Explains codebases and feature flows in accessible language with grounded analogies. Use for simple walkthroughs or mental models; skip bug triage, code review, and code changes.
jpcaparas/skills
SkillsMP has collected 76 skills from jpcaparas/skills. Open a skill to review its source and details.
- Latest recorded source activity
- SkillsMP catalog refreshed
- skills collected
- 76
- GitHub stars
- 44
- GitHub forks
- 3
Skills in this repository
Showing 40 of 76 collected skills.
Parodies text as LinkedIn-speak or reverses corporate-influencer fluff into blunt English. Use for LinkedIn-speak and corporate-cringe rewrites; skip real translation and serious editing.
Explains code flirtatiously without losing accuracy. Use for flirty or sultry code explanations; skip ordinary explanations, code edits, and explicit sexual content.
Guide maintainable code with clear names, decomposition, safe defaults, side-effect guardrails, compatibility, comments, and quality gates. Use for production code, refactors, reviews, plans, CI, scripts, config, tests, or technical debt. Skip disposable work.
Guide maintainable tests as behavior documentation with isolated side effects, compatibility coverage, and reliable assertions. Use for tests, fixtures, mocks, regressions, reviews, and testability changes. Skip disposable work.
Guide mockable, test-double-friendly code. Use for code or tests involving dependencies, I/O, time, randomness, configuration, or external services. Skip non-code writing and disposable prototypes.
Turn a convoluted engineering, scientific, or general process into one clear Mermaid diagram and export matching Markdown and PNG files. Trigger on /to-diagram, process diagram, workflow visualization, concept map, or explain this flow visually. Do not use…
Debates when explicitly invoked.
Run ambitious one-shot websites, web apps, games, simulations, clones, motion pieces, or benchmarks through fresh isolated subagents. Use for one-shot web artifacts, catalogue ideas, or parallel model/harness variants.
Draft local Azure DevOps work item packets from loose context, defaulting to Scrum PBI unless Bug, Feature, User Story, Task, Issue, or Epic is specified. Inspect repo context when present. Do NOT use for live REST/CLI creation, migration, wiki, or status…
Draft, rewrite, review, humanise, or adapt prose without losing facts, voice, or uncertainty. Use for technical docs, wikis, product, editorial, marketing, personal, or AI-like writing. Skip code-only tasks.
Turn supplied websites, apps, images, media, documents, code, or mixed references into a self-contained replication prompt for a fresh session. Default to a website/web app unless another target is named. Skip implementation, rendering, and summaries.
Coordinate bounded Codex subagents only when the user requests delegation, parallel agents, per-point reviews, multi-agent plans, or custom agents. Skip other harnesses, trivial work, and requests without delegation authority.
Decompose existing sprite sheets or illustration contact sheets on flat or gently varying backgrounds into cropped transparent PNGs with reviewed grouping, bounds manifest, and validation. Skip generation, atlas packing, and hidden-pixel reconstruction.
Use compact, low-noise shell commands for repo exploration, git status/diff/log, tests, containers, and file search. Trigger on token savings, terse shell workflow, rg, tree, pytest, npm test, cargo test, go test, or docker ps. Do NOT use when full output is…
Run /scaffold-hooks to audit, create, or refresh shared repository hooks for Claude Code, Codex, GitHub Copilot, Devin CLI, and OpenCode, together or individually. Skip Git hooks and Husky.
Rewrite or audit ASD-STE100 procedures, descriptions, and safety instructions while preserving technical meaning and exact literals.
Bootstrap or refresh root AGENTS.md and CLAUDE.md.
Give ADHD-friendly, action-first help.
Run a bounded adversarial sweep of an existing test suite. Use to harden a suite or subsystem against malformed inputs, boundaries, invalid state, races, dependency/resource failures, weak or redundant tests, flakes, and missing durable regressions. Skip…
Audify readable URLs, Markdown, HTML, DOCX, or raw text into cleaned Gemini TTS MP3 narration. Trigger on /audify, read aloud, MP3 narration, or text-to-speech resource requests. Do NOT use for music, live voice chat, or non-narration media.
Guide resilient production-app code involving jobs, queues, webhooks, persistence, APIs, retries, concurrency, observability, idempotency, backpressure, degradation, or stuck work. Skip non-code writing, throwaway scripts, and visual-only mockups.
Use for safe chezmoi setup and migration, daily dotfile sync, templates, secrets, scripts, drift/recovery, or official-doc research.
Claude Code automatic advisor for security, reviews, high-risk design, substantial multi-step plans, complex refactors, recurring failures, and risky completion checks. Skip trivial work, ordinary planning, other harnesses, or sessions without an advisor tool.
Name unfamiliar UI components from descriptions, screenshots, live pages, or DOM/code clues; return ranked aliases, prompt-ready wording, and authoritative links without using namethatui.com. Skip implementation of already-named components.
Create .xlsx travel workbooks with itinerary, preparation, or shopping sheets for trip, holiday, or conference planning. Skip prose itineraries, recommendation chat, and calendar-only scheduling.
Prefer ripgrep (`rg`) for text search, recursive codebase search, filename discovery with `rg --files`, and machine-readable search output. Trigger on search, grep, ripgrep, rg, find files, or look for pattern. Do NOT use for full-file reads or JSON queries…
Create, harden, and curate production-grade installable skills and skill libraries. Use for API/CLI/reference skills, invocation design, progressive disclosure, evals, placement, promotion, renames, deprecation, or catalog/router consistency. Skip trivial…
Explain this fixture repository's established installable-skill layout. Use only for repository-layout orientation.
Diagnose a failed release from logs, status output, and repository state.
Validate and publish an authorized release after resolving its repository and environment.
TODO: describe when this package-checking skill should trigger
Review proposed code changes for correctness and maintainability.
Draft changelog entries from merged changes and release metadata.
Validate and publish an authorized release after release notes are approved.
Orient release operators to the correct installable skill.
Write changelog copy from merged pull requests and issue metadata.
Draft release notes from merged changes and issue metadata.
Publish a release after its notes and artifacts are approved.
Orient operators to published release skills.