Skip to content

Kartik-Doye/Ravengard-AI-Recruiter / agent/skills/frontpage

frontpage

Verified

Creates or improves a repository README for prospective users, evaluators, and contributors using verified product facts, executable commands, examples, and links. Use when the repository front page is missing, stale, unclear, or overrun by internal detail.

FileKindSize
SKILL.mdskill md10.2 KB
references/readme-blueprint.mdmarkdown3.4 KB
references/research.mdmarkdown793 B

references/readme-blueprint.md

View on GitHub
# README blueprint: the section menu

Not every README needs every section. Pick by project type; order by
reader value.

## Above the fold (mandatory, in this order)

1. **Name + one-line value proposition**: what it is, stated plainly.
   "Fast, offline-first notes app that syncs when it can."
2. **Why it's different**: one or two lines max; comparison detail
   lives further down.
3. **One command to try it**: the copy-paste that gets a working
   example running. If there's no such command yet, the honest v0 says
   what's coming instead of faking it.
4. **The visual**: a screenshot/GIF of the real thing (current build,
   not the 2024 mock), or the skill-map diagram for a bundle. A README
   without a single visual is a wall.

## The menu

| Section | Earns its place when… |
| --- | --- |
| Features | the list is scannable and true: not a feature-dump of aspirations |
| Quick start | shortest verified path to first success; put it high |
| Installation | more than the one-liner: prerequisites, platforms, package managers |
| Usage | real commands with real output; the 80% path first |
| Examples | runnable, tested, linked to files in `/examples` |
| Architecture | the project is non-trivial; link to `docs/architecture/` (blueprint) |
| Configuration | a table: option · default · meaning: generated from the actual config surface |
| Compatibility | only what was tested; versions from CI matrix, not hope |
| Comparison | honest, checkable facts; no invented feature cells for rivals |
| Benchmarks | methodology + numbers you can reproduce; without both, cut it |
| FAQ | the same 3+ questions keep arriving |
| Roadmap | real intent, not wishful marketing |
| Contributing | the repo actually accepts contributions |
| Security | disclosure policy; point at SECURITY.md |
| License | one line + link; the file itself is janitor's check |

## Project-type templates

**CLI/library:** fold → quick start → install → usage → config →
examples → contributing → license.
**Web app:** fold → screenshot/demo → quick start → features → config →
deployment → contributing.
**Skills bundle (like this suite):** fold → the lifecycle map visual →
install one command → per-skill cards/table → compatibility →
principles → FAQ.
**WIP/early:** name → what it is → why → roadmap → "not ready yet,
here's how to follow along". Honesty is the whole brand at this stage.

## Writing rules

- Second person, active voice, present tense: "Run the agent", not "The
  agent can be run".
- One idea per paragraph; scannable beats complete: link out for depth.
- Code blocks specify language; shell examples show expected output
  where success isn't obvious.
- No marketing fog. A performance statement needs a reproducible workload,
  method, observed result, and date.
- Version requirements carry the exact tested or declared source.
- Emojis: at most structural (section markers), never emotional
  decoration.

## The claims audit (walk before shipping)

| Claim type | Valid source |
| --- | --- |
| Version/platform support | manifest engines, CI matrix, executed install |
| Performance numbers | reproducible benchmark, method included |
| Compatibility | tested matrix or explicit "not tested" removal |
| Counts (stars/users/downloads) | live API number, dated: or cut |
| Feature list | demonstrable in the current build |

Every row without a valid source → the claim is cut, not softened.
rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content.Stars: 198kUpdated Claude CodeCodexVerifiedInstall
claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file).Stars: 198kUpdated Claude CodeCodexUnverifiedInstall
doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.Stars: 198kUpdated Claude CodeCodexVerifiedInstall