All authors
Claude Skills by srinitude
github.com/srinitude27 skills3 installs40 views
- ReferencesOwner: `dedupe`. Load when the `url` or `skill` adapter is selected. Backlink: `SKILL.md` PD-004.Votes: 0GitHub stars: 2
- Always Current DatetimeUse when replying. Refresh current date and time.Votes: 0GitHub stars: 2
- By DesignUse when any request arrives, and especially when it touches a screen, component, flow, brand, layout, typography, colour, motion, copy, icon, form, table, dashboard, navigation, onboarding, pricing, checkout, notification, accessibility, design system, or brief. Use when choosing between directions, when shaping something unbuilt, when reviewing, critiquing, or shipping work, and during ordinary design conversation. A request that holds no design surface costs one command and nothing else. K...Votes: 0GitHub stars: 2
- DedupeUse when deduplicating bounded collections.Votes: 0GitHub stars: 2
- ReferencesOwner: `dedupe`. Load when the `url` or `skill` adapter is selected. Backlink: `SKILL.md` PD-004.Votes: 0GitHub stars: 2
- Design Like Im 5Use when creating, reviewing, or revising a digital product, full flow, design system, or screen set. It keeps the user-facing core simple across parts, states, access needs, inputs, and screen sizes. Use it for product design, UX, UI, interaction, motion, or design review work.Votes: 0GitHub stars: 2
- Dtcg TokensUse when any multimodal source must become source-specific DTCG tokens with a vision-reviewed standalone proof artifact.Votes: 0GitHub stars: 2
- Figma Code Connect Design SystemUse when a FigJam board, product requirements document, reference image, Figma design file, published library, or codebase must become or update an evidence-traceable Figma design system, DTCG token hierarchy, platform-specific UI templates, production components, and verified Code Connect mappings. Covers create, update, plan, run, validate, resume, and source-refresh work for one bounded UI or a larger product system across web, mobile, desktop, embedded, and other platforms.Votes: 0GitHub stars: 2
- Goal PromptUse when packaging source input for a standing goal.Votes: 0GitHub stars: 2
- Human LanguageUse when writing or editing any agent-written text: replies, copy, tool-call prose, and handoffs. Also use when asked to remove AI slop, write plain or natural prose for a grade 6 reader, keep the author's meaning, or check facts, voice, flow, and exact data before release.Votes: 0GitHub stars: 2
- Logic AuditUse when finding contradictions or reasoning gaps.Votes: 0GitHub stars: 2
- Meaning Preserving RewriteUse when rewriting rules without meaning loss.Votes: 0GitHub stars: 2
- Mobile First Website DesignUse when designing landing pages and marketing websites.Votes: 0GitHub stars: 2
- Only One InterpretationUse when disambiguating prompts, not improving or running.Votes: 0GitHub stars: 2
- Outcome Bounded WorkUse when instructions mix outcomes with recipes.Votes: 0GitHub stars: 2
- Prompt EnhancerUse when the user asks to enhance, improve, refine, rewrite, strengthen, or validate a prompt, or says "make this prompt better". Returns a clearer, more specific, better structured version of the prompt without executing it, picking validation checks from the prompt''s own context. Contexts include coding, research, writing, image or video generation, agentic tasks, data work, and system prompts. Flags ambiguity, contradictions, missing constraints, missing success criteria, format gaps, and...Votes: 0GitHub stars: 2
- ReifyUse when a vague idea, stray thought, remembered fragment, or uncertain direction needs to become a concrete outcome, tested design, decision record, artifact, or executable handoff.Votes: 0GitHub stars: 2
- Rich And Native MarkdownUse when supplied text must become clear Markdown that keeps its meaning: Markdown rewrites, rich document structure, and linked file sets that need short files, plain language, and sound reading paths.Votes: 0GitHub stars: 2
- Simplify SkillUse when simplifying a skill without losing behavior.Votes: 0GitHub stars: 2
- Skill FactoryUse when a workflow or capability must become a new agent skill, when an existing skill must be updated or standardized without losing its purpose, when a user-level or project-level variant is needed, or when a skill needs validation, evaluation, scaffolding, scripts, tests, or a Mise task graph.Votes: 0GitHub stars: 2
- ExamplesThis example covers the scope boundary before implementing a line-budget capability.Votes: 0GitHub stars: 2
- Starting PointUse when a request prescribes a method, tool, metric, or artifact that may not reach the result the user described, or when doing the request as written would leave that result unproved: "A/B test the signup button color" for a conversion problem, "add a cache" for a slow page, "the focused tests passed, announce the release". Also use when a stated constraint contradicts itself, when an unknown fact would have to be invented to finish, or when an external or irreversible step needs an author...Votes: 0GitHub stars: 2
- TimeboxUse when work must finish within a stated time limit.Votes: 0GitHub stars: 2
- Tool Call Configuration ForUse when one exact callable tool and a user-authored behavior configuration must become a tool-specific Agent Skill, or when that behavior must be integrated into one exact existing Agent Skill. Supports established or owned MCP, native, and custom tool contracts; stops on ambiguous identity, behavior, authority, source, or update target.Votes: 0GitHub stars: 2
- Visual Design System ExtractorUse when reference images, screenshots, moodboards, style frames, brand boards, cinematic stills, product interface shots, or a live site URL must become a production design system, design tokens, art direction, motion rules, or a YAML style specification. Covers reverse engineering visual references into a deterministic YAML contract with graded confidence, evidence boundaries, and typefaces drawn from the live Google Fonts catalog and ranked as rarely used. Not for generating images or for ...Votes: 0GitHub stars: 2
- Would Agents ActuallyUse when a claim depends on an agent taking a real action.Votes: 0GitHub stars: 2
- Would Humans ActuallyUse when a claim depends on people taking a real action.Votes: 0GitHub stars: 2