Skill Codex
Think through ideas, alternatives, and tradeoffs with the user without prematurely starting implementation. Use for $dale-brainstorm or a request to brainstorm or explore a direction.
Skill Codex
Review recent Codex task history and return evidence-backed workflow advice. Use only for explicit $dale-coach or a direct request to run Dale Coach on selected tasks or a recent time window.
Skill Codex
Decompose complex work into an adaptive graph of owned outcomes and evidence, using subagents by default. Use for $dale-graph, a requested task graph, or work with independent implementation or proof boundaries.
Skill Codex
Create or refresh evidence-backed REQ.md, CONTEXT.md, STATE.md, TDD.md, DESIGN.md, and DECISIONS.md repository primitives. Use for $dale-index, repository mapping, context recovery, or stale project documentation.
Skill Codex
Reframe an already bounded, difficult engineering, product, operational, or strategic question through one rigorous reasoning lens and at most one genuinely opposing lens, producing a falsifiable model, decision cruxes, and evidence needs instead of a tour of frameworks. Use when the user explicitly invokes…
Skill Codex
Keep one requested goal progressing until an observable completion condition is satisfied. Use for a sustained objective that does not require multiple PRs or a changing project graph.
Skill Codex
Monitor or repair one existing pull request using current review and CI evidence. Use for PR babysitting, scoped fixes, or carrying a PR to merge-ready state.
Skill Codex
Carry an engineering project through independently reviewable changes and PRs. Use when a requested project needs multiple PRs or explicit end-to-end delivery through merge.
Skill Codex
Maintain a repository on a requested recurring cadence using bounded priorities and live evidence. Use for recurring engineering triage or repository maintenance.
Skill Codex
Monitor a changing source or condition on a cadence, persist the last meaningful observation, and notify or act only when a user-defined change occurs. Use for watching pull requests, issues, releases, prices, availability, feeds, pages, dashboards, or other external state.
Skill Codex
Design and run a repeatable agent workflow with observation, bounded action, verification, and resumable state. Use for $dale-loop or requests to keep watching or working toward a defined outcome.
Skill Codex
Run consequential work through implementation, independent review, evidence-based acceptance, and focused revision. Use only for explicit $dale-max or a direct request to run Dale Max.
Skill Codex
Verify an existing implementation, fix, migration, deployment, runtime behavior, compatibility boundary, or other technical claim by mapping atomic claims to direct, fresh, reproducible primary signals and returning scoped PROVEN, PARTIAL, UNPROVEN, or CONTRADICTED verdicts with a compact proof capsule. Use when the…
Skill Codex
Create clear, polished, self-contained HTML visualizations by selecting and adapting task-relevant patterns from Anthropic's html-effectiveness examples. Use when the user invokes $dale-visualize, selects Dale Visualize through /skills, or asks to turn code, architecture, research, plans, comparisons, reports…
lubluniky/awesome-agent-blueprints
Skill Claude Code
C programming expert for memory management, systems programming, and performance optimization.
lubluniky/awesome-agent-blueprints
Skill Claude Code
Expert computer scientist for algorithms, complexity analysis, and distributed systems.
lubluniky/awesome-agent-blueprints
Skill Claude Code
ML engineering expert for feature engineering, model debugging, and production pipelines.
lubluniky/awesome-agent-blueprints
Skill Claude Code
Go expert for goroutines, channels, microservices, and concurrent patterns.
lubluniky/awesome-agent-blueprints
Skill Claude Code
Network performance expert for latency optimization, packet analysis, and infrastructure tuning.
lubluniky/awesome-agent-blueprints
Skill Claude Code
Prediction market specialist for market making, odds calculation, and event resolution.
lubluniky/awesome-agent-blueprints
Skill Claude Code
Quantitative finance expert for trading strategies, risk management, and portfolio optimization.
lubluniky/awesome-agent-blueprints
Skill Claude Code
Rust expert for async systems, unsafe code, and zero-cost abstractions.
lubluniky/awesome-agent-blueprints
Skill Claude Code
UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns.
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: