debug
25Skill Claude CodeCodex
A structured workflow for investigating bugs, failed tests, and production problems by collecting errors, examining logs, and connecting patterns across systems.
156 2d ago A 55 tokens
deep-review
26Skill Claude CodeCodex
A review workflow for staged changes, meaning code prepared to be included in the next commit. It checks security, performance, and coding style in parallel, then ranks the findings.
156 2d ago A 36 tokens
Skill Claude CodeCodex
A set of guidelines for creating polished front-end interfaces, including choices for fonts, colors, motion, and backgrounds.
156 2d ago A 48 tokens
load-plan
28Skill Claude CodeCodex
A workspace overview that shows which rules and skills are loaded, how large they are, and what phrases activate them.
156 2d ago A 69 tokens
map
29Skill Claude CodeCodex
A codebase map listing classes, functions, interfaces, and types with their exact file and line locations.
156 2d ago A 47 tokens
marketing
30Skill Claude CodeCodex
A marketing-planning workflow covering audience research, go-to-market planning, A/B test design, success measures, and competitor positioning.
156 2d ago A 64 tokens
perf
31Skill Claude CodeCodex
A performance-analysis workflow for measuring a starting point, finding slow parts, improving the highest-impact area, and checking the result.
156 2d ago A 53 tokens
pm
32Skill Claude CodeCodex
A project-management workflow for planning work in short development cycles, prioritising issues, reporting progress, assessing risks, and reviewing completed cycles.
156 2d ago A 80 tokens
prime
33Skill Claude CodeCodex
A cold-start workflow that scans a codebase and reads its README file to build an initial understanding of an unfamiliar project.
156 2d ago A 40 tokens
Skill Claude CodeCodex
A research workflow for comparing Claude Code practices from GitHub repositories, official documentation, and blog posts with the current workspace.
156 2d ago A 43 tokens
research
35Skill Claude CodeCodex
A general research workflow for defining questions, collecting sources, comparing competitors, organizing literature, combining findings, and producing a structured report.
156 2d ago A 71 tokens
retro
36Skill Claude CodeCodex
A session-review workflow that extracts key decisions, completed work, and suggestions for improvement from a conversation.
156 2d ago A 41 tokens
Skill Claude CodeCodex
A requirements-interview workflow for large software features. It asks detailed questions about technology, interface design, risks, and trade-offs before producing a specification.
156 2d ago A 80 tokens
writing
38Skill Claude CodeCodex
A writing workflow for analyzing an audience and tone, drafting content with common copywriting structures, and suggesting search-engine improvements.
156 2d ago A 86 tokens
Instructions file
A set of instructions for Claude Code workspaces, covering instruction files, how instructions are loaded, and rules that apply automatically or after trigger words.
156 2d ago A 715 tokens
Plugin Claude Code
v0.4.1 — Portable execution playbook for Claude Code with three pilot modes: Haiku Pilot (cost-first default, 70–85% savings, 7-step pre-flight incl. Source-Verify + hard-task anchor ≥5), Sonnet Pilot (quality-first, 55–65% savings, 7-step pre-flight incl. Line-Level Source-Verify + hard-task auto-escalate gate), and…
24 3mo ago A
tokens not measured
original MIT
haiku-pilot
41Skill Claude CodeCodex
Haiku-first execution playbook: through deliberate prompt structure, sub-agent delegation, and quantitative escalation gates, get Haiku 4.5 to produce near-Opus quality on most tasks. Escalate to Sonnet/Opus only when gates trigger. Triggers: "haiku", "Haiku", "Haiku mode", "haiku-pilot". Do NOT use for: cost-only…
24 3mo ago A 133 tokens
original MIT
opus-pilot
42Skill Claude CodeCodex
Opus-first ceiling-elevation playbook: through reverse-advisor loops, parallel harness hypotheses, CAR-explicit declarations, externalized decision logs, and meta-harness diagnostics, push Opus 4.7 BEYOND vanilla Opus 4.7 quality. Triggers: "opus", "Opus", "Opus mode", "opus-pilot". Sub-mode modifiers: "Opus 1M" (1M…
24 3mo ago A 188 tokens
original MIT
sonnet-pilot
43Skill Claude CodeCodex
Sonnet-first quality playbook: through context engineering, sub-agent delegation, and forced self-review loops, get Sonnet 4.6 to produce code/doc quality on par with Opus 4.7. Escalate to Opus only when quantitative gates trigger. Triggers: "sonnet", "Sonnet", "Sonnet mode", "sonnet-pilot". Do NOT use for: pure cost…
24 3mo ago A 143 tokens
original MIT