New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Rfc Create

by jiangzhe in jiangzhe/doradb

Design and formalize Doradb RFC documents through evidence-gated research, materially different architectural proposals, two review rounds, and explicit draft and formalization approvals.

Apache-2.0Auto-check passedSales & Support

Install Rfc Create

skills CLI
$ npx skills add jiangzhe/doradb --skill rfc-create -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jiangzhe/doradb rfc-create --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jiangzhe/doradb.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/rfc-create .claude/skills/rfc-create && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
rfc-create
GitHub stars
121
Token cost
~1.2k tokens
SKILL.md length
545 words
Files
3 (incl. references)
Skills in repo
10
Repo updated
First seen
Licence
Apache-2.0

At a glance

Design and formalize Doradb RFC documents through evidence-gated research, materially different architectural proposals, two review rounds, and explicit draft and formalization approvals.

  • Works in 6 steps: Perform deep research across relevant… → Produce materially different proposals… → Require user selection or feedback… → …
  • Planning large architectural
  • SKILL.md covers Required Flow, Research and Evidence Gate, Round 1: Proposals and Draft the RFC, plus 3 more sections
  • Calls cargo

What it does

Rfc Create is an agent skill from jiangzhe/doradb. Design and formalize Doradb RFC documents through evidence-gated research, materially different architectural proposals, two review rounds, and explicit draft and formalization approvals. Use when planning large architectural or multi-phase program changes in docs/rfcs, including work sourced from backlogs.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 4 other files, including reference files (for example `agents/openai.yaml` and `references/workflow.md`).

It sits in Sales & Support, covering Proposals and quotes. The repository describes itself as: DoraDB - Async Rust storage engine. The licence is Apache-2.0.

When your agent uses it

  • Planning large architectural
  • Multi-phase program changes in docs/rfcs
  • Including work sourced from backlogs

Example prompts

  • “/rfc-create”

Workflow steps

6 steps, taken from the first numbered list in SKILL.md.

  1. Perform deep research across relevant documentation, code, and provided
  2. Produce materially different proposals under the proposal quality gate.
  3. Require user selection or feedback before drafting.
  4. Create one status: draft RFC file only after explicit approval.
  5. Run a second discussion and revision round on the draft.
  6. Require explicit approval before promoting the draft to proposal or

What it can do on your machine

Read from SKILL.md and the folder at commit 78c6c3d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • cargo

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Rfc Create loads about 1.2k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 80 tokens; SKILL.md has 545 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~80
When it runs · the whole SKILL.md, loaded when a task matches
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jiangzhe/doradb at commit 78c6c3d, republished under its Apache-2.0 licence (© jiangzhe). 545 words, ~1,212 tokens.

Download SKILL.mdSave it as .claude/skills/rfc-create/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.
name
rfc-create
description
Design and formalize Doradb RFC documents through evidence-gated research, materially different architectural proposals, two review rounds, and explicit draft and formalization approvals. Use when planning large architectural or multi-phase program changes in docs/rfcs, including work sourced from backlogs.

RFC Create Workflow

Use this skill to design and formalize an RFC before implementation. Scripts are executable; invoke them directly (no cargo +nightly -Zscript prefix).

Read references/workflow.md completely before executing this workflow.

Required Flow

  1. Perform deep research across relevant documentation, code, and provided conversation context.
  2. Produce materially different proposals under the proposal quality gate.
  3. Require user selection or feedback before drafting.
  4. Create one status: draft RFC file only after explicit approval.
  5. Run a second discussion and revision round on the draft.
  6. Require explicit approval before promoting the draft to proposal or accepted.

Do not skip or reorder these gates.

Research and Evidence Gate

Read relevant architecture and process documents, then inspect impacted modules and call paths. At minimum, consider:

  • docs/architecture.md
  • docs/transaction-system.md
  • docs/index-design.md
  • docs/checkpoint-and-recovery.md
  • docs/table-file.md
  • docs/process/issue-tracking.md

Read docs/process/unit-test.md when the RFC affects test strategy, timeout policy, or validation workflow.

Ground every major decision and alternative in explicit Design Inputs:

  1. Documents.
  2. Code references.
  3. Conversation references for user constraints and decisions.
  4. Source backlogs when applicable.

Use reference tokens consistently and cite at least one material input for each major decision and alternative.

Round 1: Proposals

Present goal, scope, direction, current-state analysis, and at least these three explicitly labeled proposals:

  • First-Principles Proposal
  • Long-Term Evolution Proposal
  • Original-Requirement-Fit Proposal

For each proposal, explain its scope, rationale, tradeoffs, drawbacks, and alignment or conflict with the original request. State scope expansion explicitly and identify a prerequisite or Phase 0 candidate when useful.

Recommend the best overall direction for correctness and project evolution. Do not default to the original request or use effort tiers as substitutes for materially different strategies. Explain why the original direction is weaker when the recommendation conflicts with it.

Use the three required proposals only during proposal rounds. Record the chosen direction in Decision. Record one to four materially relevant, large rejected alternatives in Alternatives Considered, and omit minor variants.

Ask for user feedback. Round 1 is incomplete without explicit input.

Show full SKILL.md (219 more words)Show less

Draft the RFC

After approval, allocate the RFC id and create the draft:

bash
tools/rfc.rs next-rfc-id
tools/rfc.rs create-rfc-doc \
  --title "RFC title" \
  --slug "rfc-title" \
  --auto-id

Keep status: draft during discussion. Follow docs/rfcs/0000-template.md. Initialize each implementation phase with:

  • Task Doc: docs/tasks/TBD.md
  • Task Issue: #0

For non-trivial phases, include concise Prerequisites and Phase-local Choices only when they guide downstream task design. Do not repeat the preceding phase outcome.

Record source backlogs under Design Inputs -> Source Backlogs.

Round 2: Draft Revision

Incorporate feedback and finalize:

  • goals, non-goals, and scope boundaries;
  • interfaces, contracts, and correctness direction;
  • implementation phases and their actionable boundaries;
  • one to four major alternatives and explicit rejection rationale;
  • consequences, risks, and test strategy;
  • open questions and future work.

When test strategy includes timeout or hang detection, treat cargo-nextest and .config/nextest.toml as authoritative. Define runner or configuration changes only when the RFC intentionally changes that workflow.

Validate before formalization:

bash
tools/rfc.rs validate-rfc-doc \
  --doc docs/rfcs/0006-example.md \
  --stage formal

Formalization Gate

Ask for explicit approval before changing draft status. Default to draft -> proposal; use accepted only with an explicit user decision.

Output Quality

Ensure the formal RFC is:

  1. Decision-complete for implementation direction.
  2. Explicit about goal, scope, and change direction.
  3. Grounded in document, code, conversation, and backlog evidence.
  4. Explicit about one to four important, large alternatives and rejection rationale, without elevating small changes into alternatives.
  5. Phase-structured for downstream task and issue tracking.
  6. Based on materially different strategic proposals.

© jiangzhe, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 2 other files (references) in .agents/skills/rfc-create of jiangzhe/doradb.

  • SKILL.md
  • agents/openai.yaml
  • references/workflow.md

Open the folder on GitHubat commit 78c6c3d

Compare with similar skills

Rfc Create next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Rfc Create compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Rfc Create this skilljiangzhe/doradb121—~1.2kAutomated safety check: PassApache-2.0
Devil Advocatejeremylongshore/tons-of-skills-marketplace2.8k—~2.1kAutomated safety check: PassMIT
Doc Coauthoringaws-samples/sample-strands-agent-with-agentcore19541 repos~3.2kAutomated safety check: PassMIT
Audit Onboarding Proposalhoangnb24/repository-harness1.2k—~4kAutomated safety check: PassMIT
No Negative EchoLB623/no-negative-echo897—~965Automated safety check: PassMIT
GEO Service Proposal Generatorzubair-trabzada/geo-seo-claude11k—~3kAutomated safety check: NotesMIT

Similar skills

  • Devil Advocate

    jeremylongshore/tons-of-skills-marketplace

    Constructive critic and stress-tester for ideas and proposals.

    2.8k GitHub stars~2.1k tokensUpdated today
    Sales & SupportAuto-check passed

  • Doc Coauthoring

    aws-samples/sample-strands-agent-with-agentcore

    Official

    Guide users through a structured workflow for co-authoring documentation.

    195 GitHub starsUsed in 41 repos~3.2k tokens
    Sales & SupportAuto-check passed

  • Audit Onboarding Proposal

    hoangnb24/repository-harness

    Use only when the user explicitly invokes $audit-onboarding-proposal.

    1.2k GitHub stars~4k tokensUpdated 5 days ago
    Sales & SupportAuto-check passed

  • No Negative Echo

    LB623/no-negative-echo

    Prevent 此地无银三百两式 residue: finalize artifacts without echoing rejected session-only alternatives into labels, metadata, commits, PRs, or handoffs.

    897 GitHub stars~965 tokensUpdated 1 mo ago
    Sales & SupportAuto-check passed

  • GEO Service Proposal Generator

    zubair-trabzada/geo-seo-claude

    Builds a client-ready AI-search-optimization proposal from an existing GEO audit, with pricing tiers, an ROI estimate and a markdown document ready to send.

    11k GitHub stars~3k tokensUpdated today
    Sales & SupportAuto-check: notes

  • Architectural Proposals

    FritzAndFriends/SharpSite

    How to write comprehensive architectural proposals that drive alignment before code is written

    145 GitHub starsUsed in 2 repos~1.6k tokens
    Sales & SupportAuto-check passed

More from jiangzhe/doradb

All 10 skills in this repo

  • Backlog

    jiangzhe/doradb

    Manage backlog todo documents in docs/backlogs with deterministic tooling.

    121 GitHub stars~1k tokensUpdated today
    Auto-check passed

  • Issue Rfc

    jiangzhe/doradb

    Create and list GitHub Issues for Doradb RFC documents with deterministic scripts.

    121 GitHub stars~519 tokensUpdated today
    Auto-check passed

  • Issue Task

    jiangzhe/doradb

    Create and list GitHub Issues for Doradb task documents with deterministic scripts.

    121 GitHub stars~719 tokensUpdated today
    Auto-check passed

  • Rfc Resolve

    jiangzhe/doradb

    Resolve completed or superseded Doradb RFC programs after implementation tasks, tests, review, and verification are complete.

    121 GitHub stars~1.7k tokensUpdated today
    Auto-check passed

  • Style Audit

    jiangzhe/doradb

    Audit branch-diff Rust files, or explicitly requested file/directory Rust targets, for Doradb coding style using deterministic tooling and concise read-only review.

    121 GitHub stars~951 tokensUpdated today
    Auto-check passed

  • Task Prune

    jiangzhe/doradb

    Inspect and optionally remove completed Doradb task worktrees and their local branches with deterministic safety checks.

    121 GitHub stars~551 tokensUpdated today
    Auto-check passed

Categories

Questions about Rfc Create

What does Rfc Create do?

Design and formalize Doradb RFC documents through evidence-gated research, materially different architectural proposals, two review rounds, and explicit draft and formalization approvals. Rfc Create is an agent skill from jiangzhe/doradb. Design and formalize Doradb RFC documents through evidence-gated research, materially different architectural proposals, two review rounds, and explicit draft and formalization approvals.

When should I use Rfc Create?

Rfc Create fits situations like: planning large architectural; multi-phase program changes in docs/rfcs; including work sourced from backlogs.

How do I install Rfc Create in Claude Code?

Run `npx skills add jiangzhe/doradb --skill rfc-create -a claude-code`. Or copy the skill folder (.agents/skills/rfc-create in jiangzhe/doradb) into .claude/skills/rfc-create in your project. Claude Code loads it when a task matches its description.

How do I install Rfc Create in Codex?

Run `npx skills add jiangzhe/doradb --skill rfc-create -a codex`. Or copy the skill folder (.agents/skills/rfc-create in jiangzhe/doradb) into .agents/skills/rfc-create in your project. Codex loads it when a task matches its description.

Can I use Rfc Create in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jiangzhe/doradb --skill rfc-create -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/rfc-create, .gemini/skills/rfc-create, .github/skills/rfc-create and .opencode/skills/rfc-create in your project.

What does Rfc Create need to run?

Going by SKILL.md and its folder, Rfc Create needs the command-line tools its instructions call (cargo).

Does Rfc Create access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Rfc Create safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Rfc Create use?

Rfc Create is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Rfc Create use?

About 1.2k tokens (SKILL.md is roughly 4.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 766 tokens, read only when the agent opens those files.

What are the alternatives to Rfc Create?

Skills that share tags, products or a category with Rfc Create: Devil Advocate (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Doc Coauthoring (aws-samples/sample-strands-agent-with-agentcore, 195 stars), Audit Onboarding Proposal (hoangnb24/repository-harness, 1.2k stars) and No Negative Echo (LB623/no-negative-echo, 897 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Rfc Create?

jiangzhe (a GitHub user) maintains it in jiangzhe/doradb, which has 121 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on October 9, 2026.

Source: jiangzhe/doradb on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.