组织

Ravn

所在地 · American Fork, UT访问官网 ↗更新于 2026-11-13

Skills
41
仓库
1
职业覆盖
0
场景覆盖
0
Stars
★ 2

Ravn 的 Skills 41

ravnhq
ravnhq/ravn-core

writing-for-agents

Writing documents for agents. Use when creating or editing skills, or modifying AGENTS.md or CLAUDE.md.

★ 2
ravnhq
ravnhq/ravn-core

why

Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Queries every available evidence MCP in parallel and returns a cited read on decisions and tradeoffs. Use how for runtime behavior.

★ 2
ravnhq
ravnhq/ravn-core

typescript-best-practices

TypeScript type-safety rules: discriminated unions, branded types, no `as`, exhaustive switches, schema-derived types. Use when writing, editing, or reviewing TypeScript.

★ 2
ravnhq
ravnhq/ravn-core

show-me-your-work

Keep a reviewable decision trail for unattended or multi-phase work: a TSV log with one row per decision (what, why, evidence, result).

★ 2
ravnhq
ravnhq/ravn-core

ship

Take a change from idea to a ready PR with passing CI, running research, grilling, design, verification, and the pr skill in sequence.

★ 2
ravnhq
ravnhq/ravn-core

session-pickup

Resume unfinished work from a handoff note or prior coding-agent session. Use before reading a supplied handoff, even when its next action is only an inspection or report. Also use to pick up, continue where you left off, or take over from a transcript, agent URL, or pushed branch. Use pause-safely to write a handoff.

★ 2
ravnhq
ravnhq/ravn-core

review-and-simplify

Review the current branch or a GitHub PR with risk-tiered specialist subagents, judge their findings, apply safe simplifications to your own branch, and post to the PR on request.

★ 2
ravnhq
ravnhq/ravn-core

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.

★ 2
ravnhq
ravnhq/ravn-core

principle-type-system-discipline

Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, exhaust variants, derive from authoritative schemas.

★ 2
ravnhq
ravnhq/ravn-core

principle-separate-before-serializing-shared-state

Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.

★ 2
ravnhq
ravnhq/ravn-core

principle-prove-it-works

Apply after completing a task, before declaring done. Verify against the real artifact (run the feature, read the actual value, inspect the diff), not a proxy, self-report, or "it compiles."

★ 2
ravnhq
ravnhq/ravn-core

principle-make-operations-idempotent

Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.

★ 2
ravnhq
ravnhq/ravn-core

principle-guard-the-context-window

Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.

★ 2
ravnhq
ravnhq/ravn-core

principle-fix-root-causes

Apply when choosing where to fix a bug. Trace each symptom back to the first place the system went wrong and fix it there. A guard is a fix only when the state it handles is legitimate.

★ 2
ravnhq
ravnhq/ravn-core

principle-explain-the-number

Apply before you trust, report, or act on a measured number (speedup, regression, throughput, latency, eval result). Find what limits it, and rule out that it measured something other than the work you think.

★ 2
ravnhq
ravnhq/ravn-core

principle-boundary-discipline

Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.

★ 2
ravnhq
ravnhq/ravn-core

pr

Write a pull request body, for pushed work or an existing PR.

★ 2
ravnhq
ravnhq/ravn-core

pause-safely

Pause work and leave a handoff note a cold-start agent, in any harness, can resume from. Use when the user asks to pause, stop for now, go offline, restart, or hand off; "keep going" and automatic context compaction are not pauses. Use session-pickup to resume.

★ 2