AlexisBalayre
UserOne shared agent setup for Claude Code, Codex, opencode, Mistral Vibe and Cursor: AGENTS.md, skills and blocking hooks stored once in .agents/ and wired into every tool.
Categories
Indexed Skills (26)
pr-ci-review
Cost-optimal multi-agent code review of local changes or a PR, across six relevance-gated, model-tiered areas, with a deterministic pre-flight and a record-all structured verdict CI renders to the PR in full.
review-retro
Mine past automated-review runs for recurring process and judgment failures, then propose fixes to the review setup as one evidence-cited PR. Use when running the review retrospective or tuning the PR reviewer.
adapt-to-project
Fit the scaffolded agent setup to this repository by confirming the quality gate commands in .agents/quality.toml and writing the project map in AGENTS.md that the other skills read.
address-review-comments
Analyze, decide on, challenge, and implement a PR's open review comments end to end, with a human in the loop. Use when addressing PR review feedback, responding to reviewer comments, or when the user says "address review comments".
find-dead-code
Detect dead-code candidates in the repo and hand back a ranked list with per-category verification checklists.
improve-codebase-architecture
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
to-questionnaire
Turn a decision you can't fully answer into a questionnaire for someone else to fill in.
to-spec
Turn the current conversation into a spec and publish it to the project issue tracker (or a local file): no interview, just synthesis of what you've already discussed.
to-tickets
Break a plan, spec, or the current conversation into a set of tracer-bullet tickets, each declaring its blocking edges, published to the configured tracker (edges as text in one file per ticket locally, or native blocking links on a real tracker).
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
handoff
Compact the current conversation into a handoff document for another agent to pick up.
implement
Implement a piece of work based on a spec or set of tickets.
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.
domain-modeling
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing the project glossary, or recording or editing an ADR.
pr-description
Write a PR title and description (summary, evidence, merge danger) for fast human review, then create or update the PR via gh. Use when asked to draft or rewrite a PR title or body, to open a PR, or when another skill opens a PR. Assumes commits exist on the branch.
prototype
Build a throwaway prototype to answer a design question. Use when the user wants to prototype, sanity-check whether a state model or business logic feels right, or explore what a UI should look like.
review-changes
Multi-agent code review of local changes or a pull request across six relevance-gated areas, consolidated into one verdict. Use when the user asks for a review of their changes, a diff, or a PR, or says "review this".
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.
wizard
Generate an interactive bash wizard that walks a human through steps only they can perform. Use when provisioning infrastructure, setting up credentials or CI secrets, walking an unfamiliar third-party dashboard, or running a one-off migration or cutover. Don't invoke this for steps the agent can perform itself.
writing-for-agents
Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
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
Resolve an in-progress git merge or rebase conflict. Use when a merge, rebase, or cherry-pick stops on conflicts.
wait-what
Stop. That last message did not land: re-pitch it.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.