Product & Planning

garyld1962 Bundle

Use when the user has a written implementation plan file (typically produced by /execute-prd, in the plan-format contract) and wants it executed — phrases like 'execute the plan', 'run docs/plans/X.md', 'resume the plan'. Not for writing plans (use /execute-prd) or trivial single-file edits.

garyld1962 Skill

Break a PRD into independently-grabbable GitHub issues as vertical tracer-bullet slices. Use when user wants to convert a PRD to tickets, create implementation issues from a PRD — phrases like 'break this PRD into issues', 'create tickets from the PRD', 'slice the PRD into work items'. When NOT to Use: want the PRD executed end-to-end automatically (use /execute-prd); rough idea not yet a PRD (use /goal → /prd-create first); want a plan doc not issues (use /execute-prd step 1).

garyld1962 Skill

Turn an existing story, BRD, PRD, or AERS draft into an implementation-ready AERS. Interviews the author, closes structural and semantic ambiguity against the AERS and ontology rubrics, generates missing sections. Use before planning, /kickoff, or /execute-prd. When NOT to Use: vague intent without a problem statement yet (use /goal first to validate the outcome before writing requirements); no artifact at all (use /prd-create, which owns the blank start and writes the PRD folder).

garyld1962 Skill

Validate implementation against PRD acceptance criteria. Reads a PRD, extracts checkboxes, verifies each with evidence, produces a pass/fail scorecard.

garyld1962 Skill

Plan a refactor through structured interview, then file it as a GitHub issue RFC with a tiny-commit sequence and decision record. Use when user wants to plan a refactor before implementing — phrases like 'plan a refactor', 'create a refactor issue', 'refactor RFC', 'break this refactor into safe steps'. When NOT to Use: refactor already planned and ready to execute (use /execute-plan); quick code cleanup (make focused edits directly); feature work disguised as a refactor (use /prd-validate first).

garyld1962 Bundle

Use when you need a domain glossary. Derives UBIQUITOUS_LANGUAGE.md from the PRD's ONTOLOGY.md; falls back to extracting terms from conversation when no ontology exists.

garyld1962 Skill

Canonical plan document format produced by /execute-prd and consumed by /execute-plan's runtime workflow. Defines frontmatter, task metadata (depends_on, milestone_end), and mechanical acceptance blocks. Not user-invokable.

garyld1962 Skill

Analyze a PRD or plan and produce a parallel-agent execution map with dependency barriers, write scopes, and task ownership for LLM code generation. TRIGGER on: 'parallelize the plan', 'parallel execution map', 'concurrency shape', 'optimize task ownership', 'parallel-safe lanes', 'split this plan into waves', 'after I draft the plan run parallel-optimization', 'add a Parallel Execution section'. Auto-invoked by /execute-prd step 6 — humans rarely need to call this directly except when reshaping a sequential plan into parallel before re-running /execute-plan.

garyld1962 Skill

Interactive checklist and workflow for turning a story, BRD, AERS draft, or rough idea into an implementation-ready artifact for GitHub Copilot workflows.

garyld1962 Skill

Reusable rubric defining the AERS (Agent-Executable Requirements Spec) readiness standard — required sections, closed-decision categories, ambiguity priorities, interaction rules, and the composite readiness score that adds the ontology verdict from _internal/ontology-readiness to the structural score. Consumed by /prd-validate, /kickoff, /execute-prd, and /spec-review-adversarial. Not user-invokable.

garyld1962 Skill

Reusable rubric defining ontology readiness for a requirements artifact — elicitation categories, item states, completeness and extension rules, the ONTOLOGY.md format, and a deterministic ontology score. Composed into _internal/aers-readiness; remedied interactively by /prd-create; consumed by /prd-validate, /ubiquitous-language --from-ontology, /prd-acceptance, /test-plan, and /spec-review-adversarial. Not user-invokable.

hmbown Skill

In D&D, Insight detects lies and reads true intentions. The real-world version is subtext analysis: figuring out what an email actually means, what a stakeholder's real objection is, what a user's bug report is actually describing, or what the unsaid concern is behind a seemingly simple question. Insight does not read minds — it reads signals that are present but not foregrounded.

hmbown Skill

Dimension Door is the quick-switch spell: branch to branch, environment to environment, project to project. It is not a migration and it is not discovery. It assumes both endpoints are known, prepared, and close enough in shape that you can step across with only the context you actually need.

hmbown Skill

Locate Animals or Plants is service discovery with ecological instincts. It helps you find running services, background jobs, data stores, dependency roots, and other living things in an environment before you touch them. The point is not just location, but context: what is active, who depends on it, and what keeps it alive.

delorenj Skill

Add an idea to the backlog parking lot (999.x numbering)

delorenj Skill

Remove a future phase from roadmap and renumber subsequent phases

delorenj Skill

Review and promote backlog items to active milestone

vibeeval Skill

Interactive workspace discovery - learn what tools, workflows, agents, and hooks are available

vibeeval Skill

MCP server registry, auto-discovery, configuration, custom server development guide

vibeeval Skill

Codebase'i derinlemesine anla. Onboarding, architecture discovery, dependency mapping.

ascend-ai-coding Bundle

Deploy vLLM inference services on Ascend NPU servers with automatic model detection and optimized configuration. Supports local and remote deployment across bare metal, containers, and Docker images. Handles model discovery, quantization auto-detection, tensor parallelism configuration, graph/eager mode selection, and service health verification. Use when users need to: (1) Start or deploy vLLM server on NPU, (2) Launch LLM inference service, (3) Configure multi-card tensor parallel deployment, (4) Enable speculative decoding (Eagle) or quantization, (5) Run vllm offline batch inference, (6) Check or test vLLM service status.

ferroxlabs Skill

You have raw material (interview transcripts, sales-call notes, support tickets, churn surveys) and need to turn it into segments the team can write to, price to, and channel to. Or a teammate handed you a demographic and asked for a persona.

ferroxlabs Skill

Creates a customer discovery interview guide with opening script, problem-exploration questions, solution-reaction prompts, closing protocol, and post-interview analysis template using customer development methodology. Use when the user asks about customer discovery, customer interviews, talking to customers, problem interviews, solution interviews, or customer development research. Do NOT use for idea validation experiments (use idea-validation), user research for an existing product (use user-research-plan), or survey design (use employee-survey).

ferroxlabs Skill

Spending pattern identification and expense optimization through subscription auditing, fixed vs variable cost analysis, cost-per-use calculations, lifestyle inflation detection, comparison to median spending by category, and savings opportunity discovery. Use when the user asks about expense analyzer, or needs help with spending pattern identification and expense optimization through subscription auditing, fixed vs variable cost analysis, cost-per-use calculations, lifestyle inflation detection, comparison to median spending by category, and savings opportunity discovery. Do NOT use when the request requires professional financial advice or falls outside the scope of expense analyzer.

ferroxlabs Skill

Builds a written promotion case document with accomplishments and metrics, expanded scope evidence, peer and stakeholder impact, market rate context, and a clear ask. Produces a shareable document the user can present to their manager or leadership. Use when the user wants to make a case for promotion, prepare a promotion packet, or document their achievements to support a level-up request. Do NOT use for performance review self-assessments (use performance-review-prep), salary negotiation scripts (use salary-negotiation-script), or resume writing (use resume-bullet-writer).

ferroxlabs Skill

Produces a word-for-word salary negotiation dialogue with branching responses for different scenarios including initial offers, raise requests, pushback handling, and closing techniques. Works for both new job offers and current role raises. Use when the user wants to negotiate salary, prepare for a compensation conversation, counter an offer, or ask for a raise with specific talking points. Do NOT use for written counter-offer emails (use counter-offer-letter), freelance rate setting (use freelance-rate-calculator), or general career planning (use career-pivot-roadmap).

aws-samples Bundle

Use this skill to investigate and troubleshoot Amazon ECS problems by analyzing service events, task state, container logs, and following structured runbooks. Activate when: tasks fail to start or keep restarting, services can't reach desired count, containers are OOM-killed, task definitions have errors, images can't be pulled, load balancer health checks fail, service discovery doesn't work, tasks can't reach VPC resources or the internet, IAM permissions are denied, capacity providers can't scale, deployments are stuck, exec into containers fails, or the user says something is wrong with ECS without naming specific symptoms.

aws-samples Bundle

Use this skill to investigate and troubleshoot Amazon Managed Workflows for Apache Airflow (MWAA) problems by analyzing environment configurations, DAG import errors, task failures, scheduling issues, VPC networking, web server access, worker scaling, plugin and requirements issues, CloudWatch logging, IAM execution roles, secrets backend, S3 DAG bucket sync, and Airflow connections using structured runbooks. Activate when: environment creation or update failures, version upgrade issues, DAG import errors, task execution failures, scheduling problems, VPC networking issues, web server inaccessible, worker auto-scaling problems, task queue backlog, custom plugin failures, requirements.txt installation errors, CloudWatch log delivery issues, task log missing, IAM execution role permission errors, secrets backend configuration problems, S3 DAG bucket sync failures, Airflow connection issues, or the user says something is wrong with MWAA without naming specific symptoms.

aws-samples Bundle

Use this skill to investigate and troubleshoot Amazon Macie problems by analyzing discovery job failures, classification errors, custom data identifiers, finding analysis, false positives, S3 bucket inventory, sensitive data discovery, multi-account management, cost optimization, sampling configuration, Security Hub integration, and EventBridge notifications. Activate when: discovery jobs failing, classification inaccurate, custom identifiers not matching, unexpected findings, false positive management, S3 bucket inventory incomplete, sensitive data not detected, delegated admin issues, member account problems, high Macie costs, sampling configuration, Security Hub findings missing, EventBridge rules not triggering, or the user says something is wrong with Macie without naming specific symptoms.

aws-samples Bundle

Use this skill to investigate and troubleshoot AWS Cloud Map problems by analyzing namespace configurations, service registrations, instance management, DNS resolution, TTL settings, ECS service discovery, EKS integration, IAM permissions, and VPC associations using structured runbooks. Activate when: DNS or HTTP namespace issues, service registration failures, health check problems, instance registration or deregistration issues, DNS resolution failures, TTL configuration problems, ECS service discovery not working, EKS integration issues, IAM permission errors, VPC association problems, or the user says something is wrong with Cloud Map without naming specific symptoms.

aws-samples Bundle

Use this skill to investigate and troubleshoot Amazon ElastiCache problems (both Redis and Memcached engines) by analyzing cluster configurations, replication groups, parameter groups, CloudWatch metrics, slow logs, and following structured runbooks. Activate when: connection failures, timeout issues, DNS/endpoint resolution, high CPU utilization, memory pressure or evictions, high latency, slow commands, replication lag, failover issues, read replica problems, vertical or horizontal scaling, ElastiCache Serverless issues, eviction storms, memory fragmentation, maxmemory configuration, AUTH token issues, encryption problems, security group/subnet issues, backup failures, restore issues, slot migration, resharding failures, cross-slot errors, Memcached auto-discovery, consistent hashing, Global Datastore replication or failover, or the user says something is wrong with ElastiCache without naming specific symptoms.

williamcorrea23 Bundle

Executes SAP ABAP Development Tools (ADT) REST operations for object discovery, source management, object creation, activation, testing, transport handling, history, where-used analysis, message classes, and text elements. Use when working with an SAP ABAP system and the required ADT operation is unavailable through the currently configured MCP tools.

williamcorrea23 Bundle

Create product master records (materials) in SAP S/4HANA Cloud Public or on-prem private edition via OData V4 api_product/srvd_a2x/sap/product/0002 deep-insert. Use whenever the user wants to create, post, add, generate, seed, or onboard products / materials / SKUs — phrases like "create products in SAP", "seed material master", "add HAWA materials", "onboard FERT goods", "create a SERV record", "make a few demo products". Handles GET-first discovery of tenant's internal unit codes (the V4 vs V2 trap), deep-insert with explicit parent-key duplication in child description (the SADL framework trap), per-ProductType valid Product Group + Base Unit pools, idempotent bulk batches. Do NOT use this skill for SOAP MDM Replicate scenarios (different use case requiring sender business system registration) or for product extension (plant / valuation / sales / procurement views — separate entities on the same V4 service). For those, use the generic s4hana-create-record skill.

williamcorrea23 Skill

Discovers and maintains SAP system inventory across SIDs, roles, hosts, regions, VM sizes, zones, HA topology, and monitoring coverage. Foundation data consumed by all other skills. Validates VM power state on demand. No proxy required — uses Azure Resource Graph and ARM APIs.

ascend-ai-coding Bundle

Analyze Huawei Ascend NPU profiling data to discover hidden performance anomalies and produce a detailed model architecture report reverse-engineered from profiling. Trigger on Ascend profiling traces, NPU bottlenecks, device idle gaps, host-device issues, kernel_details.csv / trace_view.json / op_summary / communication.json. Also trigger on "profiling", "step time", "device bubble", "underfeed", "host bound", "device bound", "AICPU", "wait anchor", "kernel gap", "Ascend performance", "model architecture", "layer structure", "forward pass", "model structure". Runs anomaly discovery (bubble detection, wait-anchor, AICPU exposure) alongside model architecture analysis (layer classification, per-layer sub-structure, communication pipeline). Outputs a separate Markdown architecture report alongside anomaly analysis.

delorenj Skill

CRUD for phases in ROADMAP.md — add, insert, remove, or edit phases