Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 74341–74370 of 76496 skills

dokozii-d/hover-translateCarry out a task from work/tasks/ — the implementer agent writes the change, the reviewer agent checks it, findings go back for fixing; the user gets the summary and commits.Stars: 27Updated Claude CodeCodexUnverifiedInstall
releasekozii-d/hover-translatePrepare a release of HoverTranslate — version, changelog, checks, live YouTube markup, store archives, and what the user uploads where. Uploads nothing itself.Stars: 27Updated Claude CodeCodexUnverifiedInstall
taskkozii-d/hover-translateResearch an idea for HoverTranslate and write it up as a task file in work/tasks/ for the implementer agent. Changes no code. An agent invokes it only after the user agreed to that very task in this conversation — propose it and ask first, never on its own judgement.Stars: 27Updated Claude CodeCodexUnverifiedInstall
code-reviewhanzoai/devHanzo standard code quality, simplification, and correctness review: structural simplicity, 1,000-line file discipline, blast-radius verification, runtime proof, deslop, and cross-boundary agreement checks. Enabled by default across Hanzo Dev, Hanzo MCP, and Hanzo AI.Stars: 23Updated Claude CodeCodexUnverifiedInstall
devhanzoai/devHanzo Dev Mode: the smallest change that fully solves the task, and a reply a busy human understands in one read (-53% code, -41% time, -26% cost, -45% tokens, 98% of risky logic ships with a test). Use on any coding task (writing, fixing, refactoring, reviewing, auditing, choosing dependencies) and when the user says "dev", "be lazy", "simplest solution", "yagni", or complains about over-engineering or bloat. Levels: lite, full (default), ultra.Stars: 23Updated Claude CodeCodexUnverifiedInstall
docxhanzoai/devWord Document, Spec & Contract Redlining (`docx`). Draft, edit, and redline `.docx` specifications, MSAs/NDAs, RFCs, and executive memos with clean heading styles, tracked changes, and tables.Stars: 23Updated Claude CodeCodexUnverifiedInstall
pdfhanzoai/devPDF Extraction, Form Processing & Report Generation (`pdf`). Parse tables, OCR scanned documents, fill/merge/split PDFs, and render print-ready technical reports and signed agreements.Stars: 23Updated Claude CodeCodexUnverifiedInstall
pptxhanzoai/devPresentation & Executive Deck Builder (`pptx`). Generate, edit, and structure `.pptx` slide decks, board presentations, pitch decks, and QBR readouts with crisp visual hierarchy and speaker notes.Stars: 23Updated Claude CodeCodexUnverifiedInstall
uihanzoai/devDesign, build, or port user interfaces on the Hanzo stack (@hanzo/ui, @hanzo/gui, @hanzo/design tokens) while achieving measured visual parity across mobile, duo, laptop, and desktop viewports. Use when creating or refactoring UI screens, porting a reference implementation, or fixing layout and responsive regressions.Stars: 23Updated Claude CodeCodexUnverifiedInstall
xlsxhanzoai/devExcel & Spreadsheet Financial Modeling (`xlsx`). Create, audit, and transform `.xlsx` workbooks with dynamic formulas, multi-sheet financial statements, pivot tables, sensitivity matrices, and zero hardcoded magic numbers.Stars: 23Updated Claude CodeCodexUnverifiedInstall
icmarek-burza/workstationWhat to say and type in a mock Python coding interview at Google (45 minutes), from a task summary passed in by the user. Use when the user sends "ic".Stars: 22Updated Claude CodeCodexUnverifiedInstall
igmarek-burza/workstationAnswers the most recent question in a mock exam, from a task summary passed in by the user. Use when the user sends "ig".Stars: 22Updated Claude CodeCodexUnverifiedInstall
imlamarek-burza/workstationGlance sheet for a mock ML/AI system architecture interview at Google (staff level, 60 minutes), from a task summary passed in by the user. Use when the user sends "imla".Stars: 22Updated Claude CodeCodexUnverifiedInstall
imlasmarek-burza/workstationShort prose brief for a mock ML/AI system architecture interview at Google (staff level, 50 minutes), from a task summary passed in by the user. Use when the user sends "imlas".Stars: 22Updated Claude CodeCodexUnverifiedInstall
imlcmarek-burza/workstationWhat to say and type in a mock ML/AI coding interview at Google (45 minutes, PyTorch or NumPy), from a task summary passed in by the user. Use when the user sends "imlc".Stars: 22Updated Claude CodeCodexUnverifiedInstall
ismarek-burza/workstationSummarises the most recent task put to someone being examined, with every detail needed to solve it, from the live transcript and screenshot on the connected cloud drive. Its output is what the user passes to ic, ig, imla, imlas, imlc and isd skills. Use when the user sends "is".Stars: 22Updated Claude CodeCodexUnverifiedInstall
isdmarek-burza/workstationGlance sheet for a mock system design interview at Google (staff level, 60 minutes), from a task summary passed in by the user. Use when the user sends "isd".Stars: 22Updated Claude CodeCodexUnverifiedInstall
adversarial-reviewDevNullLtd/YuzuRun an adversarial two-phase code review of a change with TWO independent reviewers — Claude and Codex — who review alone, then cross-examine each other's findings, then Claude synthesizes a single weighted verdict. Use when the user says "/adversarial-review", "adversarial review", "review this with Codex", "get Codex to review", "two-reviewer review", "cross-examine this PR", or wants a second independent model to grade a change before merge.Stars: 19Updated Claude CodeCodexUnverifiedInstall
auth-and-authzDevNullLtd/YuzuAuthentication & Authorisation control plane for Yuzu — the canonical entry point for any work on RBAC, OIDC SSO, SAML, SCIM, MFA/TOTP, AD/Entra integration, API tokens, session lifecycle, enrollment, and the audit/evidence chain. Use when the user says "/auth-and-authz", "/auth", "/iam", asks to plan or implement an enterprise A&A feature, asks "what's our auth gap to enterprise readiness", asks to audit current auth state against SOC 2 CC6.x / Workstream B, or starts work that touches `auth_*`, `rbac_*`, `oidc_*`, `api_token_*`, `enrollment_*`, or `cert_store.*`. The skill bundles current-state inventory, required-features inventory, gap matrix, the canonical workflow for adding a new A&A feature, and the load order for the routed reference docs.Stars: 19Updated Claude CodeCodexUnverifiedInstall
ci-cacheDevNullLtd/YuzuStars: 19Updated Claude CodeCodexUnverifiedInstall
dev-teamDevNullLtd/YuzuRun the current session as a senior developer (Opus) leading a configurable junior fleet. Decomposes requests into scoped tasks, dispatches junior-developer subagents in parallel, optionally runs an architect plan-review gate before dispatch, autonomously resolves escalations, optionally dispatches a doc-writer second wave after juniors complete, then integrates and gates with /test + /governance. Use when the user says "/dev-team", "run the dev team", "delegate this to the juniors", "act as the senior dev", or wants a task built by a senior-led fleet.Stars: 19Updated Claude CodeCodexUnverifiedInstall
gateway-dialyzerDevNullLtd/YuzuRun dialyzer over the Yuzu Erlang gateway. Sources the Erlang toolchain and runs rebar3 dialyzer. Use after any .erl change in gateway/ — CLAUDE.md mandates dialyzer be clean before commit because compilation success does not imply type correctness.Stars: 19Updated Claude CodeCodexUnverifiedInstall
gateway-eunitDevNullLtd/YuzuRun the Yuzu Erlang gateway eunit test suite correctly. Sources the Erlang toolchain, uses --dir to work around rebar3 auto-discovery bug (#337), and explains how to interpret the output. Use when the user asks to run gateway unit tests, verify a gateway change, check for regressions in eunit, or chase an eunit flake.Stars: 19Updated Claude CodeCodexUnverifiedInstall
goDevNullLtd/YuzuReview a Yuzu pull request end to end with a static-first trust gate, isolated dynamic testing, adversarial Kimi/Codex review, a posted verdict, and head-SHA-bound re-review. Use when the user types forms such as "go PR123", "go 123", or "/go PR123"; use `--promote SHA` only after a collaborator accepts the static review of an external fork.Stars: 19Updated Claude CodeCodexUnverifiedInstall
governanceDevNullLtd/YuzuRun the Yuzu full governance pipeline on a commit range. Produces Gate 1 Change Summary, then orchestrates Gates 2-6 as parallel agent fan-outs with pre-written prompt preambles. Use when the user says "/governance <range>" or "full governance" or asks to run the multi-gate review pipeline on a PR/commit set.Stars: 19Updated Claude CodeCodexUnverifiedInstall
grill-meDevNullLtd/YuzuInterview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".Stars: 19Updated Claude CodeCodexUnverifiedInstall
haDevNullLtd/YuzuHigh Availability control plane for Yuzu — the canonical entry point for any work on ADR-2002 (active-active server tier, gateway-fronted routing, Postgres-backed coordination seam, HA Postgres storage). Use when the user says "/ha", "/high-availability", "/ha-matrix", asks to plan or implement an HA workstream (WS-0…WS-14), asks "what's our HA gap" or "is it safe to run a second replica yet", asks to audit HA readiness, or starts work touching the coordination seam (leader election / fenced epochs / transactional outbox), gateway intra-cluster routing, shared `AgentRegistry` presence, PKI/CA HA, or the `deploy/docker/*ha*` / `scripts/ha/` surface. The skill bundles the two-axis model, the safe-to-scale gate, the delivery matrix (current-state + reviewers + status), the per-workstream workflow, and the load order for the routed reference docs.Stars: 19Updated Claude CodeCodexUnverifiedInstall
releaseDevNullLtd/YuzuCut a Yuzu release end-to-end. Runs preflight checks, validates compose-file version pins, pushes the tag, monitors the release workflow until artifacts publish, troubleshoots known failure modes (artifact download bugs, version mismatch, Windows signing, macOS notarization), verifies the GitHub Releases page has every expected asset including the Compose Wizard zip, and produces a release record. Use when the user says "/release vX.Y.Z" or asks to cut a release.Stars: 19Updated Claude CodeCodexUnverifiedInstall
splitDevNullLtd/YuzuPresentation/Core/Engine split control plane — the canonical entry point for any work decomposing the Yuzu server into three binaries (presentation · core · engine) per ADR-0031-presentation-core-engine-decomposition / ADR-0032 (the admission interlock) / ADR-0033 (access-control spine). Use when the user says "/split", "/pce-split", "/decomposition", asks to plan or implement a split workstream (WS-A*, WS-B*, WS-X*), asks "what's our gap to the presentation/core split" or "is it safe to extract presentation/the engine yet", asks to audit split readiness, or starts work touching the seam (handlers calling stores directly, the INV-31-4 contract test, the Drogon port, `server/presentation` or `server/engine`, the `uce` DB grants, component service identity, or the ADR-0032 admission/grant/audit substrate — `use_case_run_id`, the release log, the capability-declaration registry).Stars: 19Updated Claude CodeCodexUnverifiedInstall
testDevNullLtd/YuzuRun the Yuzu pre-commit/pre-push test pipeline. Compiles HEAD, stands up the previous release, upgrades it, runs the full standard test surface, records every result + sub-step timing into a durable SQLite test-runs DB. Use when the user says "/test" or asks to run the full test pipeline before commit.Stars: 19Updated Claude CodeCodexUnverifiedInstall