nemo-skills-collection

Find why something isn't working — the real cause, not just the symptom. Use this skill when a bug, failure, or unexpected behavior needs to be diagnosed before it can be fixed. Covers hypothesis-driven debugging, evidence gathering, root cause isolation, and verification. Trigger phrases: "why isn't this working?", "find the root cause", "something is broken but I don't know why", "debug this", "the error doesn't make sense", "it works locally but not in production", "intermittent failure", "trace this bug", "what's causing this?". This skill finds WHY — work-audit finds WHAT IS WRONG, project-monitor detects THAT something is wrong. DISAMBIGUATION — use a different skill instead when: the problem is in production NOW with users affected, needing coordinated crisis response (use incident-response; it calls this skill for its diagnosis step); the problem is specifically slowness or capacity under load (use performance-scaling); reviewing not-yet-broken work for latent defects (use work-audit). Choose debuggin

Diagnose performance problems, optimize bottlenecks, and plan for scale. Covers profiling, load testing, capacity planning, and scaling decisions (vertical vs horizontal, caching, CDN, database read replicas, etc.). Use this skill when something is too slow, when preparing for growth, when load testing before a launch, or when deciding how to scale a system. Trigger phrases: "this is too slow", "optimize performance", "load test this", "prepare for 10x traffic", "capacity planning", "the system is struggling under load", "should we scale horizontally or vertically?", "where is the bottleneck?", "performance profiling", "latency is too high". DISAMBIGUATION — use a different skill instead when: the slowness is a sudden production incident affecting users now (use incident-response); the cause is a specific bug rather than capacity or load (use debugging-rootcause); the slowness is specifically database queries or schema (use database-maintenance). Choose performance-scaling for profiling, optimization, load te

Extract actionable learning from completed work — what went well, what didn't, and what will actually change as a result. Use after a project, sprint, release, or significant event. Produces concrete action items, not just discussion. Trigger phrases: "retrospective", "retro", "what did we learn from this project?", "what went wrong?", "how do we improve?", "post-project review", "what should we do differently next time?", "team reflection", "lessons learned". A retrospective without action items is a venting session. This skill produces change. DISAMBIGUATION — "what went wrong" is ambiguous: learning from a COMPLETED project or sprint to improve future work → retrospective (this skill); finding the technical cause of a SPECIFIC failure or bug → debugging-rootcause; deciding the future DIRECTION of an ongoing project → project-compass. Choose retrospective when the work is done and the goal is team learning.

Plan and implement a complete testing approach — unit tests, coverage analysis, verification, and validation. Use this skill when writing tests for new code, when coverage is insufficient, when tests don't catch real bugs, when validating that work meets requirements, or when setting up a testing strategy for a project. Trigger phrases: "write unit tests", "test this code", "improve test coverage", "coverage analysis", "verify this works", "validate this meets requirements", "testing strategy", "how do we test this?", "tests aren't catching bugs", "what should we test?", "is this correct?", "does this do what was asked?". Covers V&V — Verification ("built it right") and Validation ("built the right thing"). DISAMBIGUATION — choose by test level: unit tests, coverage analysis, and verification/validation of individual components → testing-strategy (this skill); full system flows from user input to output, integration test strategy → e2e-testing; finding defects in an already-produced deliverable → work-audit.

Detect, prevent, and verify hallucinations in agent outputs — especially numerical calculations, factual claims, data references, citations, and reasoning chains. Use this skill whenever an agent produces numbers, statistics, dates, names, quotes, or data-derived conclusions that could be fabricated or wrong. Trigger when the user says "verify this output", "the agent made up numbers", "check these calculations", "fact-check the agent", "the agent cited something wrong", "I don't trust this output", or when reviewing any agent output that will be used for decisions, reports, or communications. Also trigger proactively when designing agents that handle financial data, medical information, legal content, or any high-stakes numerical work. Anti-hallucination has three modes: PREVENT (before), DETECT (during), VERIFY (after).

Evaluate whether a goal, feature, project, or investment is worth pursuing — before committing resources to it. Covers ROI, opportunity cost, timing, reversibility, strategic fit, bias correction, and exit criteria. Use this skill when deciding whether to start something new, when a goal feels compelling but unclear, when you need to justify a commitment, or when you suspect the real cost or value hasn't been honestly assessed. Trigger phrases: "is this worth doing", "should we pursue this", "evaluate this goal", "is the ROI good enough", "is the scope too small to bother", "help us decide if this is worth it", "we're thinking of doing X — is it a good idea", "is this the right thing to focus on", "assess this opportunity", "should we invest in this". Outputs one of five verdicts: PURSUE / REFINE / DEFER / DESCOPE / DROP. Use before project-compass (direction) and working-standards (execution).

Transfer work, context, and responsibility between people, teams, or phases with nothing lost in translation. Use this skill whenever ownership or work moves from one party to another — design to engineering, engineering to QA, team to team, person to person, or phase to phase. Trigger phrases: "hand this off", "transfer ownership", "design handoff", "dev handoff to QA", "knowledge transfer", "someone else is taking over", "document this for the next person", "onboarding the new owner", "passing the baton", "what does the next team need to know?", "prepare for handoff". A handoff is not done when the giver says "it's ready." It is done when the receiver confirms they have everything they need.

Identify what to improve, which direction to develop, what to continue or cut, and what to do next to unlock a project's potential. Use this skill when a project needs strategic direction rather than defect-fixing — when the question is not "is this broken?" but "where should this go and how do we get there?" Trigger phrases: "what should we focus on next", "where should this project go", "what's worth improving", "should we continue or pivot", "what's holding this back", "help us prioritize", "what has the most potential", "what should we cut", "what's the next big move", "how do we make this better", "improve this project", "what direction should we take", or any question about what to build, keep, or drop. This skill gives strategic direction — not defect lists (work-audit) or scope checks (project-qa). It answers: what next, and why. DISAMBIGUATION — choose by what "next" means: strategic direction for an EXISTING project (grow/cut/pivot) → project-compass (this skill); sequencing MULTIPLE goals onto a ti

Translate an approved goal into an actionable execution plan — with task breakdown, dependency ordering, effort estimates, risk per task, milestones, and a clear sequence to start immediately. Use this skill after goal-evaluator outputs PURSUE or DESCOPE, and before working-standards begins execution. Trigger phrases: "plan this out", "break this down into tasks", "how do we approach this", "create a project plan", "sequence these tasks", "what should we do first", "turn this goal into steps", "estimate how long this will take", "map out the dependencies", "build a sprint plan", "what's the execution plan". This skill bridges decision (goal-evaluator) and execution (working-standards). It answers: what exactly needs to happen, in what order, by when. DISAMBIGUATION — "plan this out" is ambiguous: breaking ONE approved goal into executable tasks with dependencies and estimates → project-planner (this skill); sequencing MULTIPLE goals across a timeline → roadmap-planning; designing the technical architecture be

Build and maintain a product roadmap — prioritizing goals across multiple initiatives, placing them on a timeline, managing dependencies between goals, and communicating the plan to different stakeholders. Use this skill for quarterly planning, annual planning, or whenever multiple goals need to be sequenced and communicated as a coherent plan. Trigger phrases: "build a roadmap", "quarterly planning", "prioritize these goals", "what do we work on this quarter?", "how do we sequence these initiatives?", "stakeholder roadmap", "product roadmap", "annual planning", "what's our plan for the next 6 months?", "re-prioritize the roadmap", "how do we communicate what we're building?". Bridges goal-evaluator (should we do this?) and project-planner (how do we do this?). Answers: what, in what order, by when.

Review project deliverables for defects, quality issues, and gaps before they are accepted, published, or handed off. Use this skill when reviewing any project output — code, documents, designs, data, reports, plans — to find problems before they cause rework downstream. Trigger phrases: "review this before we ship it", "audit this deliverable", "find issues in this", "QA this output", "something feels off about this", "check this before sending", "review the quality of this work", "is this good enough to ship?", "find defects in this code/document/design". This skill finds WHAT IS WRONG with what was produced. DISAMBIGUATION — "review this" is ambiguous; choose by what you're checking for: defects and quality issues in the deliverable → work-audit (this skill); whether the work matches the agreed scope and requirement → project-qa; whether the code is correctly tested and verified → testing-strategy; whether the plan has hidden risks or blind spots → tenth-man. When the request is a general "review before sh

Plan and execute database operations safely — schema changes, migrations, query optimization, index management, backup verification, and capacity planning. Use this skill when designing a schema, planning a migration, diagnosing slow queries, managing database health, or preparing for data growth. Trigger phrases: "design this schema", "plan this migration", "slow query", "optimize this query", "add an index", "database is getting slow", "how do we migrate this safely?", "database capacity planning", "backup strategy", "database maintenance plan".

Design and implement an end-to-end testing strategy that validates the full system from user input to expected output. Covers test pyramid strategy, coverage planning, test design, and maintenance. Use this skill when setting up a testing strategy for a new project, when existing tests don't catch enough real bugs, when tests are too slow or flaky, or when preparing for a major release. Trigger phrases: "test strategy", "e2e testing", "how do we test this?", "test coverage", "integration testing", "tests keep breaking", "too many flaky tests", "what should we test?", "testing approach", "acceptance testing", "our tests don't catch real bugs".

Respond to production incidents — outages, degradations, data issues, or security events — with a structured process that minimizes impact, coordinates the team, and drives to resolution. Use this skill when something in production is broken, degraded, or behaving unexpectedly and users or stakeholders are affected. Trigger phrases: "production is down", "something is wrong in prod", "users are reporting errors", "the site is slow", "we have an incident", "something broke after the deployment", "critical bug in production", "how do we respond to this?", "who does what during an incident". This skill handles the CRISIS — project-monitor detects the problem, debugging-rootcause finds the cause, release-management deploys the fix.

Track whether a project or product is achieving its goals after release, using defined KPIs, health signals, and structured review cadences. Use this skill after a project or feature has been released to monitor ongoing success, detect when outcomes are not meeting targets, and decide when to escalate to project-compass for a direction change. Trigger phrases: "track project health", "is this working?", "set up KPIs for this project", "monitor outcomes", "the project shipped but we don't know if it's working", "define success metrics", "review how the project is performing", "is the product achieving what we hoped?", "what should we be measuring post-launch?", "something feels off with the results". This skill tracks PROJECT and PRODUCT outcomes — business results, user outcomes, and goal achievement. Not technical infrastructure or AI system behavior.

Manage how project outputs — features, products, reports, or changes — are released to users, clients, or stakeholders. Covers pre-release readiness, communication, rollout approach, and rollback. Use this skill before releasing any project deliverable that affects others, whether it's shipping a feature, publishing a report, deploying a product update, or handing off to a client. Trigger phrases: "how do we release this?", "prepare for launch", "ship this feature", "release plan", "how do we roll this out?", "communication plan for this release", "what do we do before we go live?", "ready to ship?", "release checklist", "how do we announce this?", "rollback plan if this fails". This skill covers the PROJECT RELEASE — not deployment infrastructure.

Identify security vulnerabilities, threats, and gaps in a project, codebase, or system before they are exploited. Covers threat modeling, vulnerability assessment, security testing, and remediation prioritization. Use this skill when starting a project with security requirements, before releasing anything that handles user data or access, when a security concern is raised, or when conducting a periodic security review. Trigger phrases: "security review", "threat model this", "find security vulnerabilities", "is this secure?", "audit this for security issues", "what are the attack vectors?", "penetration test scope", "OWASP review", "security before launch", "assess the risk". working-standards covers security as a principle. This skill does the work.

Design systems and architectures before building them — defining components, interfaces, data flows, trade-offs, and decisions. Use this skill when starting a significant new system, when an existing system needs architectural changes, or when making decisions about how components should connect and communicate. Trigger phrases: "design this system", "architecture for this", "how should we structure this?", "design this before we build it", "system architecture", "what's the right design for this?", "technical design document", "design review", "how do components connect?", "ADR", "architecture decision". Sits between project-planner (what to build) and working-standards (how to build).

Identify, classify, and strategically manage technical debt — deciding what to fix now, what to schedule, and what to live with. Covers debt inventory, refactor vs rebuild decisions, and debt reduction planning. Use this skill when technical debt is slowing down development, when deciding whether to refactor or rewrite, when planning a debt reduction sprint, or when a system is becoming hard to change. Trigger phrases: "technical debt", "the codebase is a mess", "should we refactor or rewrite?", "this is getting hard to change", "we're slowing down", "legacy code", "clean this up", "plan a refactor", "how do we manage debt?", "is it worth cleaning this up?".

Ensure project work stays in scope and matches what was agreed — before starting, during execution, and after delivery. Use this skill when a task feels bigger than it should be, when delivered work doesn't match what was asked for, when scope keeps expanding, or when you want to define clear boundaries before a task begins. Trigger phrases: "is this in scope?", "we're doing too much", "this isn't what was asked for", "define the scope", "the work has expanded beyond the original goal", "QA this task", "does this deliverable match the requirement?", "scope is unclear", "the team keeps adding things that weren't asked for". This skill focuses on SCOPE and REQUIREMENT FIT — not defect quality (work-audit) and not strategic direction (project-compass).

Apply software engineering principles as working standards when executing any project task. This skill guides HOW work gets done on a project — not whether the work is in scope (project-qa) or whether the output has defects (work-audit). Use this skill at the start of any non-trivial project task to establish working standards, and refer to it throughout execution to maintain quality decisions. Trigger phrases: "build this properly", "engineer this well", "follow SE standards", "apply best practices", "do this the right way", "production-quality", "set up a project", "start a new feature", "implement this", or any task where the work will produce code, designs, documents, or systems. These 8 principles are not a scoring rubric — they are working standards for doing good work on any project.

Apply the 10th Man Rule to stress-test plans, proposals, code architectures, decisions, or any output where groupthink or blind spots could cause failure. Use this skill whenever the user asks to "challenge", "stress-test", "red-team", "find flaws in", "critique", or "play devil's advocate" on any proposal. Also trigger when the user seems too confident about a plan ("this should work, right?"), when multiple agents/team members have agreed on something, or when the stakes are high (production deployments, architecture decisions, business strategy, security reviews). Do NOT use for purely stylistic feedback or minor wording changes.