim calculator that quantifies its consequence (overpressure, vacuum collapse, deadhead, surge, backflow/water-hammer, low-temperature/MDMT, fire case, runaway reaction), FMEA failure-mode tables with RPN/criticality scoring, event-tree analysis (ETA) for outcome frequency, fault-tree analysis (FTA) with β-factor common-cause modelling and minimal cut sets, and escalation-graph (domino) screening. USE WHEN: a task requires systematic hazard identification, qualitative-to-quantitative scenario development, mapping HAZOP/HAZID deviations to quantitative process-safety calculations, top-event decomposition, or escalation/domino analysis between adjacent equipment. Anchors on neqsim.process.safety.hazid, neqsim.process.safety.risk.eta, neqsim.process.safety.risk.fta, neqsim.process.safety.escalation.

equinor Skill

Process flowsheet optimization and Design of Experiments using NeqSim's built-in stack — SQP for constrained NLP, Particle Swarm / Nelder-Mead for global / non-smooth, ProductionOptimizer for throughput, MultiObjectiveOptimizer for Pareto, BatchStudy for parallel sweeps, MonteCarloSimulator for uncertainty, ProcessSimulationEvaluator for SciPy/NLopt/Pyomo bridging. USE WHEN: a task involves minimize/maximize over decision variables, sensitivity studies, Pareto trade-offs, max throughput, parameter screening, or DoE — distinct from `neqsim-production-optimization` which covers reservoir-level decline / gas-lift / network problems.

equinor Skill

Self-heating, spontaneous ignition and thermal-criticality screening for reactive porous media — lagging fires from combustible liquid absorbed into porous thermal insulation, Frank-Kamenetskii and Semenov criticality, critical layer thickness, critical surface temperature, induction time to ignition, and Arrhenius parameter fitting from hot-storage (basket) tests per EN 15188 / ASTM E2021. USE WHEN: a task involves a flammable liquid leak or spill onto insulation or lagging, oil-soaked lagging, spontaneous combustion, self-ignition, smouldering, a fire with no obvious ignition source, insulation-material selection driven by absorbency, or fitting oxidation kinetics from oven/basket test data. Anchors on neqsim.process.safety.selfheating.

equinor Skill

Bidirectional P&ID/NeqSim workflow. USE WHEN: understanding P&ID symbols, converting P&ID topology into NeqSim simulations, generating governed DEXPI engineering packages from ProcessSystem or ProcessModel, linking tags to historian data, evaluating valve/equipment changes, or preparing water-hammer and blowdown/flare handoffs.

equinor Skill

Equipment and process CAPEX estimation — Turton/Peters/Ulrich/Seider correlations, CEPCI escalation, material/pressure factors, bare-module to grass-roots, AACE class 1-5, location factors, currency conversion, CostEstimateResult reconciliation, and mechanical-design-driven topsides/SURF/well rollups. USE WHEN: a task requires a +30%/-30% Class-3/4 estimate for equipment, a process flowsheet, topsides, SURF, wells, or reservoir-to-market CAPEX. Anchors on CostEstimationCalculator and ProcessCostEstimate.

equinor Skill

Flow-accelerated corrosion (FAC) and high-temperature pH in closed heating- and cooling-medium loops — magnetite film stability, mass-transfer-controlled wall thinning at bends and welds, wall shear stress, in-situ pH at operating temperature versus laboratory pH, alkaline margin above neutrality, and Cr-Mo material upgrade screening. USE WHEN: a task involves localised wall thinning or leaks at bends, elbows or circumferential welds in carbon-steel tubing; a closed glycol/water or water heating-medium, cooling-medium, boiler-feedwater or condensate loop; a WHRU, steam generator or economiser tube bundle; pH control of an amine-buffered loop; or any question of the form 'is the fluid alkaline enough at operating temperature?'. Anchors on neqsim.process.corrosion.

equinor Skill

Process controllability and operability — operating envelope mapping, turndown analysis, startup/shutdown sequencing, control valve sizing per ISA-75 (Fl, Fp, choked flow), rangeability, hunting/loop tuning, recycle stability. USE WHEN: a task involves operability assessment, turndown studies, control valve sizing, startup/shutdown procedures, or 'will this design operate?' questions. Complements neqsim-dynamic-simulation (transient solver) with steady-state operability framing.

equinor Skill

Set up anti-surge recycle control and coordinated minimum-speed recycle control for centrifugal compressors in NeqSim, including compressor performance chart generation, anti-surge calculation, MinimumSpeedRecycleControllerStructure use for coordinated pressure/speed/recycle split-range control, fuel gas savings, CO2 emission reductions, and monetary cost evaluations. USE WHEN: a task needs to protect a compressor from surge, coordinate speed and recycle valve control at minimum speed, eliminate uncoordinated recycle valve opening, or evaluate power and CO2 savings from control loop optimization.

the-utopia-studio Bundle

Fires when a fellow wants to test a workflow on paper before building it — "paper test", "sketch it", "paper prototype", "sketch probe", "draw the flow and check they can follow it". Output is a hand-drawn workflow sketch plus a structured read-out naming what was legible and where the decision lived. NOT for choosing which probe to run (that is `probe-matrix`), and NOT for testing demand, trust, or willingness to pay — a sketch lies about all three; route those to `wizard-of-oz-probe` or `concierge-probe`.

the-utopia-studio Bundle

Restates a product idea as ONE decision a named human makes, then quantifies how that decision is compressed — before→after on a single axis of time, effort, or autonomy (e.g. six minutes → thirty seconds). Fires on "what's the product here", "frame the problem", "what decision are we changing", "state this as a decision", "what are we actually changing for the user". Output is a filled Compressed-Decision Statement: the decision (never a feature), its one owner, the before→after compression with a source, and the autonomy-ladder move, every claim tagged [Fact]/[Assumption]/[Hypothesis]. NOT for stripping the job to primitives (use job-in-primitives), NOT for mapping and pricing the whole workflow (use current-state-map), NOT for the 8-dimension go/no-go (use problem-quality-scorecard), NOT for the per-unit prize ratio (use physics-floor-gap).

the-utopia-studio Bundle

Falsification pass for the load-bearing beliefs under a chosen plan or wedge. Restates each assumption as a null hypothesis (the belief is FALSE), designs the single cheapest observation whose failure would disprove it, and ranks every assumption by P(wrong) x impact-if-wrong so the fellow shoots at the most-likely- fatal belief first. Fires on "what has to be true", "how would I disprove this", "what's the riskiest assumption", "what could kill this", "which belief do I test first". Output is an Assumption -> Null -> Disproof table with a pre-committed kill signal on every row. NOT the go/no-go on whether the problem is worth building at all (problem-quality-scorecard), NOT bottom-up sizing (bottoms-up-quantification), NOT the priced workflow map (current-state-map), NOT a narrative failure story (pre-mortem).

the-utopia-studio Bundle

Run a moderated usability session on a working prototype and return findings tied to the screen, not the user. Fires when a fellow says "run a usability test", "watch a user try it", "usability protocol", "can a first-time user complete X", or "see where they get stuck". Product runs, Engineering watches muted, Design notes; the task is framed as a goal not an instruction, the user is kept in user mode (no leading, no explaining, no "do you like it"), and every finding is scored on observed task success (behaviour 0.7), never stated preference (opinion 0.1). Output is a Usability Findings sheet — each defect tied to a step, counted across users, severity by frequency × blocking. NOT for building the prototype (use `first-mocks`; this tests what that builds), NOT for shadowing an expert to capture their judgment (use `tacit-knowledge-interview`; that mines expertise, this tests your design), and NOT for testing demand or willingness to pay (a user can complete every task and still never want it — route to `wiz

zjunlp Skill

Comprehensive strategy for analyzing individual patient records in MIMIC-IV EHR database and generating high-quality, diverse QA pairs. Use this skill whenever the task involves analyzing a specific patient's clinical data from MIMIC-IV (or similar EHR databases), querying across hospital and ICU tables, and submitting QA pairs that cover the patient's full clinical story — diagnoses, procedures, medications, care trajectory, and outcomes. Trigger when you see tasks like "Analyze patient <ID>", "Generate QA pairs for patient", or any patient-centric EHR exploration task.

viktorsbaikers Bundle

Internal shared DevRites helper library. Documents cross-cutting engine commands and references; not a user workflow. Do not invoke directly.

oleg-koval Skill

Use claude-relay to run a long or rate-limit-prone task autonomously across subscription accounts. Invoke this skill whenever the user says "use relay", "run this with relay", "do this overnight", "run this autonomously", "use relay for X", or has a multi-hour / multi-step task they want to hand off completely. Also use proactively when a task looks like it will take many turns and the user hasn't thought about rate limits yet. Guides goal writing, picks the right flags, and starts the run.

oleg-koval Skill

Orchestrate a full release-day workflow for iOS, Android, or Garmin apps: verify the main branch CI is green, generate a changelog from git history, draft platform-ready store listing copy, trigger semantic-release (or tag manually), wait for the build, and queue the App Store submission. Use when the user says "cut a release", "ship version X", "it's release day", or "prepare the release".

oleg-koval Skill

Generate polished, platform-validated App Store / Google Play / Connect IQ store listing copy (title, subtitle, description, "what's new", keywords) from a git changelog or release notes. Use when preparing a new release submission, when the user says "write the store listing", "update the App Store description", "draft the what's new", or "prepare my store copy" for iOS, Android, or Garmin apps. Chains naturally after changelog-generator and before apple-store-submit or garmin-watchface's store publishing workflow.

oleg-koval Skill

> 🤖 *Auto-generated by **weekly-pattern-learner** · App Store rejection handling workflow observed in FocusNotch App Store session, Jun 2026 (92 user turns covering rejection → plan → code fixes → metadata → resubmit)*

oleg-koval Skill

Comprehensive PR finalization workflow for PRs that may already be partially or fully addressed. Checks the current state of all review comments (CodeRabbit, Qodo, Greptile, human), identifies which issues are already resolved vs. still open, verifies the test suite passes, runs linting, and prepares a clean push. Handles stale bot comments on moved/renamed files, direct unit test gaps, and branch conflict resolution. Use when a PR has been worked on and you need to confirm it is truly ready to merge, or when review tools show findings that may already be fixed.

oleg-koval Skill

Migrate unfinished tasks from a daily Obsidian note to the next workday's note, bullet-journal style. Marks migrated tasks in the source note with [>] (the BJ migration symbol) and copies them to the target note under "## Carried over". Use this skill whenever the user says "roll over today's tasks", "migrate unfinished tasks to tomorrow", "end of day task sync", "move open tasks to next workday", or when a scheduled end-of-day / start-of-day routine fires. Fully idempotent: safe to re-run; already-migrated tasks ([>]) are not touched again.

howard-lynn-ye Skill

Build a volatility surface that is not silently arbitrageable - invert prices to implied vols, fit a smile, check butterfly and calendar arbitrage, and interpolate between maturities. TRIGGER - implied volatility solver, Newton diverges, bisection bracket, "implied vol returns 0.001", "no implied volatility for this option", price below intrinsic, BelowIntrinsicException; SVI, raw SVI, Gatheral, svi calibration, a b rho m sigma, SviSmileSection; volatility smile, skew, surface fitting, total variance, log-moneyness; butterfly arbitrage, negative implied density, Durrleman g(k), calendar spread arbitrage, static arbitrage check, Gatheral and Jacquier 2014; interpolating the vol surface, "my interpolated surface has arbitrage", "vol interpolation between expiries". SKIP for pricing one option and the models themselves - Heston, CRR, SABR, Monte Carlo (option-pricing-models), for library choice, Greek units and licences (derivatives-pricing), and for option chain data and historical chains (options-backtesting).