
Claude Skills by Inebrio
github.com/InebrioShape of a feature analysis document (00-analysis.md). Use when writing or reading the analysis artifact that opens a feature.
Rules for service, CLI, shared types and infrastructure code in this repository. Use when implementing anything behind the interface.
Shape of a story blueprint, the technical plan an orchestrator executes. Use when writing or reading a blueprint artifact.
Where things live in this repository and how to find them fast. Use before analysing, planning or implementing anything in this project.
Run five independent reasoners on one high-stakes decision and converge. Use when a choice is expensive to reverse and a single opinion is not enough.
Where documentation lives in this repository, how a page is structured, and what a change owes the docs. Use when writing or updating documentation.
Run a Tier 1 or Tier 2 feature end to end — feature level, story level, parallelism, integration, and retrospective. Use when you are running a multi-agent feature per AGENTS.md's Workflow tiers, not for Tier 0 inline work.
Rules for the dashboard SPA in this repository, including the visual bar a page must clear. Use when implementing anything a user sees.
How to freeze and arbitrate the interface between parallel implementers. Use when coordinating backend and frontend work on the same story.
Non-negotiable rules of this project — wire transparency, surface parity, permission chain, branch policy. Use when planning or reviewing any change here.
Drive a story from BLOCKED back to PASS after validation, with a hard iteration cap. Use when a validation report lists blocking findings.
Judge which documentation screenshots a change actually invalidates, on top of the mechanical selector, and get a person's approval before regenerating any of them. Use when reviewing a diff that touches the dashboard before its screenshots are refreshed.
Analyze the staged diff and write a conventional commit message, then commit.
Run one user story end to end in its own worktree, from claim to merge. Use when you are responsible for delivering a single story.
Where tests live in this repository, how to run them, and what a story owes in coverage. Use when writing or running tests.
Shape of a user story file with acceptance criteria and edge cases. Use when writing or reading a story artifact.
How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking. Use when verifying implemented work.