Profile My skills Saved Collections Edit profile Submit a skill

← all publishers

SpencerGoss

@spencergoss source repo

11 published skills

  1. ▌
    Pre Mortem · spencergoss
    Use when reviewing code for fragility before deployment, after completing a feature, before a release, or when the user says "what could break", "find fragile code", "pre-mortem", "what will go wrong", "future bugs". NOT for current bugs (use debug-session) or code style (use refactor-session).
    0
    installs
  2. ▌
    Judge Panel · spencergoss
    Use when a task has a WIDE solution space and one-attempt-iterated is likely to lock in a mediocre first idea — "what's the best way to structure X", "try a few approaches to Y and pick the best", "I'm not sure which design wins", "compare a few implementations", competing-implementation or competing-design forks where the right answer isn't obvious up front. NOT for narrow tasks with one obvious approach (just do it), NOT for stress-testing a single proposal (use devil-advocate).
    0
    installs
  3. ▌
    Decision Log · spencergoss
    Use when choosing between named alternatives (libraries, tools, algorithms, schemas, approaches), when making an architectural decision that has lasting consequences, when the user asks "should we use X or Y", "which approach is better", or "why did we choose X", or when you pick one option over another for non-obvious reasons. Trigger whenever a choice is made that future work would need to understand. For progress logging of completed work (what was built, TODOs), use a project journal instead. This skill = decision rationale storage for lasting architectural choices.
    0
    installs
  4. ▌
    Tdd Workflow · spencergoss
    Use when a spec or plan exists and it's time to write code — or when fixing a bug. Trigger on: "fix this bug", "write tests for", "write a function that", "create a module", "the spec is ready, let's implement", or any request to write working code when the WHAT is already clear. The hard gate: no implementation before a failing test exists.
    0
    installs
  5. ▌
    Debug Session · spencergoss
    Use when something is broken and the cause isn't obvious. Trigger on: "it's not working", "tests are failing", "the build is broken", "nothing is running", "something weird is happening", "it worked before", "I don't know what changed", "rollback this", any error, crash, unexpected output, or regression. Also trigger when an agent made autonomous changes that need auditing or reversing. NOT for design reviews or refactoring — use code-review-session or refactor-session instead. Never assume cause — always diagnose before fixing.
    0
    installs
  6. ▌
    Devil Advocate · spencergoss
    Argues AGAINST proposals on significant decisions. Triggers on architecture decisions, new skill creation, strategy pivots, anything touching live money or production systems. Forces genuine counterarguments before committing.
    0
    installs
  7. ▌
    Security Audit · spencergoss
    Use when you want to find security issues in a codebase — leaked API keys, hardcoded credentials, exposed env files, XSS/SQL injection risks, insecure dependencies, or before going to production. Trigger on: "security check", "audit my project", "scan for secrets", "find leaked keys", "check for vulnerabilities", "hardcoded passwords", "exposed credentials", "make it production-ready", or any first-time public sharing of a codebase.
    0
    installs
  8. ▌
    Spec Driven Dev · spencergoss
    Use when about to build or implement a specific feature with clear scope — before writing implementation code. Trigger on: "implement [feature]", "build [feature]", "add [feature]", "create a system that [does X]", "planning session for [feature]", or an explicit feature request with defined scope. NOT for: vague "let's work on X", simple additions, config changes, bug fixes, or exploratory discussion.
    0
    installs
  9. ▌
    Refactor Session · spencergoss
    Use when improving code structure without changing behavior — cleaning up messy code, extracting functions, renaming for clarity, removing duplication. Trigger on: "refactor this", "clean up this code", "this is too messy", "extract this function", "this function is too long", "rename this", "remove duplication", or any structural improvement task. Hard rule: never refactor and change behavior in the same commit.
    0
    installs
  10. ▌
    Performance Tuning · spencergoss
    Use when code is slow, a pipeline has a bottleneck, a job is taking too long, memory usage is too high, or you need to benchmark before and after an optimization. Trigger on: "this is slow", "optimize", "profile this", "this job takes too long", "pipeline bottleneck", "memory usage", "benchmark", "it's hanging", "takes forever", "needs to be faster", "latency", "why is this slow". Always measure before optimizing — no guessing.
    0
    installs
  11. ▌
    Code Review Session · spencergoss
    Use after writing or modifying code, before committing or merging — to catch bugs, security issues, and quality problems. Trigger on: "review this code", "check my code", "look at what I wrote", "code review", finishing a feature or bug fix, after a tdd-workflow green phase, or before any git commit on non-trivial changes. NOT for design reviews, architecture discussions, or general issue checking — only for reviewing code changes (git diff).
    0
    installs