31 skills
thermo-nuclear-code-quality-review
Passed all 3 security checksRun an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
·0↓2.5k
deslop
Passed all 3 security checksRemove AI-generated code slop and clean up code style
·0↓920
fix-merge-conflicts
Passed all 3 security checksResolve merge conflicts non-interactively, validate build and tests, and finalize conflict resolution
·0↓495
make-pr-easy-to-review
Passed all 3 security checks·0↓22
fix-ci
Passed all 3 security checksFind failing PR checks, inspect logs or external check links, and apply focused fixes
·0↓21
loop-on-ci
Passed all 3 security checksMonitor PR checks and fix failures until green. Uses gh pr checks as the source of truth for PR-attached checks.
·0↓21
what-did-i-get-done
Passed all 3 security checksSummarize authored commits over a user-specified time period into a concise update
·0↓21
check-compiler-errors
Passed all 3 security checksRun compile and type-check commands and report failures
·0↓21
verify-this
Passed all 3 security checksVerify a claim with fresh local evidence: restate it falsifiably, capture baseline and treatment, compare artifacts, and return VERIFIED, NOT VERIFIED, or INCONCLUSIVE.
·0↓20
get-pr-comments
Passed all 3 security checksFetch and summarize review comments from the active pull request
·0↓20
new-branch-and-pr
Passed all 3 security checksCreate a fresh branch, complete work, and open a pull request
·0↓20
workflow-from-chats
Passed all 3 security checksExtract durable working preferences from recent Cursor chats and convert them into skills, rules, or workflow docs. Use when asked to learn preferences, mine feedback, personalize workflows, or generate team/person-specific agent guidance.
·0↓20
review-and-ship
Passed all 3 security checksReview the current branch for bugs, intent fit, and test coverage; run or write tests; commit focused work; open or update a PR.
·0↓20
pr-review-canvas
Passed all 3 security checks·0↓20
control-cli
Passed all 3 security checksBuild or adapt a local harness to drive, inspect, and profile an interactive CLI or TUI without external services. Use for CLI UX checks, startup regressions, memory leaks, hangs, prompt flows, or terminal demos.
·0↓20
weekly-review
Passed all 3 security checksProduce a weekly synthesis of authored commits with highlights by bugfix, tech debt, and net-new work
·0↓20
control-ui
Passed all 3 security checksBuild or adapt a local browser/CDP harness to drive and inspect a web, IDE, or Electron UI. Use for local UI verification, screenshots, accessibility snapshots, perf profiles, visual diffs, or reproducing UI bugs.
·0↓20
run-smoke-tests
Passed all 3 security checksRun Playwright smoke tests, debug failures, and verify fixes
·0↓20
architect
Passed all 3 security checksSketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
·0↓10
unslop
Passed all 3 security checksCut AI tells from any writing. Must always apply.
·0↓8
principle-subtract-before-you-add
Passed all 3 security checksApply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
·0↓8
principle-laziness-protocol
Passed all 3 security checksApply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
·0↓8
typescript-best-practices
Passed all 3 security checksTypeScript best practices. Use when reading or editing any .ts or .tsx file.
·0↓8
why
Passed all 3 security checksUse for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
·0↓8
interrogate
Passed all 3 security checks·0↓8
arena
Passed all 3 security checksSpawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
·0↓8
reflect
Passed all 3 security checksSpawn three parallel review subagents over the active transcript, surface learnings, and route each to a concrete edit on an existing skill. Use when the user says reflect.
·0↓8
automate-me
Passed all 3 security checks·0↓8
thermos
Passed all 3 security checksLaunch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.
·0↓8
principle-prove-it-works
Passed all 3 security checksApply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or 'it compiles.'
·0↓7
principle-fix-root-causes
Passed all 3 security checksApply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
·0↓7