Code Review
Automated code review and analysis
implementing-ef-core
by bitwarden
Implementing Entity Framework Core repositories and migrations for PostgreSQL, MySQL, and SQLite at Bitwarden. Use when creating or modifying EF repositories, generating EF migrations, or working with non-MSSQL data access in the server repo.
reviewing-incremental-changes
by bitwarden
Use this skill when re-reviewing a PR that already has comments or when responding to developer changes after initial review. Apply when PR threads exist or when reviewing force-pushed commits. Handles incremental reviews, detects addressed feedback, avoids duplicate comments, and focuses only on newly introduced issues.
posting-bitwarden-review-comments
by bitwarden
Use this skill when posting inline comments to GitHub pull requests. Apply when formatting comments following Bitwarden engineering standards with severity emojis, clear explanations, and actionable suggestions. Use after findings are classified and ready to post. DO NOT USE when posting summary comments.
posting-review-summary
by bitwarden
Use this skill when posting the final summary comment after all inline comments are posted. Apply as the LAST step of code review after all findings are classified and inline comments are complete. Detects context (GitHub sticky comment, new comment, or local file) and routes output accordingly.
reviewing-security-architecture
by bitwarden
This skill should be used when the user asks to "review the security architecture", "check authentication patterns", "evaluate trust boundaries", "review encryption implementation", "assess authorization design", or needs to evaluate system designs for authentication, authorization, data protection, or cryptographic correctness.
analyzing-git-sessions
by bitwarden
Analyzes git commits and changes within a timeframe or commit range, providing structured summaries for code review, retrospectives, work logs, or session documentation.
josh-braun-copywriting
by sachacoldiq
Josh Braun's 5 cold email writing principles plus personalization best practices. Use when refining email copy, improving message quality, or reviewing outreach for common mistakes.
freshworks-publish-skill
by freshworks-developers
Pack and publish completed Freshworks custom apps to the marketplace. Use when the user wants to pack, publish, submit, or deploy a Freshworks app to the marketplace, prepare app for submission, create app package, or asks about app publishing workflow.
testing
by kubb-labs
Testing, CI, and troubleshooting guidance for running the repository's test suite and interpreting CI failures.
pr
by kubb-labs
Rules and checklist for preparing PRs, creating changesets, and releasing packages in the monorepo.
second-opinions
by vinta
Use when wanting independent review from external models before merging, committing, or finalizing architecture or plan decisions, or when the user asks for a second opinion, codex review, or gemini review
dart-log-failure-parser
by flutter
Parse failures from Dart and Flutter test logs.
TDD Green Phase - Make Tests Pass
by anton-abyzov
Write minimal code to make failing tests pass. Use when saying "TDD green", "make tests pass", or "implement for tests".
postgres-optimization
by rohitg00
PostgreSQL optimization including indexes, query plans, partitioning, JSONB operations, and connection pooling
database-optimization
by rohitg00
Query optimization, indexing strategies, and database performance tuning for PostgreSQL and MySQL
release
by AsiaOstrich
"[UDS] Guide release process and changelogs"
bison-strategy
by Senpi-ai
BISON v3.0.1 — Conviction Holder. Patient multi-asset (BTC/ETH/SOL) conviction trader. MIN_SCORE 11 across 9 components (4H/1H structure, momentum, SM alignment, funding, volume, OI proxy, RSI). Conviction- scaled margin tiers (25%/31%/37%) and 7-10× leverage. DSL is wide by design — time-cuts DISABLED — so a real directional thesis can run multiple days into the move. Few trades. Long holds. Big moves. v3.0.1 ships a race-window dedup cache that eliminates the ENGINE_FAILURE retry noise on already-held assets, plus a doubled DSL exit interval to throttle REDUCE_ONLY spam when runtime position-state lags HL.
classifying-review-findings
by bitwarden
Use this skill when categorizing code review findings into severity levels. Apply when determining which emoji and label to use for PR comments, deciding if an issue should be flagged at all, or classifying findings as CRITICAL, IMPORTANT, DEBT, SUGGESTED, or QUESTION.
employer-footprint
by Zal4DW
This skill should be used when the user asks to "check my digital footprint", "what will employers see about me online", "audit my online presence", "what does my digital profile look like to a recruiter", "check my social media for red flags", or "employer impression report". Conducts a comprehensive digital footprint analysis through the lens of a potential employer, producing a credit-report style dashboard of positive and negative signals across social media channels, public content, and online presence.
i18n
by d-kimuson
"Use when updating Lingui catalogs or fixing translations"
agent-orchestration-governance
by hushh-labs
Use when changing repo-scoped Codex custom agents, subagent concurrency or depth, delegation policy, or handoff verification rules in hushh-research.
wire-voice-action
by hushh-labs
Wire a functional voice action -- one that mutates state, reads and speaks real data, sends/cancels/confirms something, or calls a backend -- into the Kai action gateway. Use for anything on the "Action" list produced by wire-voice-navigation's Step 0 (never for pure "go to this screen" navigation -- that skill handles those directly and this one refuses to). This is a decision guide, not a linear recipe: functional actions genuinely branch on what they do, and picking the wrong branch either silently no-ops or ships an unconfirmed irreversible mutation.
release-ios-appstore
by hushh-labs
Use when releasing, submitting, or verifying a public Hussh One iOS App Store build cut from green main: Apple-managed signing with an Admin ASC API key, a binary whose backend is chosen by backend_target (default UAT, or production), per-version "What's New" and build attach via the ASC API, and the two-gate dispatch path (prepare-only default, opt-in irreversible public submit).
ship-discipline
by hushh-labs
The Hushh engineering operating standard for building, verifying, and reporting work. Release transitions are explicit user-authorized operations governed by the canonical Admin release SOP; ordinary code changes do not imply UAT or production deployment.