Agent skills for Claude Desktop

Groundledger paid-media skill with SAFE defaults (Snapshot → Advise → Fence → Experiment).

Calculate and model paid-media CPA, CPL, CPC, CPM, ROAS, MER, break-even targets, contribution margin, LTV:CAC, impression-share…

Create a professional paid-advertising strategy covering objectives, economics, platform selection, campaign architecture, audiences…

Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it.

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries.

Apply when reviewing or shaping code that's hard to trace.

Use before review when the user asks to strip, remove, or clean up comments in code.

Apply after completing a task, before declaring done.

Apply when concurrent actors might write to the same file, branch, key, or state object.

Cut AI tells from any writing. Must always apply.

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds.

AI-assisted pair programming with multiple modes (driver/navigator/switch), real-time verification, quality monitoring, and comprehensive…

Orchestrates multi-agent pair programming workflows where Claude and OpenAI Codex cross-review requirements and code implementations.

Drive interactive terminal programs your exec-style shell tool cannot: REPLs, TUIs, pagers, ssh/sudo password prompts, docker exec -it…

Write an implementation plan that a human executes step by step: independently verifiable steps, exact verification commands, changes…

Transforms uploaded photos into elegant 2:3 travel palette postcards combining source photography, selective watercolor studies, archival…

Transforms competitor research, pricing signals, and product walkthroughs into actionable product decision briefs and PRD inputs.

Audits and optimizes Claude Code skills and SKILL.md configurations for triggers, context budgets, and quality standards.

Generate publication-quality figures and tables from experiment results.

Facilitates structured, evidence-based academic paper analysis and interactive deep reading within your research workflow.

Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation.