Productivity & Workflow Agent Skills for Claude Desktop

Converts Markdown paper drafts to LaTeX source, performs silent compilation with BibTeX, captures and auto-fixes formatting errors and…

Apply the Fable-derived 10-stage OBSERVE, OBSERVE, LISTEN, THINK, CONNECT, CONNECT, FEEL, ACCEPT, CREATE, GROW loop to consequential or…

Use when: (1) User says "总结经验", "复盘", "extract methodology", "what did we learn", "抽象智慧", or asks to reflect on a completed project, (2) A…

Intercept the response flow to offer the user a choice about response depth before Claude answers. Use the repository's canonical…

Reduce output and context tokens without losing technical accuracy.

Assists with job applications: evaluating job postings, tailoring CVs, writing cover letters, and preparing for interviews.

Toolcraft: use before code changes once generated app behavior or an approved spec is clear.

Use when working on Journal of Financial Intermediation (JFI) manuscripts to test whether the paper is centrally about banking and…

trailhead work cluster: the verbs that resolve tickets on the map and manage a ticket's lifecycle.

Dig undocumented institutional knowledge out of a company's record — Slack, email, docs, tickets, CRM, code, meeting notes — and return an…

Analyze a repository's portfolio trust-signal quality for 2026 hiring and write a recommendations report you can act on.

Capture a proven thread or workflow as a reusable Agent-Native skill and save it as a personal or organization resource.

Turn an evidenced Change intent into a dependency-valid task ledger, confirmed test seams, and resumable task contexts.

Stress-test one consequential product, architecture, recovery, or scope decision and preserve the accepted result when it must outlive the…

Optimize TwinMind transcription accuracy and speed with Ear-3 model

Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active…

Activate maximum performance mode with parallel agent orchestration for high-throughput task completion

Use when interpreting the Strategic Management Journal (SMJ) review process and a decision letter, and planning the revision strategy.

Use when finalizing a USENIX Security Symposium submission — the per-cycle HotCRP site, the registration deadline a week before the paper…

Use when driving the OpenAI Codex CLI (`codex`) directly from Bash, scripts, or agents — headless runs with codex exec, resuming sessions…

Use when a change is expected to span multiple files or modules, or when deciding whether to hand work to subagents, run them in parallel…