luongnv89

Run OpenCode in a docker-dev sandbox (SSH/gh on by default; --no-ssh/--no-github to isolate). Prints docker exec attach; kept until you confirm rm. Don't use for opencode.ai (opencode-runner), Herdr, or the app.

Scan a live site with isitagentready.com, then approve each step: triage the 0-5 agent-readiness score, write agent-ready-plan.md, file issues via /plan-to-issues. Don't use for applying llms.txt/SEO fixes (seo-ai-optimizer) or app-store ASO.

Convert a phased plan (MODERNIZATION_PLAN.md, sprint tasks) into labelled GitHub issues under one epic whose body maps each issue to its plan task by phase. Run after /codebase-modernizer. Don't use for writing plans, resolving issues, or triage.

Set up or tune any dev machine, fresh or drifted, on macOS, Linux, or Windows: report what's missing, install only that, then fix PATH, duplicate runtimes, and shell config. Don't use for Dockerfiles, CI images, or single package installs.

Optimize App Store and Google Play listings via a 7-phase, plan-approval-gated ASO workflow (keyword strategy, metadata, localization). Don't use for web SEO, paid UA campaigns, or pre-submission compliance audits.

Audit a stale, inherited, or messy codebase — deps, bugs, security, tests, CI, docs, UI/UX — then emit a phased, testable modernization plan. Read-only: plans upgrades, never applies them. Not for single-PR review, PRD-to-tasks, or UX-only audits.

Sync a GitHub fork with upstream while keeping unmerged feature branches and open PRs mergeable. Use for rebase on upstream, PR conflicts, integration main. Don't use for git init, releases, or non-fork repos.

Manage AI agent fleets in Herdr: split root + sub-agents into one tab as a tiled grid, message/wait/read via herdr CLI, steer any pane. Use for Herdr multi-agent fleets. Don't use for tmux, screen, or non-Herdr terminals.

Test a learner on a single Claude Code tutorial lesson (01-10) with 10 questions, scoring answers and flagging weak spots. Use before, during, or after a lesson. Don't use for whole-tutorial assessment or explaining a topic instead of testing it.

Comprehensive Claude Code self-assessment and learning path advisor. Runs a multi-category quiz covering 10 feature areas, produces a detailed skill profile with per-topic scores, identifies specific gaps, and generates a personalized learning path with…

Draft a blog post from ideas and resources. Use when users want to write a blog post, create content from research, or draft articles. Guides through research, brainstorming, outlining, and iterative drafting with version control.

Ensure all communication matches brand voice and tone guidelines. Use when creating marketing copy, customer communications, public-facing content, or when users mention brand voice, tone, or writing style.

Create or update CLAUDE.md files following best practices for optimal AI agent onboarding

Comprehensive code review with security, performance, and quality analysis. Use when users ask to review code, analyze code quality, evaluate pull requests, or mention code review, security analysis, or performance optimization.

Generate comprehensive, accurate API documentation from source code. Use when creating or updating API documentation, generating OpenAPI specs, or when users mention API docs, endpoints, or documentation.

Systematic code refactoring based on Martin Fowler's methodology. Use when users ask to refactor code, improve code structure, reduce technical debt, clean up legacy code, eliminate code smells, or improve code maintainability. This skill guides through a…

Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost. Don't use for authoring new skills, eval retrofits, or prose.

Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.

Improve an external, legacy, or drifted SKILL.md to the skill-creator standard — hard validation gates plus an advisory predictability audit. Don't use for authoring from scratch (skill-creator output is already standard), bulk eval, or prose edits.

Find Agent Skills for a goal the user cannot name yet, then export an installable bundle. Use when they ask which skills fit a project. Don't use for installing named skills, authoring skills, or catalog maintenance.

Add GitHub skill repos to the ASM index: clone, audit, eval, regenerate index, rebuild catalog, open PR. Use when given GitHub URLs to onboard. Don't use for authoring (skill-creator), improving (skill-auto-improver), or install (asm install).

Install an improved variant of one named skill: resolve it by local path, repo, or name, run skill-auto-improver on a throwaway copy, then install the improved result. Don't use for improving in place, upstream PRs, or plain asm install.

Re-ingest every already-enabled repo in data/skill-index-resources.json: sync the working tree, run preindex, rebuild the catalog for verification, summarize updated/unchanged/failed/skipped, then gate commit + PR behind explicit confirmation. Use when asked…

Validate a skill. Don't use for unrelated docs.

Create structured GitHub issues from text, screenshots, or lists, with acceptance criteria and preserved reporter context. Use for filing bugs/features, batch creation, or template cleanup. Don't use for resolving, triaging, or deep issue analysis.

Review a PR end-to-end with CI checks, fix cycles, and optional auto-merge. Use for PR review, cleanup, or readiness checks. Don't use for creating PRs, raw issue analysis, or non-PR code review.

Create an atomic PR closing a GitHub issue end-to-end via a 6-step pipeline. Use to resolve, fix, or implement issue #N. Don't use for analysis without fixing (/issue-analysis), reviewing a PR (/issue-pr-review), or bulk backlog work (/auto-pilot).

Run an autonomous triage-resolve-review-merge loop to auto-pilot the GitHub issue backlog, resolving everything until done with zero prompts. Don't use for single-issue work (/issue-resolver), triage (/issue-triage), or PR review (/issue-pr-review).

Analyze one GitHub issue for root cause, complexity, and risk into .gitissue/analysis-N.json. Use when you need to analyze or scope issue #N. Don't use for creating issues (/issue-creator), triaging (/issue-triage), or resolving (/issue-resolver).

Scan open GitHub issues for dependencies, priority, parallel work, and staleness. Use to prioritize the backlog or pick what to do next. Don't use for one-issue analysis (/issue-analysis), resolving (/issue-resolver), or creating (/issue-creator).

Generate a .gitissue.yml by auto-detecting a repo's stack, test runner, and size. Use to init, setup, or configure gitissue, or set up IDD. Don't use for editing an existing .gitissue.yml, creating issues (use /issue-creator), or plain git/npm init.

Research French mortgage rates → offline weekly HTML market report: bank averages, scenario matrix, leading indicators, sourced forecasts. No personal data. Don't use for a personal capacity calc (use capacite-emprunt-fr) or non-France loans.

Analyze French syndic quarterly charge-call PDFs (appels de fonds), persist extracted charges as a local KB, and generate one beautiful anomaly-focused HTML report. Don't use for AG convocations, tax notices, bank statements, or non-copropriété PDFs.

Generate French mortgage capacity per HCSF rules (35% DTI, 25-year cap) with live rates. Use when a buyer asks how much to borrow; outputs 3 scenarios (15/20/25 ans). Don't use for consumer credit, debt consolidation, non-France loans, tax advice.

Prepare French 2025 income-tax declaration filed in 2026: collect inputs/PDFs/profiles, fetch official rules, compute IR, render markdown. Don't use for tax optimization, filing/submission, non-France tax, or impots.gouv.fr login.

Ingest a French Assemblée Générale (AG) PDF and generate an interactive HTML report (Tailwind + Chart.js) with meeting info, résolutions, year-over-year budget, travaux progress, and a 5-point pre-vote briefing. Don't use for non-AG French docs (acte, bail),…

Create concise checklist cheatsheets from official tool docs. Use for docs URLs, setup guides, or updating existing cheatsheets. Don't use for long tutorials or API references.

Author standardized AI cheatsheets in the awesome-cheatsheets format

Publish or refresh a verified free-AI-credit offer from screenshot or text — extracts, web-verifies live status, normalizes to F5 schema, validates, diffs, commits on approval. Don't use for general scraping, unrelated YAML, or bulk imports.

Publish or refresh a verified free-AI-credit offer from screenshot or text — extracts, web-verifies live status, normalizes to F5 schema, validates, diffs, commits on approval. Don't use for general scraping, unrelated YAML, or bulk imports.

Evaluate the coding harness you are running inside (pi, opencode, claude-code) on its live setup and current model, via bench setup run. Measures it with and without its skills, MCP servers and plugins on --ab, and reports which of them the run actually…

Benchmark this harness's live configuration (skills, MCP servers, settings included) and get a scored report with improvement suggestions

Extract a design system from a screenshot (PNG/JPG/WEBP) or a live URL and produce a schema-compliant `design.v1.json` file plus a ready-to-use agent prompt for applying the design to any website/app. When run inside the sleek-ui repository, offers to add the…

Delegate approved coding tasks to Pi subprocesses with free opencode defaults, model setup, live progress, and metrics. Don't use for direct edits, CI, or non-Pi agents.

Analyze and tune a running llama.cpp server for local coding agents: propose config (ctx, prompt cache, MTP), benchmark before/after, report deltas. Use to optimize llama-server for Claude Code or Aider. Don't use for vLLM, ollama, or non-llama.cpp.

Run OpenCode in a disposable luongnv89/docker-dev container; never mounts SSH keys or GH tokens. Use to isolate OpenCode or dodge rate limits. Don't use for opencode.ai (opencode-runner), Herdr (herdr-agent-comms), or the project's app (run).