Claude Skills by thedixitjain

Configure GSD workflow toggles and model profile

Create PR, run review, and prepare for merge after verification passes

Package sketch design findings into a persistent project skill for future build conversations

Package spike findings into a persistent project skill for future build conversations

Spike an idea through experiential exploration, or propose what to spike next (frontier mode)

Manage persistent context threads for cross-session work

Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.

Validate built features through conversational UAT

Upgrade gstack to the latest version.

Router for the gstack skill suite. (gstack)

Full safety mode: destructive command warnings + directory-scoped edits. (gstack)

Constrain LLM output with grammars; guarantee valid JSON.

Scrape the Hacker News front page (titles, points, comment counts).

Clone the later half of the current conversation, discarding earlier context to reduce token usage while preserving recent work.

Automate time tracking, project management, and invoicing workflows in Harvest -- log hours, manage projects, clients, and tasks through natural language commands.

Command-line access to search, scraping, and structured web data.

Expert Haskell engineer specializing in advanced type systems, pure

One sentence - what this skill does and when to invoke it

分析一段时间内健康数据的趋势和模式。关联药物、症状、生命体征、化验结果和其他健康指标的变化。识别令人担忧的趋势、改善情况，并提供数据驱动的洞察。当用户询问健康趋势、模式、随时间的变化或\"我的健康状况有什么变化？\"时使用。支持多维度分析（体重/BMI、症状、药物依从性、化验结果、情绪睡眠），相关性分析，变化检测，以及交互式HTML可视化报告（ECharts图表）。

HeartMuLa: Suno-like song generation from lyrics + tags.

> One-screen quick reference for the Origin plugin. Lists the daily verbs, the daily flow, where data lives, and how to view it without a GUI. Use when the user says \"help\", \"what can I do\", \"list origin commands\", \"how do I use origin\", or invokes `/help`.

Analyzes what is done and the users query and offers advice on what to do next. Use if user says what should I do next or what do I do now or I'm stuck or I don't know what to do

'Execute Hex secondary workflow: Core Workflow B. Use when implementing secondary use case, or complementing primary workflow. Trigger with phrases like \"hex secondary workflow\", \"secondary task with hex\". '

Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.

Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.

Apple HIG guidance for navigation-related components including search fields, page controls, and path controls.

Apple HIG guidance for system experience components: widgets, live activities, notifications, complications, home screen quick actions, top shelf, watch faces, app clips, and app shortcuts.

Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.

Create or update a shared Apple design context document that other HIG skills use to tailor guidance.

Check for .claude/apple-design-context.md before asking questions. Use existing context and only ask for information not already covered.

Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.

Problem-solving strategies for hilbert spaces in functional analysis

Himalaya CLI: IMAP/SMTP email from terminal.

Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.

Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.

Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.

Periodically self-assess output quality to catch degradation before the judge does.

Use terminal_rg / terminal_find when you need raw filesystem search outside the project tree — system configs, /var/log, /etc, archive contents — or when files-tools.search_files is too project-scoped. Teaches the rg vs find vs terminal_exec(\"ls/du/tree\") split, common rg flag combos for code/logs/configs, find predicates for mtime/size/type queries, and the rule that for tree views or single-file stat info you should just use terminal_exec instead of inventing a tool. Read before reaching ...

Read when a terminal-tools call returned something surprising — empty stdout despite no error, exit_code is null, output_handle came back expired, \"too many jobs\" / \"session busy\" / \"too many PTYs\", warning was set unexpectedly, semantic_status disagrees with exit_code. Diagnostic recipes only — load on demand. Don't preload; the foundational skill covers the happy path.

Use when working with Harvard Law Review (HLR) student editors after an offer — the intensive substantive and technical edit, the cite-check / source-pull, and author responsiveness. Manages the relationship and process; it does not run the pre-offer placement (hlr-placement-strategy) or the author-side cite apparatus build (hlr-footnotes-and-cite-check).

Use when running the final pre-submission preflight for the Harvard Law Review (HLR) via HLR's own electronic submission system — manuscript readiness, anonymization, length limits, Bluebook 22nd-edition footnotes, expedite setup, and season timing. Final upload checks; it does not plan the placement strategy (hlr-placement-strategy) or draft content.

Practical home and homelab network planning for gateways, switches, access points, IP ranges, DHCP reservations, DNS, cabling, and common beginner mistakes.

Select hook scope (plugin, project, global) by audience. Use when authoring a hook.

This skill should be used when the user asks to create a hookify rule, write a hook rule, configure hookify, add a hookify rule, or needs guidance on hookify rule syntax and patterns.

'Execute Hootsuite secondary workflow: Core Workflow B. Use when implementing secondary use case, or complementing primary workflow. Trigger with phrases like \"hootsuite secondary workflow\", \"secondary task with hootsuite\". '

Track long-horizon objectives across multiple sessions with milestone checkpoints, progress persistence, and drift detection

Use when deciding where HPCA material belongs across the four destinations the venue offers — the 11-page body, the anonymized artifact mirror, the staging shelf for the rebuttal/revision window, and the post-acceptance public release — while keeping anonymity intact and every reference author-complete.

Use when running the final pre-submission preflight for a Human Resource Management (Wiley \"HRM\") manuscript via Wiley ScholarOne — double-blind anonymization, the title-page split, APA style, the data-availability statement, ORCID, and the dual-contribution check the EIC screens on. Final checks; it does not draft content.

Use when exhibits are the bottleneck for a Human Resource Management (Wiley \"HRM\") manuscript — the descriptives/correlation table, the model build-up, interaction and simple-slope plots, the theoretical-model figure, and (for qualitative work) the data-structure figure. Builds reader-ready exhibits; it does not run the analysis (hrm-data-analysis).

Use when the theoretical argument and hypotheses are the bottleneck for a Human Resource Management (Wiley \"HRM\") manuscript — building an HRM/OB mechanism (AMO, HR-system strength, signaling, social exchange) and deriving testable predictions a priori. Builds the theory; it does not run the analysis (hrm-data-analysis).