n-n-code/n-n-code-skills

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Project overlay for checked-in or submodule-managed third-party source, provenance, local patches, and the app-owned integration seam. Not for package-manager dependency changes without vendored source.

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Prompt engineering workflow for designing, rewriting, debugging, evaluating, and optimizing LLM prompts, system prompts, developer prompts, few-shot examples, structured-output instructions, tool-use prompts, and prompt eval cases. Use when prompt behavior, reliability, safety, cost, latency, or model fit is the main…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Adversarial review workflow for pressure-testing an existing candidate plan, diagnosis, design, argument, proposal, or recommendation. Use when the user asks to challenge its assumptions, run a premortem, play devil's advocate, red-team a non-security decision, or identify what would change the conclusion. Do not use…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Companion overlay used only with security when explicitly security-focused review, threat model, or implementation centers on authentication, sessions, recovery, MFA or passkey lifecycle, federation or account linking, identity-provider or recovery callbacks, invitations, or tenant authorization. Never use alone or…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Evidence-grounded threat modeling, vulnerability review, and secure implementation. Use for explicit security audits or primary risks involving authorization, untrusted input, external requests, parsers/uploads, secrets, sensitive data, isolation, or release integrity. Not for routine implementation or non-security…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Use when adding, extending, or repairing a repo-owned Playwright test harness across Node Playwright Test, Playwright Pytest, or .NET/Java test frameworks. Also use when explicitly persisting @playwright/cli developer tooling, or adding or regenerating Playwright Test Agent definitions for a compatible Node Playwright…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Draft, synthesize, rewrite, tighten, or split rough tickets, conversations, user stories, feature definitions, and acceptance criteria into testable story cards or split story sets, or audit existing story inputs with a separate readiness report. Use for ambiguous story-level product behavior or when supplied…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Create a constraint-aware implementation plan from a Ready Story Card and sufficiently evidenced Repo Context. Use when the requested artifact is the plan itself; use story-to-plan-orchestrator for multi-stage preparation, packet completion, resumption, or validation. Avoid story drafting, repo scouting, and direct…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Inspect a repository for story-specific implementation evidence, applicable decisions, validation prior art, and bounded planning-critical external primary sources, then produce compact Repo Context. Use for pre-implementation file discovery and greenfield path grounding; use tester-mindset for test strategy and avoid…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Coordinate multi-stage story-to-plan preparation across story-clarifier, story-repo-scout, and story-implementation-planner. Use for complete implementation-ready handoffs, two or more missing stages, split-slice selection, partial-packet resumption, consistency validation, or stale-stage recovery before coding; use a…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Testing mindset skill for context-driven test strategy, exploratory testing, validation design, acceptance criteria, oracles, weak-test detection, edge cases, heuristics, checklists, and evidence review for code, products, plans, or claims. Use when the user asks what to test, how to test, whether evidence is enough…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Decision-framing workflow for turning an ambiguous problem or open choice into a recommendation, experiment, or concrete next move. Use when the user wants to explore a vague idea, compare plausible approaches, understand system trade-offs, or decide what to do. Do not use for sustained brainstorming, when the…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Canonical overlay for graphical UI or frontend redesign, polish-heavy implementation, and deep UX review; use ui-guidance for routine changes. Compose with matching implementation guidance when visual direction, accessibility, interaction, responsive behavior, forms, navigation, or data presentation need stronger…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Baseline overlay for routine graphical UI and frontend changes that preserve the existing design language; use ui-design-guidance for redesign, polish-heavy implementation, or deep UX review. Compose with matching implementation guidance. Not for terminal UIs or pure plotting.

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Use for DeepSeek Harness (dsh) installation, operation, configuration, automation, extension, troubleshooting, or source-checkout maintenance across profiles, patches, plugins, Web/headless/SDK/ACP surfaces, and Cordis extension points. Not for generic DeepSeek API integration or reusable SKILL.md authoring; use only…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Evaluate and improve repeated agentic software-development workflows using development traces, diffs, review feedback, incidents, and eval results. Use for recurring delivery failures, handoff or verification problems, and evidence-backed changes to how coding agents work. Not for delivering one change, a prompt-only…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Coordinate end-to-end or resumed multi-stage software delivery from intent through implementation, verification, review, release, and maintenance. Use when an agent must carry a change across lifecycle stages, recover interrupted delivery, or assess that delivery workflow. Not for a single planning, coding, testing…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Use the chrome-devtools-axi CLI to operate Chrome or investigate live page behavior. Default for ad hoc browsing, forms, rendered extraction, screenshots, DOM/CSS, console/network failures, responsive behavior, and performance or memory questions. Excludes static-only fetching, direct-MCP-only requests, explicitly…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Author, revise, or review visual DESIGN.md/design.md files, or explain an interface's visual rules without edits. Use source files, images, tokens, or a brief to document web, mobile, or desktop design decisions and reusable UI patterns. Excludes software architecture, UI implementation, and repository agent…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Understand, review, design, implement, and troubleshoot Jekyll pages and sites using Liquid, front matter, layouts, includes, collections, themes, and assets. Use for conceptual Jekyll questions, tracing page rendering, creating or redesigning Jekyll pages, focused theme overrides, static HTML conversion to Jekyll, or…

n-n-code/n-n-code-skills

Skill Claude CodeCodex

Run and interpret Google Lighthouse audits for performance, accessibility, best practices, and SEO; compare reports, diagnose and verify improvements, audit authenticated user flows, and configure Lighthouse CI budgets and regression gates. Not for general browser debugging, Playwright test or harness work, backend…