测试与安全技能

Semantic audit of the IDD instruction corpus for leaked session context, cross-file contradictions, fresh-memory completability gaps, automation blockers, and restatement-discipline drift. Use on request to audit .github/instructions, the issue-authoring skill bundle, and the installed agent entry files (CLAUDE.md, AGENTS.md, GEMINI.md, .github/copilot-instructions.md). Read-only — never edits files or mutates issues.

中文简介正在准备中。当前显示原文说明。

Create or update project test-case assets and test reports. Use when Codex is asked to generate test cases in Excel, produce a Word/DOCX test report, summarize automated test execution, turn repository tests into a formal testing artifact, or沉淀/复用 a project testing documentation workflow.

中文简介正在准备中。当前显示原文说明。

Pressure-test startup ideas against real user pain, current behavior, competitors, first-customer access, MVP scope, founder-market fit, and a two-week launch test. Produces a direct strong, weak, or pivot verdict.

中文简介正在准备中。当前显示原文说明。

Audit and optimize a skill system with evidence. Use for skill architecture, token or context waste, role and prompt boundaries, routing hits or misfires, plugin packaging, registry/docs/source drift, duplicate workflows, or deciding whether a reusable change belongs in a skill. Runs deterministic checks first and applies only authorized, minimal fixes.

中文简介正在准备中。当前显示原文说明。

Use for deterministic terminal or CI browser automation, repeatable regressions, traces, snapshots, screenshots, and unattended playwright-cli batches. Route interactive or signed-in Chrome work through browser-automation-router first.

中文简介正在准备中。当前显示原文说明。

GStack engineering-manager plan review for architecture, data flow, APIs, migrations, edge cases, tests, performance, release risk, and implementation boundaries.

中文简介正在准备中。当前显示原文说明。

GStack QA method for web/UI behavior verification and narrow fix loops when the user explicitly allows QA to repair issues.

中文简介正在准备中。当前显示原文说明。

GStack report-only QA method for checking web or UI behavior, documenting blockers, and preserving evidence without modifying code.

中文简介正在准备中。当前显示原文说明。

GStack CSO method for broad infrastructure-first security posture review, threat areas, severity calibration, and safe remediation scope.

中文简介正在准备中。当前显示原文说明。

GStack review method for pre-landing code, diff, PR, or implementation review focused on bugs, regressions, missing tests, and release risks.

中文简介正在准备中。当前显示原文说明。

Run user-authorized black-box web security tests and evidence-based reports. Use for 黑盒安全测试、渗透测试、数据泄露、未授权访问、公开 JS/API、登录爆破防护、CORS 或安全响应头检查。

中文简介正在准备中。当前显示原文说明。

GStack developer-experience plan review for setup, local commands, docs, test loops, onboarding friction, and maintainability before implementation.

中文简介正在准备中。当前显示原文说明。

GStack investigation method for bugs, incidents, failing tests, regressions, and unclear behavior where evidence and root cause should precede fixes.

中文简介正在准备中。当前显示原文说明。

Codex adapter for Garry Tan's full gstack methodology across CEO/product pressure, CTO architecture, design, engineering, QA, security, shipping, documentation, and retrospectives. Use when the 总控/CEO or 架构/CTO role needs gstack method routing, implementation-plan hardening, or the user says gstack should help a role.

中文简介正在准备中。当前显示原文说明。

Systematic testing methodology for exhaustive branch coverage, edge case identification, and production bug prevention. Use when PR review reveals incomplete test coverage, when tests pass but users report bugs, when code changes break existing features, when verifying all branches and edge cases before merge, when analyzing "it works on my machine" issues, when planning test strategy for new features, or when debugging flaky tests and race conditions.

中文简介正在准备中。当前显示原文说明。

Produces a deep, honest peer-review of how someone uses Claude Code by statistically analyzing their local session data (~/.claude/usage-data/ and ~/.claude/projects/). Trigger whenever the user asks to review, analyze, audit, or critique their own Claude Code usage, workflow, habits, or skill level — including phrases like "analyze my cc usage", "review my cc sessions", "peer review my cc workflow", "deeper than /insights", or any ask for an honest audit of their AI workflow. Also covers portfolio/hiring-manager framings (e.g. "portfolio for Anthropic/OpenAI/xAI"), but ALWAYS ask the user in Step 0 which version to build (self / hr / both) before running — never silently produce an HR report, because that version goes to outsiders and needs explicit privacy setup. The HTML report is laid out ledger-first for SELF (opening band, output/team/leak/trend ledgers, then peer review, 9-dim scoring, try-this-week, case study, claim-indexed evidence). The HR variant is a recruiter version v1: identity card, earned badges (threshold-based, earned-only), allowlist-filtered output ledger, one case study, and a methodology & scope disclosure — no scores, no peer-review memo, no charts.

中文简介正在准备中。当前显示原文说明。

Create, restyle, or rebuild Chinese academic PowerPoint presentations from papers, theses, reports, figures, notes, templates, screenshots, or visual mockups. Use for presentation planning, Template DNA extraction, slide mockups, template-based editable PPTX generation, editable reconstruction, rendering, and final QA.

中文简介正在准备中。当前显示原文说明。

Builds a talk as a beatdeck - a fixed 1920x1080 React stage where one click is one beat, with authored motion, presenter view, overview, and an offline self-contained build. Covers turning source material (PPTX, Keynote/PDF export, Markdown, notes) into a content audit and a scene/beat map, choosing or applying a theme, writing scene layers, automatic beats, and verifying every beat with npm run verify. Use whenever the task is creating, porting, restyling, rehearsing or fixing a presentation, talk, keynote, slide deck or conference session that should feel like a live system rather than slides, or whenever the repo contains src/beatdeck/.

中文简介正在准备中。当前显示原文说明。

Enforce traceability from natural-language intent to machine predicates, final observables, evidence, and owner-readable acceptance. Use when conducting any audit, review, QA pass, parity or compliance check, security assessment, code or architecture review, visual or behavioral comparison, data validation, system verification, completion gate, or claim that an implementation satisfies a human request.

中文简介正在准备中。当前显示原文说明。

Use when a developer needs a ChatGPT Apps submission import file from an MCP server. Inspect the implementation, generate chatgpt-app-submission.json with app info, tool-hint justifications, positive and negative test cases, then report review findings and outputSchema warnings.

中文简介正在准备中。当前显示原文说明。

Cut a versioned release: smoke-test the package, bump the version, tag, publish to PyPI/npm/Docker, and verify the published artifact. Use when asked to release or ship a version.

中文简介正在准备中。当前显示原文说明。

When the user wants to audit or diagnose SEO issues — "technical SEO," "why am I not ranking," "meta tags review," "my traffic dropped," "Google update hit me," "core web vitals," "crawl errors," "indexing issues," or even a vague "my SEO is bad." For pages at scale, see programmatic-seo. For structured data, see schema-markup. For AI search, see ai-seo.

中文简介正在准备中。当前显示原文说明。

You are a security engineer. Auto-detect package managers, scan for vulnerabilities and leaked secrets, fix what's fixable, report the rest. Covers the dependency tree and tracked files — reviewing a pending diff's security belongs to a platform-native security-review skill when present.

中文简介正在准备中。当前显示原文说明。

Detect and run every test layer (unit, integration, E2E), add tests where coverage is below threshold, and loop until green. Use when asked to test or raise coverage.

中文简介正在准备中。当前显示原文说明。