Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/XxYouDeaDPunKxX/ai-protocol-kit/llms.txt

Use this file to discover all available pages before exploring further.

The GitHub README Framing and Authoring Protocol v2 is a phase-gated working contract for writing, rewriting, restructuring, or materially reframing a repository README. Its purpose is to derive the right README from the real project, the real reader, and the real job the README must perform — not from template momentum, generic GitHub conventions, or inherited wording. Use it whenever you are about to produce or substantially change a README and want the output to be accurate, fitted, and justified rather than complete-looking.

Core Rule

Build the smallest correct README that accurately represents the real project, fits the real reader, uses the real reader’s language, and performs the real job the README needs to do.

Operating Posture

This protocol is README-specific. It is not a generic output protocol. It exists to help the AI derive the right README from repository truth — not from template momentum, vague confidence, or inherited wording. Do not assume every repository needs the same README. Do not assume every README should be comprehensive. Do not assume every README should mirror familiar GitHub templates. Do not assume the existing README is correct. Do not let the most visible files alone define the whole repository.

Interaction Rules

Follow the phases in order. Before writing, close the project model, the README role, the reader model, the language boundary, and the section model. An unresolved ambiguity does not pass to the next phase.
RuleBehaviour
Phase orderFollow phases in order; do not skip to drafting, formatting, badges, or polish.
Ambiguity handlingIf ambiguity remains and could materially change reader fit, role, claims, structure, language, or next action, stop and ask before proceeding.
Asking questionsAsk one thing at a time. Keep materially distinct ambiguities separate.
Evidence useUse real evidence from the workspace. Do not invent features, workflows, maturity, stability, support level, or status.
Existing READMETreat as gated material. Do not read it unless operator authorisation is explicitly given.
OptimisationOptimise for correctness, clarity, fit, orientation value, and reader usefulness — not for completeness.

Phases

1
Phase 1 — Classify the Project
2
Determine and report: project name, project type, primary purpose, primary audience, current maturity, primary user or reader, primary public or operational unit, whether the repository is product-facing, developer-facing, research-facing, content-facing, internal-facing, or mixed, and whether the repository is primarily something to use, install, read, adapt, study, deploy, extend, evaluate, or reference.
3
Project type taxonomy
4
TypeDescriptionapplicationA runnable software applicationlibraryImportable or linkable code for reuseCLI toolA command-line interfaceframeworkAn opinionated structure or runtime scaffoldtemplate or starterA starting point or scaffolddocumentation repositoryWritten documentation as the primary outputcontent repositoryWritten, media, or mixed contentresearch repositoryExperimental work, studies, or findingsartifact repositoryCompiled or packaged release artefactsshowcase repositoryPortfolio or demonstration workmixed repositoryMore than one type in meaningful proportioninternal operational repositoryTooling, configs, scripts not intended for public use
5
Primary unit taxonomy
6
UnitExamplessource repositoryThe repo itself is the artefactpackagenpm, PyPI, RubyGems, etc.CLICommand-line tooldeployable applicationA runnable build or containerdocumentation surfaceRendered docsstatic siteGitHub Pages or similarcontent collectionA set of articles, files, or mediaresearch artifactPapers, notebooks, datasetsreusable templateStarter files, scaffoldportfolio or showcase artifactDemonstration or portfolio entry
7
Stop and ask if classification remains materially ambiguous. Do not proceed with README role selection or section design on unresolved project classification.
8
Phase 2 — Inspect the Workspace
9
Read only enough to close the README decision perimeter. Determine and report: high-level repository structure, manifests and package descriptors, entry points, core modules, executable surfaces, scripts relevant to running or building the project, configuration surfaces, dependency signals, deployment signals, documentation surfaces other than the README, licensing signals, contribution or governance signals, whether the repository appears stable or experimental, whether there are public-facing claims already encoded elsewhere, and whether the repository contains multiple reader surfaces that should not be collapsed into one README voice.
10
README gate rule
11
If a README already exists, do not read it in this phase. Do not use it for initial project understanding. Do not treat it as a primary source. Access to the existing README requires explicit operator authorisation. Without authorisation, the existing README remains out of scope.
12
Do not compensate for missing evidence by falling back to generic README conventions. If workspace evidence is insufficient to support justified framing, stop and ask.
13
Phase 3 — Determine the README Role and Reader Action
14
Before drafting anything, decide and report what job the README must perform. Close the reader before closing the structure. Do not design a README for a generic GitHub visitor if the real reader is narrower or more specific.
15
Possible README roles
16
RoleWhen to useorientation surfaceReader needs to understand what the project isquickstart surfaceReader needs to go from zero to running quicklyusage surfaceReader knows what it is; needs to use ittechnical entrypointReader is a developer or integratordocumentation gatewayREADME routes into a deeper docs treeinstallation guidePrimary job is getting it installedproject overviewBroad summary for evaluators or newcomersreference surfaceLookup-oriented; reader returns repeatedlyportfolio-facing overviewEvaluator or employer audienceresearch framing surfaceAcademic or experimental contextadaptation or integration surfaceReader is adapting or embedding the project
17
Do not assume every README is mainly a quickstart or a project overview. Do not assume every README should route into a docs tree. Do not let a secondary reader distort the README away from the primary reader.
18
Phase 4 — Determine Editorial Posture and Language Boundary
19
Before defining sections, decide and report how the README should sound and what kind of language it is allowed to use. Tone is not decoration — language is part of reader fit.
20
Determine and report: whether the README should be technical-first or orientation-first, whether it should be concise, moderate, or expansive, the appropriate tone (sober, practical, explanatory, direct, or mixed), the real reader’s natural vocabulary, which terms are normal and clear for that reader, which terms would sound internal or inflated, and any preferred or forbidden wording.
21
Do not let tone overstate project maturity, polish, stability, or support. Do not default to internal system taxonomy when plain reader language exists. Do not let editorial polish substitute for unresolved framing.
22
Phase 5 — Design the README Model
23
Before writing full prose, decide and report the README structure. Determine and report: recommended title form, recommended opening pattern, what belongs above the fold, which sections are required, which are optional, which should be excluded, the order that best fits the README role, which claims are justified, which claims are not justified, and what details should stay in deeper docs rather than the README.
24
Possible sections (treat as options, not defaults)
25

Full section list

SectionJustification required?
titleAlways
one-line descriptionAlmost always
project overviewWhen reader needs orientation
why it existsWhen motivation is non-obvious
statusWhen maturity or stability is a reader concern
features or capabilitiesWhen the feature set is the primary decision signal
installationWhen setup is non-trivial or the reader needs it
quickstartWhen speed-to-running is the primary job
usageWhen usage patterns are complex or non-obvious
examplesWhen concrete examples aid comprehension
configurationWhen configuration is a meaningful reader task
project structureWhen structure aids navigation or contribution
architectureWhen design decisions affect integration
developmentWhen contributors need a separate on-ramp
limitationsWhen known limitations affect reader decision
roadmapWhen planned work is a meaningful signal
documentation linksWhen a deeper docs tree exists
contributingOnly if contribution is actively invited and supported
licenseWhen the licence is a meaningful signal for this reader
26
Do not generate section bureaucracy. Do not include common sections just because they are common. If a section is skipped, know why. Prefer the smallest correct structure.
27
Phase 6 — Draft the README
28
Write the README only after the model is defined. Write each section for its actual reader, actual job, and allowed technical depth.
29
Drafting rules
30
  • Write in plain, direct language.
  • Avoid filler, ceremony, and generic GitHub mood.
  • Start with what the project is and what it does.
  • Make examples, commands, and setup steps accurate and project-real.
  • Make claims proportionate to the actual maturity and scope.
  • Prefer concrete explanation over generic marketing language.
  • Do not let section count substitute for clarity.
  • 31
    If commands, examples, configuration, installation steps, or environment claims cannot be verified from the workspace, stop and ask before asserting them. Do not use confident wording to hide missing evidence.
    32
    Phase 7 — Review Against Project Truth and Reader Truth
    33
    Before finalising, produce a concise review stating: what the README is trying to do, who it is for, what it foregrounds, what it deliberately keeps out, which project claims it makes, which claims it avoids, which sections were included and why, which sections were excluded and why, and which risks remain.
    34
    Check for
    35
  • Overstatement of maturity or scope
  • Invented features
  • Generic template drag
  • Missing core orientation
  • Mismatch between tone and project reality
  • Internal or machine-like vocabulary where reader language should be used
  • Setup steps not grounded in the repository
  • Claims not supported by workspace evidence
  • 36
    Do not finalise the README until this review is complete.
    37
    Phase 8 — Optional Existing README Audit (Gated)
    38
    This phase is gated. Only enter if the operator explicitly authorises reading the existing README. If authorisation is granted, read the existing README as material to audit — not as a primary source of truth. Do not let the old README override the project model already established.
    39
    If authorised, determine and report: what the existing README gets right, what it gets wrong, what it overstates, what it understates, what should be preserved, what should be revised, what should be removed, and whether the final result should be a revision, restructuring, or full rewrite.

    What NOT to Invent

    No invented features

    Do not describe features, workflows, or capabilities that cannot be verified from real workspace evidence.

    No assumed maturity

    Do not use language that implies stability, production-readiness, or long-term support unless the project clearly justifies it.

    No template drag

    Do not include sections, badges, or structure just because they are common on GitHub repositories of similar appearance.

    No unverified commands

    Do not write installation steps, quickstart commands, or configuration examples that have not been verified against the real workspace.

    Final Safeguards

    • Never assume every repository needs a comprehensive README.
    • Never assume every README should begin with feature bullets.
    • Never assume every project needs badges.
    • Never assume installation or quickstart belongs in every README.
    • Never assume contribution guidance belongs in the README rather than elsewhere.
    • Never assume the existing README is correct.
    • Never read the existing README without operator authorisation.
    • Never optimise for template completeness.
    • Never use prose quality to hide unresolved ambiguity.
    • Always optimise for a README that is justified, accurate, readable, and fitted to the real project and the real reader.

    Build docs developers (and LLMs) love