All authors
Claude Skills by adnanmokhtar
github.com/adnanmokhtar258 skills0 installs0 views
- Demo Data SeedLoads a demo tenant with orders, invoices and refunds into the local database.Votes: 0GitHub stars: 2
- Migration SafetyReviews a migration for locks, rewrites and unsafe defaults before it merges.Votes: 0GitHub stars: 2
- Nest ModuleScaffolds one NestJS feature module with its controller, service, entity and spec.Votes: 0GitHub stars: 2
- Eval RunLLM eval coverage (static, no model calls) per call site and CI gate; runs the project's eval harness on request.Votes: 0GitHub stars: 2
- Llm Gateway AuditLLM call sites first (llm-sites.py), then the seam, call budgets, agent loops and metering — read-only.Votes: 0GitHub stars: 2
- Prompt AuditInside each LLM call: structured output, stop reasons, model ids vs a dated table, per-model params, prompt versions.Votes: 0GitHub stars: 2
- Retrieval EvalRetrieval stage alone: recall@k filtered and unfiltered on a labelled set, the no-context guard, which stage failed.Votes: 0GitHub stars: 2
- Vector Index AuditANN index vs a stated target: exact scan at scale, default params, metric/dim mismatch, filtered recall, stale vectors.Votes: 0GitHub stars: 2
- Algorithm Contract ScanFind input that breaks an algorithm's contract — unsorted search, unstable ties, key collapse, biased draws, geodesy.Votes: 0GitHub stars: 2
- Complexity DerivationDerive the time and space complexity of code or a design — loops, recurrences, amortized, expected vs worst; cited.Votes: 0GitHub stars: 2
- Complexity ScanFind super-linear work on data-sized input, uncapped recursion, cycles and stalled loops; caps resolved, counted proof.Votes: 0GitHub stars: 2
- Numeric Stability ScanFind float error in numeric code (accumulation, cancellation, overflow, conditioning, fast-math) and unsized sketches.Votes: 0GitHub stars: 2
- Align DetectAlign's class ledger and dispatcher: runs the four align detectors and every installed owner detector, maps legacy classes to AL ids, reduces, never halts.Votes: 0GitHub stars: 2
- Convention OracleTiered oracle map for align; drops rows citing no oracle, reports splits, unenforced rules and stale docs (AL-01–04).Votes: 0GitHub stars: 2
- Convention Ratchet ScanConvention-rule suppressions, ratchet growth, per-package lint drift and half-done declared migrations (AL-29–32).Votes: 0GitHub stars: 2
- Find And AlignAlign's per-row fix as a proof ladder: route non-align rows, classify EQ/VC/FN, cheap diff gates, re-detect to zero, zero style diff or an approval.Votes: 0GitHub stars: 2
- Naming Layout ScanFile, directory, identifier, synonym and placement names vs the naming rules the project declares (AL-16–19).Votes: 0GitHub stars: 2
- Wrapper Adoption ScanFind live code that bypasses a declared wrapper: raw or banned imports, copies of a named helper, deep imports, a missing required prop or gate.Votes: 0GitHub stars: 2
- Api Consistency AuditAPI surface consistency audit — 22 drift fingerprints across endpoints, covering response envelope shape, error contract, pagination, resource-path and field naming, idempotency keys, auth/rate-limit/security headers, conditional requests (ETag/If-Match), batch contract, log and metric naming, timeout-retry policy, and OpenAPI coverage. Used by /polish on backend-* stacks; 16 fingerprints emit a closure verb from a closed 15-verb vocabulary, 6 emit a routed observation with no verb. Every fin...Votes: 0GitHub stars: 2
- Api SnapshotSnapshot the API's OpenAPI spec and diff it against the last committed snapshot, blocking merge on breaking changes that carry no ADR. Run on any controller or DTO change. Proves the *declared* contract held — `endpoint-test-method` is the runtime counterpart that proves the running route still matches its DTO.Votes: 0GitHub stars: 2
- Debug TenantDebug tenant isolation issues — a user sees data that doesn't belong to them, or doesn't see data that does. Use on a suspected cross-tenant leak or a missing-data report; walks the full tenant-resolution chain hop by hop. Not a static scan — it reproduces against a running system via `log-tail-method` and `endpoint-test-method`.Votes: 0GitHub stars: 2
- Edge Error ScanEdge errors: catch-alls that flatten status, unmapped ORM errors, wrong-adapter filters, default error paths — read-only.Votes: 0GitHub stars: 2
- Endpoint Test MethodHit a running dev endpoint via curl and verify status + response shape + required headers (auth, tenant) field-by-field against the DTO. Use AFTER any controller, DTO, guard, pipe or interceptor edit to prove the route works end-to-end, or when a frontend reports an unexpected shape and you need ground truth. NOT when no dev server is running (it refuses to auto-start), NOT against staging/prod hosts, and NOT for static contract diffing — that is api-snapshot.Votes: 0GitHub stars: 2
- Env DiffCompare .env against .env.example — flag missing keys (will break at runtime), orphan keys (dead config), and unvalidated keys (absent from the env schema). Run after pulling a branch that may have added env vars, after editing the env schema, and in CI as a pre-deploy gate. Checks key presence and validation wiring only, never whether a value is correct.Votes: 0GitHub stars: 2
- Http Contract ScanHTTP contract: action POST 201, missing → 200 null, unsafe GET, PUT/PATCH, pagination, spec drift — read-only.Votes: 0GitHub stars: 2
- Job Lifecycle ScanJobs and schedules: model in the payload, deleted record, payload drift, self-overlap, misfire, schedule zone, lost failure — read-only.Votes: 0GitHub stars: 2
- Log Tail MethodTail structured logs from the dev server, filtered by correlation id, level, or module. Use when a request failed and you need what the server actually recorded — a 500 with no body, a trace to follow end-to-end, an error whose stack never reached the client. Reads what was already logged; it cannot recover a field the code never emitted, does not tail production, and is not a metrics or APM query.Votes: 0GitHub stars: 2
- Module ScaffoldGenerate a complete module following the project's declared architecture — entity, repo, service/use-case, DTOs, controller, tests, DI wiring, migration. Use when creating a new feature module from scratch or replacing a prototype with a properly-layered version. Emits structure, not verified behaviour — run `endpoint-test-method` on each scaffolded route once wired.Votes: 0GitHub stars: 2
- Parallelize Independent OpsConvert a sequential I/O-bound code path into bounded parallel execution using the project's concurrency primitive. Used when an endpoint, batch job, or aggregation does N independent awaits in a loop — the most common backend perf failure. Refuses to parallelize when data dependencies, transactions, or shared keys make it unsafe.Votes: 0GitHub stars: 2
- State Transition ScanState machines: an illegal event answered as success, a terminal state re-opened — FSM-library semantics, read-only.Votes: 0GitHub stars: 2
- Validation Boundary ScanValidation boundary: bodies the pipe never sees, coercion before validation, null via optional, unknown keys — read-only.Votes: 0GitHub stars: 2
- Wire Format ScanWire format: Decimal and 64-bit numbers, serializer reshaping, float money in carriers, time binding and offsets — read-only.Votes: 0GitHub stars: 2
- Check Business CoverageBusiness cycles: forward action with no inverse, API-only inverse, send without resend, unsubscribe, erasure, dead ends.Votes: 0GitHub stars: 2
- Ledger ScanLedger rules: balanced and append-only postings, idempotent posting, balance cache, reconciliation, records retention.Votes: 0GitHub stars: 2
- Lifecycle ScanLifecycle graph: unreachable and trap states, declared vs built graph, cross-aggregate status, provider events, history.Votes: 0GitHub stars: 2
- Pricing Rule ScanMoney rules: rounding policy, units, FX, discounts, price snapshots, promotions, refunds, proration, billing periods.Votes: 0GitHub stars: 2
- Report ScanReport rules: fan-out totals, one metric two ways, exclusions, currency sums, ratio SQL, books reconciliation, business day.Votes: 0GitHub stars: 2
- Tax Invoice ScanTax and issued documents: rate dating, tax base, rounding level, credit notes, e-invoice validation, chains.Votes: 0GitHub stars: 2
- Architectural DiagnosisProject-wide architecture diagnosis, /optimize Phase 0: import-graph lanes per stack, cycles, layer and boundary violations against the declared architecture, coupling, god and bottleneck modules, churn × complexity hotspots, all ranked against the repo's own distribution.Votes: 0GitHub stars: 2
- Change BriefThe comprehension gate — "if you can't explain the code, it isn't yours." For every non-trivial change (AI-generated or human), produce + validate a 5-field change brief (What / Why this shape / Edge cases / Blast radius / Verified by) before the change is committed or a PR opens. Mechanical, not advisory — the brief has a required shape, a hand-wave grep, and a citation requirement; a brief that paraphrases the diff without explaining it is rejected. Wired into /pre-commit and /review-change...Votes: 0GitHub stars: 2
- Correctness Smell ScanFind logic that is wrong for one input — discarded pure results, equality and boolean traps, shared or captured state, float money and unsafe parses, non-exhaustive switches, naive time, leftover breakpoints — each proved by a concrete-input test.Votes: 0GitHub stars: 2
- Dead Code ScanFind code nothing reaches — unused files and exports, unreachable statements, dead flag branches, commented-out code — each proved by a tool report, a zero-importer search and a boot after removal.Votes: 0GitHub stars: 2
- Debt LedgerTrack technical debt as a persisted, ranked ledger — dated/owned TODOs, unjustified suppressions, deprecated-API call sites, major-version-lag deps — each with a blast-radius and a fix-cost, diffed run-over-run so accrual (new debt vs paid-down) is visible instead of rediscovered every audit.Votes: 0GitHub stars: 2
- Duplication ScanFind copies that drifted — clone pairs where a fix reached one copy only, one business rule implemented twice, new clones a change adds — each proved by a divergence test or a new-clones-only run against the merge-base.Votes: 0GitHub stars: 2
- Error Handling ScanFind failures the code hides — empty or log-only handlers, failures returned as empty success, unchecked statuses and error returns, floating promises, catch-alls, lost causes, state the error path never restores — each proved by fault injection.Votes: 0GitHub stars: 2
- Refactoring SweepCodifies the 10 Fowler-style refactoring closure verbs as detector + procedure pairs. Is the core apply-engine of /refactor (these 10 verbs ARE /refactor's closed vocabulary) and is also used by /optimize Phase 2 (tactical) and any /align-recheck run that hits the refactoring class. Each verb has a fingerprint (what triggers it), a procedure (how to apply it safely), and a verify step (what must stay green). Behaviour-preserving — refactoring NEVER changes observable output.Votes: 0GitHub stars: 2
- Smoke VerifyStack-agnostic boot-check run as the FINAL step of a behaviour-preserving sweep (/optimize, /audit, /align, /migrate). A green test suite does NOT prove the app still starts — a refactor can break DI wiring, route/handler registration, an import cycle, or config loading that no unit test exercises. This skill actually boots the app (dev server / HTTP server + health probe / CLI invocation / library import) per PROJECT_KIND and FAILS if it doesn't come up. Reuses frontend/skills/dev-server-sta...Votes: 0GitHub stars: 2
- Suppression ScanFind what the analyzers were told not to say — blanket or rule-less suppressions, suppressed correctness and project-local rules hiding a live diagnostic, correctness rules switched off or left at warn — each proved by an unsuppressed re-run.Votes: 0GitHub stars: 2
- Test ShieldPre-sweep coverage gate for behaviour-preserving work (/optimize, /audit refactor + perf verbs). "Refactor, tests stay green" is only proof of preservation if a test actually exercises the touched branch — on an UNCOVERED branch a structural fix can silently change behaviour and still show green. Before such a fix, this skill detects the touched-but-uncovered branches in scope and pins current behaviour with a characterization test (dispatching /add-test) BEFORE the fix lands, or halts the ro...Votes: 0GitHub stars: 2
- Type Safety ScanFind where types lie at runtime — boundary values cast with no validator, non-null assertions on values that can be missing, checker strictness switched off, untyped exported signatures — each proved by a malformed-input test or the checker's own diagnostic.Votes: 0GitHub stars: 2