nightly-lower-code-complexity
Nightly direct-execution skill for reducing code complexity thresholds. Receives pre-computed threshold data, refactors violations, updates thresholds, commits, and creates a PR.
notion-to-jira
>
performance-review
Performance review methodology. N+1 queries, inefficient algorithms, memory leaks, missing indexes, unnecessary re-renders, bundle size issues. Evidence-based recommendations.
plan-execute
This skill should be used for any non-trivial request — features, bugs, stories, epics, spikes, or multi-step tasks. It accepts a ticket URL (Jira, Linear, GitHub), a file path containing a spec, or a plain-text prompt. It assembles an agent team, breaks the work into structured tasks, and manages the full lifecycle from research through implementation, code review, deploy, and empirical verification.
plan-improve-tests
This skill should be used when improving test quality. It scans the test suite for weak, brittle, or poorly-written tests, generates a brief with improvement opportunities, and creates a plan with tasks to strengthen the tests.
plan-local-code-review
This skill should be used when performing a code review on local changes on the current branch compared to the main branch. It uses multiple parallel agents to check for bugs, CLAUDE.md compliance, git history context, previous PR comments, and code comment adherence, then scores and filters findings by confidence level.
pull-request-review
This skill should be used when checking for code review comments on a pull request and implementing them if required. It fetches PR metadata and comments, generates a brief from unresolved feedback, and bootstraps a project to address the review comments.
quality-review
Code quality review checklist. Correctness, coding philosophy compliance, test coverage, documentation quality. Findings ranked by severity in plain English.
reproduce-bug
How to create reliable bug reproduction scenarios. Covers failing tests, minimal scripts, environment verification, and reproduction evidence capture.
root-cause-analysis
Root cause analysis methodology. Evidence gathering from logs, execution path tracing, strategic log placement, and building irrefutable proof chains.
security-review
Security review methodology. STRIDE threat modeling, OWASP Top 10 vulnerability checks, auth/validation/secrets handling review, and mitigation recommendations.
security-zap-scan
Run an OWASP ZAP baseline security scan locally using Docker. Checks for the ZAP baseline script, executes the scan, and summarizes findings by risk level with remediation recommendations.
task-decomposition
Methodology for breaking work into ordered tasks. Each task gets acceptance criteria, verification type, dependencies, and skills required.
task-triage
8-step task triage and implementation workflow. Ensures tasks have clear requirements, dependencies, and verification plans before implementation begins.
tdd-implementation
Test-Driven Development implementation workflow. RED: write failing test, GREEN: minimum code to pass, REFACTOR: clean up. Includes task metadata requirements, verification, and atomic commit practices.
test-strategy
Test strategy design. Coverage matrix, edge cases, TDD sequence planning, test quality review. Behavior-focused testing over implementation details.
ticket-triage
Analytical triage gate for JIRA tickets. Detects requirement ambiguities, identifies edge cases from codebase analysis, and plans verification methodology. Posts findings to the ticket and produces a verdict (BLOCKED/PASSED_WITH_FINDINGS/PASSED) that gates whether implementation can proceed.
verification-lifecycle
Verification lifecycle: classify types, discover tools, fail fast, plan, execute, loop. Includes verification surfaces, proof artifacts, self-correction loop, escalation protocol, and definition of done.
install-wallet-ui-react-native
Use when setting up Wallet UI in a new or existing Expo application. Guides selection between modern @solana/kit (Recommended) or legacy @solana/web3.js.
ui-refactor-extract
Refactor UI code without behavior change (extract/rename/reorganize) while preserving public APIs and adding evidence via tests or inspection.
client-generation
Generate or update typed API clients from canonical contracts.
compatibility-check
Validate API compatibility across versions or consumers.
contract-update
Update request/response API contracts and client wiring without business logic.
authz-policy
Define and enforce authorization rules for protected actions, with tests and audit considerations.
backend-test-additions
Add or extend backend tests to prove behavior, invariants, and regressions for services/endpoints/jobs.
domain-logic-module
Add or refactor domain rules into a testable module boundary with explicit invariants.
endpoint-scaffold
Create a validated, authorized backend endpoint with error mapping and tests.
integration-adapter
Build an external API adapter with timeouts, retries, idempotency, and error mapping.
job-worker-orchestration
Add background jobs and orchestration with idempotency, retries, and observability aligned to repo conventions.
observability-audit
Ensure logging/metrics/tracing and auditability match the quality bar for changed behavior.
persistence-layer-change
Implement schema/migration changes and update data access patterns safely.
a11y-semantics-pass
Improve semantics and accessibility coverage for UI changes (roles, labels, focus, keyboard, ARIA correctness).
component-scaffold
Create a new UI component consistent with repo conventions (structure, typing, styling, exports).
data-fetching-integration
Wire UI to a data source with typed inputs/outputs, loading/error/empty states, and caching rules.
form-validation
Add input validation rules and UX patterns for forms (client-side validation, errors, submit gating) consistent with repo conventions.
frontend-test-additions
Add or extend frontend tests to cover intended behavior and critical UI states.
performance-pass-ui
Identify and reduce avoidable UI performance regressions (render churn, heavy computations, oversized bundles) without behavior change.
state-modeling
Define client state shape and transitions for non-trivial UI flows (multi-step, branching, async, derived state).
kalshi-markets
Access Kalshi prediction market data including market prices, orderbooks, trades, events, and series information. Use when the user asks about prediction markets, Kalshi markets, betting odds, market prices, or needs to search or analyze prediction market data.
ask-questions-if-underspecified
Clarify requirements before implementing. Do not use automatically, only when invoked explicitly.
bootstrap-repo
Bootstrap or refresh a repo scaffold (governance docs, .codex folder, Tree.txt). Use only when explicitly invoked.
create-plan
Create a concise, executable plan for a coding task. Use when the user explicitly asks for a plan or when work is clearly multi-step.
decision-capture
Capture non-trivial decisions as a proposed entry for a repo's decision log (e.g., DECISIONS.md). Use when work involves meaningful tradeoffs.
governance-sync
End-of-work audit that identifies which governance artifacts should be updated based on actual changes. Use when wrapping a milestone/checkpoint or after multi-file/structural work.
intake-interview
Interview to extract intent, constraints, assumptions, and success criteria for a new system or major feature. Produces an Intake Brief (not a plan, not code).
personalize-repo
Tailor a bootstrapped repo into a project-specific operating system by capturing intent, constraints, and preferences, then updating docs and generating a repo-local REPO_PROFILE.json. Use only when explicitly invoked.
prediction-arbitrage-scout
Scout price discrepancies between Polymarket and Kalshi for discovery and comparison. Read-only; no execution.
cartographer
Generate a deterministic project map (Tree.txt + docs/PROJECT_MAP.md) for a repo. Use only when explicitly invoked.
email-best-practices
Use when building email features, emails going to spam, high bounce rates, setting up SPF/DKIM/DMARC authentication, implementing email capture, ensuring compliance (CAN-SPAM, GDPR, CASL), handling webhooks, retry logic, or deciding transactional vs marketing.
send-email
Use when sending transactional emails (welcome messages, order confirmations, password resets, receipts), notifications, or bulk emails via Resend API.
Page 271 of 1445 · 72246 results