All authors
Claude Skills by korchasa
github.com/korchasa62 skills2 installs114 views
- Write PrdProduce a Product Requirements Document (PRD) for a product feature. Use when the user asks to write a PRD, or to formalize a feature's scope, goals, user value and success metrics. Not for internal technical or architecture change proposals.Votes: 0GitHub stars: 3
- AskUse when the user asks a question to be answered from the project's memex (long-term knowledge bank for AI agents) rather than training data or the live web. Reads the index, follows one SALP-REF hop, files a cited answer back. Not for source code.Votes: 0GitHub stars: 3
- AuditUse when the user asks to audit a memex (long-term knowledge bank for AI agents) for orphans, dead SALP REFs, missing sections, contradictions or index drift. Runs a structural check, layers LLM-judgement findings, auto-fixes trivia with `--fix`.Votes: 0GitHub stars: 3
- SaveUse when the user gives a source (URL, file, or text) to save into the project's memex — a long-term knowledge bank for AI agents. Stores the raw source, extracts cross-linked entity pages, audits backlinks, updates the index. Not for casual reads.Votes: 0GitHub stars: 3
- Setup Agent Code Style DenoUse when the user asks to add Deno/TypeScript code-style rules to AGENTS.md, or during initial Deno project setup. Do NOT trigger for non-Deno TypeScript projects (use setup-agent-code-style-strict), or for runtime-agnostic style advice.Votes: 0GitHub stars: 3
- Setup Agent Code Style StrictAdd TypeScript strict-mode code-style rules to AGENTS.md. The rule text ships inside this skill, so write it from here, not from memory. Use when the user asks for strict-mode style rules. Not for Deno projects (use setup-agent-code-style-deno).Votes: 0GitHub stars: 3
- Diagnose Acceptance RunWhere this repo keeps the artifacts of a failed acceptance run, what they are called, and the commands that read them. Use with the `diagnose-benchmark-failure` skill when a flowai acceptance scenario fails.Votes: 0GitHub stars: 3
- Project StatusShow the current state of this project in one report — open and in-progress tasks, the newest acceptance-test verdict per scenario, and SWE-rebench benchmark pass rates per result cell. Use when the user asks how the project is doing, what is open, which acceptance tests are red, or what the benchmarks say. Triggers on "project status", "состояние проекта", "/project-status".Votes: 0GitHub stars: 3
- 09A skill we ship should teach a method that works in the user's project. Today `diagnose-benchmark-failure` teaches this repository's directory layout, so a user who installs it is told to open files that exist only here. Splitting the two halves makes the shipped skill usable outside this repo and keeps our own paths where they stay accurate.Votes: 0GitHub stars: 3
- 09Let a user (or the agent) see the current state of the project's open tasks in one command — which tasks are in progress, which are still to do, how far each is — without reading every task file, and without assuming every project uses flowai's own task layout.Votes: 0GitHub stars: 3
- Tasks OverviewShow the current state of the project's tasks, hiding archived ones, deriving the task layout from AGENTS.md and generating a project-local status script. Use when the user asks which tasks are open or in progress, or how far the work has got.Votes: 0GitHub stars: 3
- Split WorkSplit independent work items and run them in parallel through subagents. Use when a request names several areas that do not share files.Votes: 0GitHub stars: 3