House README standard: structure, badge row, tone, per-archetype templates, and verification gates for steipete/openclaw repos.
npx skills add https://github.com/openclaw/agent-skills --skill readme-standard
One structure for every public README in the steipete and openclaw orgs. Load
this skill before writing or reviewing a README. The reference implementation
is openclaw/fs-safe — read its README
first if unsure what "good" looks like.
Every README answers, in order, with no detours:
reference material moves to docs/ (or the docs site) and gets linked.
Concretely:
# <name> <one emoji> — <playful tagline, one line>
<badge row>
<1–2 sober sentences: what it is, who it is for. No adjectives doing the work
nouns should do.>
<OPTIONAL: one small code/terminal sample (≤10 lines) that demonstrates the
core value. If one sample can prove the pitch, put it here.>
## Install ← smallest path first (brew/npm/npx), alternatives after
## Quick start ← 60 seconds to first success; commands must actually run
## <core sections> ← 2–6 sections, each one level deeper than the last
## Development ← build/test/lint in ≤10 lines, link CONTRIBUTING if present
## License ← one line
First paragraph states plainly what the tool does and for whom.
capabilities into the sections where they are demonstrated.
README describes the present tense of the tool. Version-specific migration
notes live in the changelog or docs/.
Anything beyond that moves to docs/ with a link. Exhaustive command/flag
references belong in docs/ or the docs site, never in the README — a
summary table with links is fine.
have a working setup for that level of use.
one screenshot near the top. Compress; no >500 KB images.
…), the README is a front door, not a mirror. Link, don't duplicate.
Style: flat-square, always dynamic — a badge that can go stale is a bug.
Never hardcode versions into img.shields.io/badge/... URLs.
Order: CI · version · platform/runtime · license · extras (Homebrew, docs).
[](https://github.com/OWNER/REPO/actions/workflows/ci.yml)
Per ecosystem, add what applies:
https://img.shields.io/npm/v/PKG?style=flat-square → npm pagehttps://img.shields.io/github/v/release/OWNER/REPO?style=flat-squarenpm/node/v badge for npm packages; staticbadge/platforms-... or badge/Swift-6.x-... is acceptable for facts that
only change with a commit (platforms, language version, min OS).
https://img.shields.io/github/license/OWNER/REPO?style=flat-squareUse the repo's *actual* workflow filename and default branch in the CI badge.
Verify every badge URL renders (HTTP 200 and not the shields "invalid" card)
before shipping.
CLI tool (Go/TS binary) — Install (brew → go install/npm), Quick start
(3–6 commands with one-line comments showing a real session), Commands
(summary table linking docs/), Configuration, JSON/automation output if
agent-facing, Development, License.
npm library — Install, one core-usage sample that compiles, then one
section per capability tier (basic → options → advanced/edge), API reference
link (docs site or generated docs), Development, License.
Swift package — badges (Swift version, platforms, CI), SPM install snippet
(both Package.swift lines), Quick start compiling sample, capability
sections, platform notes, Development, License.
macOS app — screenshot first, Install (brew cask → direct download link),
what-it-does tour keyed to the screenshot, permissions/setup notes,
Development, License.
Web service / site — what it is + hosted URL, self-host/deploy path,
local development, architecture pointer, License.
package) and execute each quickstart/example command, or validate flags
against real --help output when execution needs credentials/hardware.
Fix the README, not the transcript.
file in the repo's toolchain is enough).
returns non-404; every badge renders.
stale minimums, or "coming soon" for shipped things. Check package.json/
go.mod/Package.swift for the real runtime floors.
exist in docs/ already, be moved there in the same PR, or be genuinely
obsolete (state which in the PR body).
Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.
Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Build and distribute Expo development clients locally or via TestFlight
Use when you have a written implementation plan to execute in a separate session with review checkpoints
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.
Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.
Take openclaw/readme-standard from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference go.
Without those the skill loads but fails at the first command.