Product & Planning

l-gevity Skill

Moves bespoke, duplicated, or over-local code down into reusable capabilities outside the immediate implementation: framework-native features, stack-aware approved libraries, internal platform products, managed services, or external standards. Use when assessing whether custom code should be replaced by a lower-level capability, especially an external library or service; when reducing bespoke wrappers around commodity behavior; or when designing an improvement roadmap for reuse and platform leverage. Skip purely in-codebase componentization or patternization unless the target is an approved external library, framework capability, platform product, or managed service.

l-gevity Skill

Structures validated requirements into an atomic, traceable, typed dependency graph and derives a trustworthy dependency order. Use when normalizing requirement wording, preserving stable IDs, splitting or merging requirements, modeling dependencies and constraints, detecting duplicates, conflicts, cycles, orphans, stale references, or missing verification, refining requirement-scope boundaries, or producing a graph package. Do not use for initial problem discovery or implementation planning.

l-gevity Bundle

Grounds proposed requirements in a real actor-bound problem, explicit scope, authoritative sources, evidence, assumptions, priority, and validation confidence. Use when defining or sharpening a problem, extracting obligations or stakeholder needs, separating facts from interpretations and hypotheses, writing solution-free requirement candidates, defining measurable expected outcomes without turning them into acceptance criteria, deciding what belongs in scope, sweeping quality characteristics for unstated non-functional obligations, reverse-engineering provisional requirements from existing code, tests, schemas, configuration, public interfaces, documentation, or history, or determining whether requirements are ready for dependency modeling. Do not use for graph construction or implementation planning except to prepare their inputs.

l-gevity Skill

Determines whether graph-structured requirements are ready for architecture, development, and verification, then derives the smallest coherent build-preparation package without inventing requirement meaning. Use when producing capability maps, epics or workstreams, implementation slices, dependency sequencing, riskiest-assumption ordering, parallel-ready slices, contract candidates, domain-model seeds, cross-cutting constraints, acceptance-test references, ADR seeds, technical questions, or explicit ready/partly-ready/not-ready decisions. Do not use for initial discovery or requirement graph normalization.

l-gevity Bundle

Decides whether functionality solves a real problem and is worth its complexity cost. Use in prospective mode to build, defer, or drop proposed capabilities, and in retrospective mode to keep, simplify, deprecate, delete, or mark existing code obsolete. Trigger for feature triage, backlog grooming, PR scope review, dead-code audits, tech-debt reviews, "is this worth it?", "should we remove this?", "is this defensive check necessary?", and cases involving impossible-state guards, redundant validation, cargo-culted patterns, phantom requirements, requirement-pinned mechanism, or unused generality, and evidence-driven revisits of outcome hypotheses after release.

bastani-inc Skill

Create a detailed execution plan/spec/PRD for implementing features or refactors in a codebase, designed around the program's entrypoints, the doors that carry domain intent, by leveraging existing research in the codebase.

mikeonbreeze Bundle

Researches city-level ADU regulations, municipal codes, and standard details for any California city. This skill supports three research modes — Discovery (WebSearch to find key URLs), Targeted Extraction (WebFetch to pull content from discovered URLs), and Browser Fallback (Chrome MCP for cities with difficult websites). When used standalone, run all three modes sequentially. When invoked by an orchestrator (e.g., adu-corrections-flow), run in the specified mode only. Triggers on city-specific ADU questions, corrections letter items referencing municipal code, or when the California ADU state-level skill indicates a question requires local jurisdiction rules.

aiagentskills Skill

Creates content PRDs with objectives, audience, and distribution plans.

aiagentskills Skill

Writes structured PRDs with goals, scope, requirements, and success metrics.

chili-piper Bundle

Guides an admin through building a complete Concierge web-form router from scratch — teams, meeting types, rules, distributions, and the live router — via a discovery interview and confirmation checkpoint. Data fields stay UI-only; third-party webform trigger mapping is now API-writable via thirdPartyForm.

forsonny Bundle

Use after the product spec is approved, before any implementation work. Pressure-tests the spec with a 100-question self-interrogation where each question builds on the previous answer. Returns critical issues, strengths, and a revised proposal. Material revisions loop back to brainstorming.

forsonny Bundle

Use at stage 2 after the UX spec has been approved and deep-discovery has cleared the product spec, when scope warrants dedicated UX pressure-testing. Runs a 100-question interrogation targeted at flows, state completeness, accessibility, voice, and platform appropriateness. Material revisions loop back to design-brainstorming.

full-stack-skills Bundle

Event Storming workshop facilitation guide — collaborative domain exploration methodology with 6-step process (chaos exploration/timeline/pivotal events/commands & actors/aggregate discovery/bounded context), standardized sticky note color conventions (orange/blue/yellow/green/pink/purple), workshop preparation and facilitation tips, and digital tool recommendations. Use when user asks about event storming, 事件风暴, workshop, 工作坊, domain exploration, collaborative modeling, or needs to organize a DDD discovery workshop.

full-stack-skills Bundle

DDD architecture evaluation and evolution — DDD maturity 5-level model (AdHoc/Aware/Applied/Scaled/Optimized), architecture fitness assessment (business alignment/team fit/tech fit/evolution capability), technical debt quantification with scoring, architecture evolution roadmap (4 phases), and migration risk assessment. Use when user asks about architecture evaluation, 架构评估, DDD maturity, 技术债务, architecture evolution, 架构演进, or needs to assess DDD implementation health.

glebis Bundle

User-invoked review that coordinates the humane review skills — layout-rules, ux-writing, nielsen-heuristics, walkthrough, design-tokens contrast — into one prioritized verdict, and marks the domains it cannot cover instead of improvising them. Supports quick and full modes. Identifies the artifact first and runs a reduced document pipeline for a README, PRD, or docs page rather than stretching a UI pipeline over it. Use when explicitly asked for a holistic review of a screen, flow, feature, product, or document. Triggers on humane review, full review, review the whole thing, holistic UI audit, cross-skill design review, "review this properly", "полный ревью".

glebis Bundle

Review a document from multiple stakeholder perspectives (personas), collect structured feedback, and optionally update the document. Use when a document should be stress-tested from different viewpoints before sharing — e.g., "review this PRD from an engineer's perspective", "what would a skeptical investor say about this pitch?" Triggers on persona review, review from a stakeholder perspective, what would an engineer say, stress-test this PRD, review this pitch, skeptical investor.

glebis Bundle

Run a panel of independent synthetic respondents against copy, a slogan, brand values, a landing page, or any user-facing text — each in an isolated context, each a different specific person — then read the panel for convergence and divergence. Use when the user asks "how does this land", "what would people think of this", "test this tagline", "get reactions to this copy", "run a panel", or wants gut-level audience reaction rather than expert critique. Complements persona-review, which is expert stakeholder critique of a document. Triggers on respondent panel, how does this land, what would people think, test this tagline, reactions to this copy, gut reaction, audience reaction.

alexzhu0 Skill

Use when converting customer call notes, interview transcripts, sales discovery notes, or PM research fragments into a concise PRD with user problems, requirements, non-goals, and risks.

alexzhu0 Skill

Use when converting roadmap notes, feature lists, planning docs, or backlog themes into a release plan with milestones, scope, dependencies, rollout phases, and validation checks.

altinity Bundle

Diagnose ClickHouse merge performance, part backlog, and 'too many parts' errors. Use for merge issues and part management problems.

altinity Bundle

Diagnose ClickHouse issues by analyzing system.part_log (part creation, merges, mutations, downloads, removals, moves). Use for too many parts / micro-batch inserts, merge backlog or slow merges, mutation storms (ALTER DELETE/UPDATE), unusual replication DownloadPart churn, unexpected RemovePart spikes, or ZooKeeper/Keeper znode growth correlated with part activity.

nvidia-bionemo Bundle

NOTE: molecule and target inputs and your NGC_API_KEY are transmitted to external NVIDIA-hosted API endpoints on every call. Use local NIM containers for confidential or proprietary data. Run a complete computational drug discovery pipeline using NVIDIA BioNeMo NIMs: generate drug-like molecules with GenMol, dock them to a protein target with DiffDock, then predict binding affinity with Boltz2. Use this skill whenever the user wants to generate and screen small molecule drug candidates, perform hit discovery, optimize leads against a protein target, or do virtual screening combining molecule generation, docking, and affinity prediction. Triggers on: drug discovery pipeline, hit discovery, lead optimization, virtual screening, molecule generation, molecular docking, binding affinity, GenMol, DiffDock, Boltz2, SMILES, SAFE notation, NIM microservice. This is a multi-step pipeline composing three BioNeMo NIMs.

azborgonovo Bundle

Reviews a merge request or pull request against its linked work item, publishes the findings as inline comments on the diff, and records the verdict on the change. It fetches the change and the work-item context, isolates the change locally, hands the review itself to the review-changes skill, posts each finding, and then approves the change or requests changes according to that verdict. It ships with adapters for GitLab and GitHub as the code host, and Jira and GitHub Issues as the tracker. For any other host or tracker, it degrades to whatever tool discovery can reach. This skill is user-only: it runs only when the user invokes /pr-review <MR or PR URL>. When the user wants to review a GitLab MR or a GitHub PR, code-review a merge request or pull request, or evaluate the diff of a change against its linked work item, suggest this command instead of a manual review.

azborgonovo Bundle

Triages every open review thread on a merge request or pull request, then acts on each one. For a thread you agree with, it implements a tested fix, replies in-thread with the fixing commit, and resolves the thread. For a thread you disagree with, it replies with your reasoning and leaves the thread open for the human reviewer to close. It ships with adapters for GitLab and GitHub as the code host, and it degrades to any other host that tool discovery can reach. This skill is user-only: it runs only when the user invokes /address-pr-comments <MR or PR URL>. When the user wants to work through reviewer feedback on a GitLab MR or a GitHub PR, resolve review comments, or address a round of code review, suggest this command instead of triaging threads by hand.

yesterday-ai Bundle

Scaffold, polish, and publish open-source projects with AI-first documentation, governance, and CI. Use when: Starting a new OSS package, polishing/publishing an existing repo, setting up AGENTS.md / CONTEXT.md / DECISIONS.md / ROADMAP.md, onboarding AI agents to a codebase, or creating standard community files (README, LICENSE, CONTRIBUTING, CHANGELOG, CI pipelines, issue templates). Outputs repo description and tags at the end.

yesterday-ai Skill

Plan the next milestone: goal, exit criteria, rough size. Creates M###-CONTEXT.md and M###-ROADMAP.md. Run after init-project has scaffolded `.ytstack/`, before slice-milestone. Draws the goal from a validated pitch when available (OFFICE-HOURS.md or prior milestones); if no pitch exists yet in greenfield, prefer office-hours first so the milestone is grounded in real demand. Updates STATE.md with the new current_milestone.

yesterday-ai Skill

Challenge premise, scope, and ambition via four modes: SCOPE EXPANSION, SELECTIVE EXPANSION, HOLD SCOPE, SCOPE REDUCTION. Auto-detects mode: concept-mode reviews a pitch (OFFICE-HOURS.md) before any scaffolding exists; milestone-mode reviews a committed milestone (M###-CONTEXT.md + M###-ROADMAP.md) before slicing. Use concept-mode right after office-hours to stress-test the pitch; use milestone-mode after plan-milestone and before slice-milestone. Thin ytstack wrapper around the vendored gstack plan-ceo-review procedure.

yesterday-ai Skill

Break the current milestone into slices. Reads M###-ROADMAP.md, asks for slice content until all slices are filled. Creates M###-S##-PLAN.md per slice. Enforces 1-7 tasks per slice (iron rule). Run after plan-milestone, before plan-task.

yesterday-ai Skill

After a slice completes, review whether the milestone roadmap still fits reality. Reads recent summaries, surfaces deviations, prompts for roadmap changes (add/split/reorder/remove slices). Run at slice boundaries, not mid-slice.

lukehle Skill

Change management for finance automations that an auditor can read - what changed, who approved it, what evidence exists, how to roll it back, and the run log that proves it. Covers threshold changes, gate overrides, new automations, decommissioning, and stakeholder rollout. Use before changing any automation that produces a reported number, and whenever a data-quality BLOCK is overridden. Trigger on "change the pipeline", "update the automation", "override the gate", "adjust the threshold", "deploy the change", "SOX", "audit trail", "who approved", "roll out to the team".

nvzver Skill

Recommend what to work on next. Input: none (or a plain 'what's next' / 'recommend an order' question). Output: a plain 'what's next' gets a fast-path answer — the highest-priority backlog/not-started roadmap item quoted with a file:line citation, no agent dispatch; 'what should I pick' / 'sequence the backlog' dispatches the project-manager agent for dependency/risk/value sequencing and runs its returned pick gate. Reads ${specs_root}/roadmap.yaml on demand via scripts/roadmap-row.sh (whole-file read is fallback only).

nvzver Skill

Check roadmap hygiene and apply approved fixes. Input: none. Output: proposed row diffs (stale/inconsistent entries — missing pitch, status vs branch mismatch, merged-but-not-shipped) delivered and gated one by one via AskUserQuestion; only approved rows are written, each quoted inline. Runs inline — no agent dispatch. Reads ${specs_root}/roadmap.yaml on demand via scripts/roadmap-query.sh hygiene (whole-file read is fallback only).

nvzver Skill

Decompose a pitch into independently-shippable epics. Input: a pitch slug or path (argument; if omitted, the highest-priority backlog pick). Output: the project-manager agent's epic list delivered and gated (approve / reject / adjust) via AskUserQuestion; on approval the first epic seeds an lsa:discover handoff and the remaining epics are surfaced. Reads ${specs_root}/pitches/<slug>.md.

nvzver Skill

Plan and run parallel implementation of roadmap epics — the parallel build-execution entry point. Triggers on 'run agents in parallel', 'implement the backlog in parallel', 'parallel implementation', or 'ship epics to PR in parallel'. Computes a dependency-ordered wave plan via the disjoint-epic decomposer, proposes it for approval, then dispatches one agent per epic in an isolated git worktree, gates each via the independent lsa:reconcile + the .lsa.yaml gate: checks, and converges via the serialized merge. Honors the .lsa.yaml autonomy ladder (manual = human merges · semi = auto-merge on green · auto = + deploy + healthcheck; default manual). Input: [epics] (slug/path list) + optional --parallel / --sequential; the no-arg form is a read-only preview of parallelizable backlog items. Output: an approved wave plan, per-epic worktree/PR dispatch, and a gate-proven roll-up (merged @ <sha> / deployed reported only when the gate proved it). Reads ${specs_root}/roadmap.yaml.

ryanalberts Skill

Turn a raw customer signal (quote, support ticket, feature request, exec ask) into a structured Product Requirements Document. Use when a PM mentions a customer quote and wants a spec, when "let's write a PRD" comes up, when a vague feature request needs scoping, or when the user asks for a problem statement, MoSCoW prioritization, success metrics, or PRD template.

ryanalberts Skill

Synthesize many raw customer signals (support tickets, interview snippets, churn reasons, sales notes, NPS verbatims, app reviews) into a small set of ranked, PRD-ready problems. Use when a PM pastes or attaches a pile of feedback and asks "what's the real problem / what should we build first / what are the themes", when there are too many signals to read one by one, or when someone needs to turn voice-of-customer data into prioritized problem statements before writing a PRD. This is the front-of-funnel step that precedes pmstack-prd.