JUNERDD

@junerdd source repo

24 skills
0 followers
8 hours ago last updated

▌
Mr · junerdd bundle
Use and maintain the `mr` Node CLI for generic Git MR/PR branch workflows. Use when the user asks to create, preview, configure, troubleshoot, install, update, uninstall, or explain MR/PR flows with `mr`, `mrm`, `mrt`, or `mrp`; when handling branches named like `mr/target/current`, strategy flags `--merge`, `--rebase`, `--merge-target`, `--pr`, default detached mode (`--detached`, `--no-detached`, `MR_DETACHED`, `mr.detached`), detached conflict worktree placement (`MR_WORKTREE_DIR`, `mr.worktreeDir`), request providers or commands (`MR_REQUEST_PROVIDER`, `mr.requestProvider`, `MR_REQUEST_COMMAND`, `mr.requestCommand`, CNB/GitHub/GitLab), automatic update notices (`MR_NO_UPDATE_CHECK`, `NO_UPDATE_NOTIFIER`), conflict resume, `--rm-mr`, `--dry-run`, diagnostics flags, or the upstream `JUNERDD/mr` implementation behind this CLI.

0
installs
▌
Debug · junerdd bundle
Coverage-first runtime debugging and repair from failure contract through broad first-pass breakpoint/probe batching, root-cause proof, causal repair, separate verification, and cleanup, with language-neutral structured event capture. Use to debug, troubleshoot, diagnose, investigate, fix, repair, resolve, or explain runtime bugs, regressions, flaky or timing-sensitive failures, long-lived streams, expensive or user-only reproductions, broad instrumentation, or bundled collector/dashboard operation. Treat debug/fix as end-to-end repair unless explicitly limited to diagnosis or recommendations. Reuse existing project debug instrumentation and collector sessions. Default each runtime run to a user handoff; use agent autonomy only when explicitly delegated for that run or remaining runs. Never let evidence-analysis requests rewrite reproduction ownership. Maintain one ledger through evidence, repair, verification, and cleanup.

0
installs
▌
Bugbot · junerdd bundle
Detect introduced production bugs in local branch or uncommitted changes, persist the review as a fresh Markdown report, then repair confirmed findings and verify the fixes. Use when the user requests Bugbot detection or when conversation context shows an unambiguous intent to act on a Bugbot report; detection does not modify reviewed code or Git state.

0
installs
▌
Grill Me · junerdd bundle
Deeply pressure-test a plan or design by asking one question at a time until assumptions, tradeoffs, risks, failure modes, and scope edges are explicit. Use when the user asks to be grilled, wants a plan or design stress-tested, or needs the live conversation kept in sync with a local Markdown Q&A log.

0
installs
▌
Plan Mode · junerdd bundle
Create or update an editable Markdown implementation plan with code references, decisions, and todos. Use when the user requests a plan, planning-only work, a saved plan file, or architecture and tradeoff analysis as the deliverable. Task complexity or multiple files alone should not activate a planning-only approval gate during authorized implementation.

0
installs
▌
Git Commit · junerdd bundle
Draft a Conventional Commit message from the currently staged Git changes. Use when the user wants a commit message suggestion, asks to summarize staged work into a commit, or needs a Conventional Commit subject/body without actually running `git commit`. This skill must only inspect staged changes and must not stage files, inspect unstaged work, or create the commit.

0
installs
▌
Code Review · junerdd bundle
Perform a deep, scoped review of diffs, pull requests, working trees, files, or pasted code. Use for `/code-review`, merge-safety assessment, or one bounded post-implementation review. Produce a product-grounded report with coverage and issue lineage; keep review read-only and continue already-authorized fixes only after freezing the report.

0
installs
▌
Hack Review · junerdd bundle
Perform a scoped, coverage-led review of a working tree, staged diff, commit range, branch diff, PR, or suspicious implementation to find hack-like implementation risks. Use when Codex must audit brittle shortcuts such as impossible-state fallbacks, masked root causes, duplicate abstractions, hardcoded special cases, boundary bypasses, hidden temporal coupling, write-then-fix-up flows, or other ownership problems, and must write a Markdown report that enumerates all distinct hack-risk findings discovered within the reviewed scope plus coverage gaps and intentional exceptions.

0
installs
▌
Split Commits · junerdd bundle
Split a large or mixed Git working tree into focused local commits by staging one logical batch at a time and using `$git-commit` for staged-diff messages. Use when the user wants separable changes committed independently. Honor authorization for individual batches or the full sequence; ask about a prepared batch only when committing it is not already authorized. Do not push.

0
installs
▌
Thermo Review · junerdd bundle
Perform an extremely strict, report-writing code quality review focused on structural simplification, responsibility concentration, abstraction quality, file-size pressure, spaghetti branching, canonical ownership, type boundaries, and exhaustive recursive candidate sweeps. Use for thermo-nuclear code quality review, thermonuclear review, harsh maintainability review, deep code quality audit, structural quality gate, or when asked whether a change is too complex or should be restructured. Writes a Markdown report and does not make code changes unless explicitly asked for fixes.

0
installs
▌
Find Local Skill · junerdd bundle
Decompose a user request into deliverables, workflow phases, tools, domains, and implicit prerequisites, then find and select applicable local skills from Cursor, Claude Code, OpenCode, Codex, and shared Agent Skills roots before analyzing or handling the request. Use when the user asks to find, choose, inspect, route, or reason about available local skills; when a request explicitly says to check all local/available skills first; or when doing skill-aware requirement analysis, planning, or capability routing where deeper request understanding is needed before skill selection.

0
installs
▌
Regression Review · junerdd bundle
Perform a scoped, coverage-led review of working tree, staged, commit-range, branch, or PR changes to find user-visible behavioral regressions. Use when Codex must audit code changes for broken or degraded user journeys, changed defaults, loading/error/permission/session behavior, stale data, ordering, retries, duplicate/destructive actions, exported output, emails, CLI output, or other visible behavior, and must write a Markdown report that enumerates all distinct findings discovered within the reviewed scope plus coverage gaps, intentional visible changes, and scoped behavior-graph deltas when they clarify the affected path.

0
installs
▌
Comment Strategist · junerdd bundle
Add or rewrite code comments with calibrated granularity so they explain intent, constraints, data meaning, contracts, and control-flow decisions instead of translating syntax. Use when Codex is asked to document existing code, improve low-value comments, add structured comments to functions, interfaces, classes, types, fields, exported constants, configuration objects, state transitions, or complex internal logic while preserving the repository's existing comment language and style.

0
installs
▌
Reduce Reinvention · junerdd bundle
Identify, prevent, and remediate 重复造轮子 across code, libraries, services, templates, docs, platform workflows, and architecture decisions. Use when asked to audit duplicated implementations, search for existing reusable assets before building, decide build-vs-reuse/buy, consolidate similar components/tools/APIs, create reuse catalogs, write ADR/RFC/migration plans, establish golden paths/paved roads, or improve discoverability, ownership, and governance for reusable assets.

0
installs
▌
Composable Components · junerdd bundle
Authors or refactors accessible primitive and product compound React components with genuinely configurable subparts, transparent host props and refs, data-rendering boundaries, state ownership, asChild/Slot behavior, and private underscore file-type folders. Use for compound component APIs, composable UI primitives, product composers, polymorphic parts, or their component-local _components/_types/_helpers/_utils layout.

0
installs
▌
Multitask Coordinator · junerdd bundle
Explicit-only coordination for non-trivial multi-step work with dependency-aware, hierarchical subagent scheduling. Use only when the user explicitly invokes or names `$multitask-coordinator` to coordinate parallel or dependent workstreams, recursive subplanners, ephemeral shared memory, migrations, large repositories, dirty or isolated worktrees, uninterrupted workers, or multi-agent orchestration audits; otherwise do not select it proactively. After invocation, build a task and decision graph, assign one owner per decision domain and write boundary, dispatch useful ready work, preserve healthy workers, route conflicts to the correct owner, integrate evidence, and verify the result.

0
installs
▌
Receiving Code Review · junerdd bundle
Resolve code-review reports, PR feedback, or equivalent comments. Verify current execution chains and product intent, challenge incorrect or stale claims, and implement confirmed actions with a disposition ledger. Use for review follow-up that preserves staged work and settled decisions, with at most one terminal post-implementation review.

0
installs
▌
Receiving Hack Review · junerdd bundle
Resolve hack-review reports or feedback about brittle shortcuts, duplicate ownership, masked causes, and boundary bypasses. Verify the current invariant owner and bounded intentional exceptions before applying scoped fixes. Use to challenge stale claims and account for every finding and ownership gap without blindly removing necessary guards.

0
installs
▌
Delegate To Cursor Sdk · junerdd bundle
Opt-in workflow for routing bounded coding tasks through the independent cursor-delegate CLI and Cursor SDK, with reviewed implementation packets, internal subagents, hierarchical workstreams, follow-up packets, a chronological no-regression execution dashboard with Stop controls, agent-guided loopback API-key authorization, a global authorization barrier, and owned temporary-artifact cleanup. Use only when the user explicitly injects or names `$delegate-to-cursor-sdk` / `delegate-to-cursor-sdk`; otherwise do not select it proactively.

0
installs
▌
Exhaustive Code Slimmer · junerdd bundle
Exhaustive code slimming, code-pruning, and approval-gated architecture cleanup workflow for maximizing removable code while preserving behavior and improving developer experience. Use when the user asks for code cleanup, ruthless simplification, dead-code removal, dependency pruning, refactoring for less code, DX architecture review, exhaustive shrinking, maximal code reduction, redundancy removal, or aggressive but behavior-preserving simplification.

0
installs
▌
Receiving Thermo Review · junerdd bundle
Resolve thermo-review reports or structural quality feedback. Verify responsibility boundaries, decomposition gaps, 350-line findings, and behavior parity before applying scoped fixes or evidence-backed waivers. Use to process existing structural findings, challenge stale or misleading claims, and account for unresolved coverage without changing unrelated code or Git state.

0
installs
▌
Github Context7 Research · junerdd bundle
Reconcile current or version-specific third-party library documentation from Context7 with read-only GitHub evidence from source, types, tests, examples, releases, issues, pull requests, and commits. Use when implementing against an external library, SDK, or framework; diagnosing behavior the docs do not fully explain; checking whether an API changed; or asking how an open-source dependency actually works. Do not use for ordinary questions about the current repository that need no external library evidence.

0
installs
▌
Receiving Regression Review · junerdd bundle
Resolve regression-review reports or feedback about user-visible behavior changes. Verify current inputs, guards, outputs, intended product changes, and coverage before fixing proven regressions. Use to challenge stale or incorrect claims and produce a disposition for every finding, intentional change, and open surface.

0
installs
▌
Artifact Template Soft Focus Color Haze · junerdd bundle
Create restrained, newly composed Soft-Focus Color Haze backgrounds. Use when the user selects this template, names Soft-Focus Color Haze, or explicitly invokes $artifact-template-soft-focus-color-haze. Treat the retained PNG as a style-language reference only: vary the composition instead of copying it, and adapt the color field to support any supplied subject.

0
installs

24 published skills