Use AIO Sandbox for isolated browser workflows.
原文语言:英语
菜单
这个仓库中的 skills
SkillsMP 已收集 Abd0r/porcupineai 中的 73 个 Skill。打开任一 Skill 可查看来源和详情。
Abd0r/porcupineai已展示 33 / 73 个已收集 Skill。
Use AIO Sandbox for isolated browser workflows.
原文语言:英语
Safe cross-platform screen observation and UI interaction on macOS, Linux, and Windows.
原文语言:英语
Run a data-quality gate before drawing conclusions — inspect distributions, check for missing/duplicate/sensitive values, validate schema, and aggregate honestly.
原文语言:英语
Parse, validate, transform, extract from, and safely mutate JSON, CSV, and YAML using node -e and jq when available.
原文语言:英语
Reproduce bugs, isolate cause, fix, verify.
原文语言:英语
Reproduce, isolate, root-cause, and fix bugs with evidence instead of guessing. Use for any test failure, stack trace, regression, or unexpected behavior before proposing a fix.
原文语言:英语
Orient in an unfamiliar codebase — map the repo, locate symbol definitions vs usages, trace call paths, and understand build/test setup before editing.
原文语言:英语
Write and maintain README, CHANGELOG, guides, and code comments that stay accurate and current — verified against source, never imagined. Use when creating or editing any user-facing or developer-facing docs.
原文语言:英语
Safely and efficiently read, search, and edit files with Porcupine's filesystem tools, avoiding destructive mistakes.
原文语言:英语
Recover safely from broken Porcupine customizations.
原文语言:英语
Delegate focused, self-contained work to an isolated sub-agent with its own context, budget, and tools.
原文语言:英语
Decompose a large goal into targeted parallel sub-agent missions and integrate verified results — the harness carries the orchestration, the user states the goal.
原文语言:英语
The universal problem-solving loop for ANY task — understand, recon, decompose, plan, execute one step at a time, verify each, reflect. The umbrella that routes to domain skills. Use as the default operating loop when a task is not trivial.
原文语言:英语
Debug systematically instead of guess-and-patching — reproduce first, isolate one variable, read the actual error at file:line, and verify the fix with a real command. Use for any bug, test failure, or unexpected behavior.
原文语言:英语
Isolate risky work before it can hurt you — run untrusted code in a container, put experiments in a disposable clone, and use Porcupine's mode settings and Escape-cancel to contain yourself. Use whenever work could be destructive, untrusted, or hard to…
原文语言:英语
Write secure-by-default code — keep secrets out of code and logs, validate all input against an allow-list, and neutralize path traversal and command injection. Use when writing or reviewing any code that touches input, files, or the shell.
原文语言:英语
Compare methods fairly - baselines, held-out data, leakage prevention, and honest significance.
原文语言:英语
Analyze data without fooling yourself - hygiene, distributions, statistics, and honest plots.
原文语言:英语
Evidence-graded literature search, dedupe, and synthesis with citation trails.
原文语言:英语
Run experiments anyone can reproduce - seeds, pinned env, versioned data, full-run verification.
原文语言:英语
Write papers where every claim maps to evidence and every citation resolves.
原文语言:英语
Write reliable shell commands — correct quoting, pipes, exit-code checks, and knowing when to use a purpose-built tool instead of bash.
原文语言:英语
LOC and language breakdown with pygount or cloc.
原文语言:英语
Safe local git plus pointer to GitHub skill stack.
原文语言:英语
Set up GitHub auth via gh CLI, HTTPS token, or SSH.
原文语言:英语
Review PR diffs and leave gh review comments.
原文语言:英语
Explore a GitHub repo structure, README, and layout.
原文语言:英语
List, create, triage, label, close GitHub issues with gh.
原文语言:英语
Resolve PR merge conflicts in isolated worktrees.
原文语言:英语
PR lifecycle: branch, commit, push, open, CI, merge.
原文语言:英语
Profile a GitHub user from public repos and README.
原文语言:英语
Clone, fork, create repos; remotes, releases, settings.
原文语言:英语
Verify which issues a PR solves via gh, not web search.
原文语言:英语