toverux
User🤖 Curated agent skills for AI agents — one coherent engineering loop that compounds: grill → spec → implement → review → commit → learn. Adopt it or fork it!
Categories
Indexed Skills (47)
commit
Commit the working tree with a repo-appropriate, value-communicating message, then scan the session for compound-worthy learnings.
compound-refresh
Garbage-collect the knowledge stores — audit docs/solutions/ and AGENTS.md against the current code.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
simplify
Optional pre-review quality pass — behavior-preserving fixes for reuse, dead weight, altitude, and clarity. Bug hunting is /code-review's job.
spec
Synthesize the current conversation into a spec at docs/specs/<feature>.md, test seams included.
teach
Teach the user a new skill or concept, within this workspace.
tickets
Break a spec, plan, or the current conversation into tracer-bullet ticket files alongside the spec, each declaring its blocking edges.
code-review
The review gate — check the changes since a fixed point against the spec and the project's standards, in parallel subagents.
review-gate
The review gate — effort-scaled, multi-angle review of the working diff or the changes since a fixed point, every finding independently verified.
questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
handoff
Compact the conversation into a handoff document a fresh session can resume from.
implement
Implement a spec or a single ticket, driving TDD at the seams agreed in the spec.
grill-me
Grill the user relentlessly about a plan, decision, or idea.
codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
compound
Capture this session's durable learnings and route each to the right knowledge store, every write user-gated. Use at loop end when the commit tail prompts a session scan, when diagnosing-bugs closes out a fix, or when the user wants to capture, remember, or write down a learning, convention, gotcha, or preference.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, explore what a UI should look like, or when a decision in a grill-me interview needs empirical evidence.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
writing-great-skills
Load before writing or editing any file an agent will load and act on — a skill (SKILL.md), an AGENTS.md or CLAUDE.md, or a rules file. The vocabulary and principles that make those files predictable. A session that only reads them leaves this unloaded.
typescript-code-style
Load before writing or editing any TypeScript or JavaScript file (.ts, .tsx, .js, .jsx), the moment a task will create or modify such code and before the first edit. Covers strictness, style, nullability, immutability, and assertion-based error handling. The trigger is writing; a session that only reads code leaves it unloaded.
general-code-style
Load before writing or editing any source file, in any language, the moment a task will create or modify code and before the first edit. Covers line breaks, the 100-character line limit, comments, and docblocks. The trigger is writing; a session that only reads code leaves it unloaded.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to be grilled about a plan, wants a decision stress-tested, or when requirements are fuzzy before a spec is written.
setup-cantrips-loop
Configure this repo's cantrips loop — knowledge stores and storage backend — by writing docs/agents/cantrips-loop.md.
writing-for-agents
Load before writing or editing any file an agent will load and act on — a skill (SKILL.md), an AGENTS.md or CLAUDE.md, or a rules file. The vocabulary and principles that make those files predictable. A session that only reads them leaves this unloaded.
sync-upstream
Reconcile this repo's forked skills with a new upstream release. Use when the user says an upstream (compound-engineering, mattpocock/skills) was updated, asks to merge/sync upstream changes into the forks, or wants the forks' divergence audited.
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
general-guidelines
Behavioral guidelines to reduce common LLM coding mistakes. Always use this when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes, surface assumptions, and define verifiable success criteria.
cs-code-style
Load before writing or editing any C# file (.cs), the moment a task will create or modify C# code and before the first edit. Covers language level, member declaration style, type choice, and naming. The trigger is writing; a session that only reads code leaves it unloaded.
afk
Keep the session's prompt cache warm while you step away.
commit
Scan the session for compound-worthy learnings, then commit the working tree with a repo-appropriate, value-communicating message.
compound-refresh
Garbage-collect the knowledge stores — audit AGENTS.md, and docs/solutions/ where that store is enabled, against the current code.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
simplify
Optional pre-review quality pass — preserving fixes through the reuse, simplification, and efficiency lenses. Bug hunting is /review-gate's job.
spec
Synthesize the current conversation into a published spec, test seams included.
teach
Teach the user a new skill or concept, within this workspace.
tickets
Break a spec, plan, or the current conversation into tracer-bullet tickets, each declaring its blocking edges.
implement
Implement a spec or a single ticket, driving TDD at the seams agreed in the spec.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
codebase-design
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.
tdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
compound
Capture this session's durable learnings and route each to the right knowledge store, every write user-gated. Use at loop end when /commit's opening scan finds candidates, when /diagnosing-bugs closes out a fix, or when the user wants to capture, remember, or write down a learning, convention, gotcha, decision, or preference.
writing-great-skills
Load before writing or editing any file an agent will load and act on — a skill (SKILL.md), an AGENTS.md or CLAUDE.md, or a rules file. The vocabulary and principles that make those files predictable. A session that only reads them leaves this unloaded.
research
Investigate a question against high-trust primary sources and capture the findings as a Markdown file in the repo. Use when the user wants a topic researched, docs or API facts gathered, or reading legwork delegated to a background agent.
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.