Orkas-AI

164 mods across 3 repositories, 2.5k stars between them.

pdf-editing

49

Orkas-AI/Orkas

Skill Claude CodeCodex

Use the bundled tools; do not install nano-pdf, pypdf, qpdf, Poppler, or another PDF package during a task.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 3 tokens original MIT

brand-research

50

Orkas-AI/Orkas

Skill Claude CodeCodex

Use this skill to research a company, product, or brand from its website and public sources, then produce a sourced Brand DNA brief. The work is evidence collection plus synthesis; do not invent missing facts.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 3 tokens original MIT

product-dev

51

Orkas-AI/Orkas

Skill Claude CodeCodex

Deliver scoped repository changes or technical decisions with verification evidence. Product discovery, disposable prototypes, product acceptance design, and repository operations belong to their respective capabilities.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 2 tokens original MIT

github

52

Orkas-AI/Orkas

Skill Claude CodeCodex

Use gh as the primary interface for GitHub data and actions. Keep this skill focused on basic operations and command safety, not maintainer triage strategy.

not rated 2.2k +31 today A SkillSpector: pass 1 tokens original MIT

product-test

53

Orkas-AI/Orkas

Skill Claude CodeCodex

Use this skill to define the observable behavior that must be true for a story or feature to be considered done. It turns product context into concise, testable Given/When/Then scenarios that engineers and QA can verify without guessing intent.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 2 tokens original MIT

material-organizer

54

Orkas-AI/Orkas

Skill Claude CodeCodex

Organize only the materials the user has already provided or explicitly pointed to. The job is to make messy inputs easier to scan, reuse, archive, or continue from later while preserving source traceability.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 3 tokens original MIT

content-writer

55

Orkas-AI/Orkas

Skill Claude CodeCodex

Turn a goal, source pack, or draft into defensible, channel-ready content. Keep research, evidence, composition, and editing distinct.

not rated 2.2k +31 changed 24d ago A SkillSpector: warn 3 tokens original MIT

swiftui-dev

56

Orkas-AI/Orkas

Skill Claude CodeCodex

Use this skill for SwiftUI development, architecture, structure, performance, and Apple native app profiling. It combines.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 3 tokens original MIT

office-word

57

Orkas-AI/Orkas

Skill Claude CodeCodex

Use the bundled Office tools as the default path. Do not install OfficeCLI or document libraries when these tools are available.

not rated 2.2k +31 changed 1mo ago A SkillSpector: pass 2 tokens original MIT

social-data

58

Orkas-AI/Orkas

Skill Claude CodeCodex

Skill "social-data" from Orkas-AI/Orkas, covering social data, when to use, how to call, default output and social data fetch result.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 2 tokens original MIT

deep-research

59

Orkas-AI/Orkas

Skill Claude CodeCodex

The agent chooses the research question, gathers sources, and writes the report. This Skill performs deterministic processing only; it never calls a model.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 3 tokens original MIT

office-ppt

60

Orkas-AI/Orkas

Skill Claude CodeCodex

Use the bundled Office tools as the default path. Do not install OfficeCLI or python-pptx when these tools are available.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 3 tokens original MIT

wps

61

Orkas-AI/Orkas

Skill Claude CodeCodex

Use office-word, office-excel, or office-ppt for the artifact-specific workflow, and apply the WPS compatibility checks in this skill.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 1 tokens original MIT

product-ui

62

Orkas-AI/Orkas

Skill Claude CodeCodex

Use this skill when UI design and UI implementation should happen together. It turns product context into usable frontend screens, components, layout decisions, design-system choices, accessibility rules, and visual polish.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 2 tokens original MIT

agent-creator

63

Orkas-AI/Orkas

Skill Claude CodeCodex

Create or edit a custom Agent by emitting one inline ... container in the final reply. The host parses and applies the container; do not call a mutation tool or write agent.json directly.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 3 tokens original MIT

package-installer

64

Orkas-AI/Orkas

Skill Claude CodeCodex

Install third-party open-source projects (a GitHub URL or a local git directory the user provides) as external packages. The project is cloned verbatim into the per-user packages directory — never edit, normalize, or reorganize its files.

not rated 2.2k +31 changed 24d ago A SkillSpector: pass 3 tokens original MIT

skill-creator

65

Orkas-AI/Orkas

Skill Claude CodeCodex

Create, edit, or faithfully import a custom Skill through host-owned metadata tags, >> whole-file blocks, or the native package importer. Do not mutate the Skill directory with generic file or shell tools.

not rated 2.2k +31 changed 15d ago A SkillSpector: pass 3 tokens original MIT

seo-backlink-value

66

Orkas-AI/Orkas

Skill Claude CodeCodex

Value a backlink offer the way a buyer should: veto bad sites first, then price the good ones against a market band and the seller's quote. Deterministic, stdlib-only, no network. The agent supplies the metrics; this skill only computes.

not rated 2.2k +31 today A 4 tokens original MIT

data-analysis

67

Orkas-AI/Orkas

Skill Claude CodeCodex

Derive reviewable conclusions from the user's data. Use the available source and computation tools; this Skill does not prescribe a format, language, library, or artifact. Respect project metric definitions and business rules. Preserve inputs unless transformation was requested, and match effort to the decision's risk.

not rated 2.2k +31 today A 2 tokens original MIT

investment-report

68

Orkas-AI/Orkas

Skill Claude CodeCodex

Read when the user requests a synthesis, comparison, handoff, or durable report. Do not rerun unrelated analysis merely to fill a template.

not rated 2.2k +31 today A 2 tokens original MIT

market-data

69

Orkas-AI/Orkas

Skill Claude CodeCodex

Read for every substantive StockAnalyser route. It owns the shared input and evidence contract; the other Skills own interpretation.

not rated 2.2k +31 today A 2 tokens original MIT

portfolio-risk

70

Orkas-AI/Orkas

Skill Claude CodeCodex

Read with market-data for a portfolio review, stress test, or rebalance question. Keep account values and holdings private and use only what is needed.

not rated 2.2k +31 today A 2 tokens original MIT

quant-lab

71

Orkas-AI/Orkas

Skill Claude CodeCodex

Read with market-data for strategy design, backtesting, or experiment review.

not rated 2.2k +31 today A 3 tokens original MIT

security-research

72

Orkas-AI/Orkas

Skill Claude CodeCodex

Read with market-data for a company thesis, comparison, factor screen, or watchlist. The goal is a decision-ready evidence map, not a forced rating.

not rated 2.2k +31 today A 3 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: