New: 97,000+ 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

Validation Protocol

by Inebrio in Inebrio/Routerly

How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking.

AGPL-3.0Auto-check passed

Install Validation Protocol

skills CLI
$ npx skills add Inebrio/Routerly --skill validation-protocol -a claude-code

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

GitHub CLI
$ gh skill install Inebrio/Routerly validation-protocol --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/Inebrio/Routerly.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/validation-protocol .claude/skills/validation-protocol && 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
validation-protocol
GitHub stars
100
Token cost
~628 tokens
SKILL.md length
295 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
AGPL-3.0

At a glance

How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking.

  • Verifying implemented work
  • SKILL.md covers Two levels, in this order, Evidence, Classification and Report, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Validation Protocol is an agent skill from Inebrio/Routerly. How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking. Use when verifying implemented work.

Its SKILL.md is about 630 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Self-hosted LLM gateway that routes requests across AI providers (OpenAI, Anthropic, Gemini, Mistral, Ollama) using intelligent multi-policy scoring — including an LLM-native… The licence is AGPL-3.0.

When your agent uses it

  • Verifying implemented work

Example prompts

  • “/validation-protocol”

What it can do on your machine

Read from SKILL.md and the folder at commit bcf58f1. 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

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    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

Validation Protocol loads about 628 tokens when it runs. Until then it costs about 47 tokens; SKILL.md has 295 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~47
When it runs · the whole SKILL.md, loaded when a task matches
~628

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 Inebrio/Routerly at commit bcf58f1, republished under its AGPL-3.0 licence (© Inebrio). 295 words, ~628 tokens.

Download SKILL.mdSave it as .claude/skills/validation-protocol/SKILL.md (or your agent's skills folder).
name
validation-protocol
description
How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking. Use when verifying implemented work.

Validation protocol

One file per story: <specs-root>/<feature>/03-validation/<story-id>.md.

Two levels, in this order

Static. Read the story, the blueprint, and the diff. For each acceptance criterion and each edge case, find the code that satisfies it. A criterion with no code behind it is failed before anything runs.

Dynamic. Start the application with the exact command in the blueprint, in the story's own worktree, with its own environment sourced and its own ports. Then exercise every criterion the way a user would: browser for anything a user sees, real commands for the command line, real HTTP for the API. Reading the code is never a substitute for running it.

Evidence

A verdict without evidence is an opinion. Every criterion carries what you actually observed:

  • the command you ran and its output, or
  • the request you sent and the response you got, or
  • the browser steps you took and what the page showed.

Also check what nobody asked you to: the console for errors, the server log for stack traces, the other theme, the empty state, a second run of the same action.

Classification

Blocking — a criterion or edge case fails, the app does not start, data is lost or corrupted, a security or permission check is missing or wrong, a surface the story requires is absent, or the change breaks something that worked before.

Non-blocking — everything else: cosmetics, wording, a slow path, a refactor you would have done differently. Record it, do not gate on it.

Report

markdown
# <story-id> — Validation

## Verdict
PASS or BLOCKED. One line of why.

## Criteria
| Id | Result | Evidence |
Every AC and EC from the story, none skipped, none invented.

## Blocking findings
### B1 — <what is wrong>
- Expected: <from the story, quoted>
- Observed: <what happened>
- Evidence: <command, output, or steps>
- Location: <file:line, when known>

## Non-blocking findings
One line each.

## Not verified
What you could not check and why. Never leave this implicit.

Boundaries

You can run anything. You cannot change anything except this report. Do not route a fix through another tool, and never ask another agent to apply one for you: your value is that you did not write the code. A finding you fix is a finding nobody reviews.

© Inebrio, AGPL-3.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/validation-protocol of Inebrio/Routerly.

Open the folder on GitHubat commit bcf58f1

Compare with similar skills

Validation Protocol 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.

Validation Protocol compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Validation Protocol this skillInebrio/Routerly100—~628Automated safety check: PassAGPL-3.0
User Storiesphuryn/pm-skills27k—~748Automated safety check: PassMIT
Job Storiesphuryn/pm-skills27k—~743Automated safety check: PassMIT
Create StoriesDonchitos/Claude-Code-Game-Studios26k—~7.2kAutomated safety check: PassMIT
Story ReadinessDonchitos/Claude-Code-Game-Studios26k—~6.9kAutomated safety check: PassMIT
User Story Writerdeanpeters/Product-Manager-Skills7.2k2 repos~2.9kAutomated safety check: PassCustom licence

Similar skills

  • User Stories

    phuryn/pm-skills

    Create user stories following the 3 C's (Card, Conversation, Confirmation) and INVEST criteria with descriptions, design links, and acceptance criteria.

    27k GitHub stars~748 tokensUpdated 22 days ago
    Product & Project ManagementAuto-check passed

  • Job Stories

    phuryn/pm-skills

    Turns a feature into job stories in the When, I want to, so I can format, each with six to eight acceptance criteria tied to the user's situation and outcome.

    27k GitHub stars~743 tokensUpdated 22 days ago
    Product & Project ManagementAuto-check passed

  • Create Stories

    Donchitos/Claude-Code-Game-Studios

    Break one epic into implementable stories embedding TR-ID, ADR guidance, acceptance criteria.

    26k GitHub stars~7.2k tokensUpdated 8 days ago
    Product & Project ManagementAuto-check passed

  • Story Readiness

    Donchitos/Claude-Code-Game-Studios

    Is a story implementation-ready?. An agent skill from Donchitos/Claude-Code-Game-Studios.

    26k GitHub stars~6.9k tokensUpdated 8 days ago
    Product & Project ManagementAuto-check passed

  • User Story Writer

    deanpeters/Product-Manager-Skills

    Writes user stories in Mike Cohn's format with Gherkin acceptance criteria, turning user needs into development-ready work with testable conditions.

    7.2k GitHub starsUsed in 2 repos~2.9k tokens
    Product & Project ManagementAuto-check passed

  • Stories

    sanity-io/sanity

    Official

    Invoke FIRST, before creating, editing, or deleting components, stories, styles, CSS, themes, colors, or design tokens — anything that changes how the UI looks, no exceptions.

    6.4k GitHub stars~621 tokensUpdated today
    Frontend & DesignAuto-check passed

More from Inebrio/Routerly

All 17 skills in this repo

  • Docs Conventions

    Inebrio/Routerly

    Where documentation lives in this repository, how a page is structured, and what a change owes the docs.

    100 GitHub stars~624 tokensUpdated yesterday
    Auto-check passed

  • Feature Lifecycle

    Inebrio/Routerly

    Run a Tier 1 or Tier 2 feature end to end — feature level, story level, parallelism, integration, and retrospective.

    100 GitHub stars~3k tokensUpdated yesterday
    Auto-check passed

  • Story Lifecycle

    Inebrio/Routerly

    Run one user story end to end in its own worktree, from claim to merge.

    100 GitHub stars~905 tokensUpdated yesterday
    Auto-check passed

  • Test Conventions

    Inebrio/Routerly

    Where tests live in this repository, how to run them, and what a story owes in coverage.

    100 GitHub stars~467 tokensUpdated yesterday
    Auto-check passed

  • Analysis Format

    Inebrio/Routerly

    Shape of a feature analysis document (00-analysis.md). An agent skill from Inebrio/Routerly.

    100 GitHub stars~472 tokensUpdated yesterday
    Auto-check passed

  • Blueprint Format

    Inebrio/Routerly

    Shape of a story blueprint, the technical plan an orchestrator executes.

    100 GitHub stars~581 tokensUpdated yesterday
    Auto-check passed

Questions about Validation Protocol

What does Validation Protocol do?

How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking. Validation Protocol is an agent skill from Inebrio/Routerly. How to validate a story against its criteria and write the report, including what counts as evidence and what counts as blocking.

When should I use Validation Protocol?

Validation Protocol fits situations like: verifying implemented work.

How do I install Validation Protocol in Claude Code?

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

How do I install Validation Protocol in Codex?

Run `npx skills add Inebrio/Routerly --skill validation-protocol -a codex`. Or copy the skill folder (.agents/skills/validation-protocol in Inebrio/Routerly) into .agents/skills/validation-protocol in your project. Codex loads it when a task matches its description.

Can I use Validation Protocol 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 Inebrio/Routerly --skill validation-protocol -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/validation-protocol, .gemini/skills/validation-protocol, .github/skills/validation-protocol and .opencode/skills/validation-protocol in your project.

What does Validation Protocol need to run?

SKILL.md names no scripts, command-line tools or credentials: Validation Protocol is instructions for the agent only.

Does Validation Protocol 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 Validation Protocol 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 Validation Protocol use?

Validation Protocol is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Validation Protocol use?

About 628 tokens (SKILL.md is roughly 2.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Validation Protocol?

Skills that share tags, products or a category with Validation Protocol: User Stories (phuryn/pm-skills, 27k stars), Job Stories (phuryn/pm-skills, 27k stars), Create Stories (Donchitos/Claude-Code-Game-Studios, 26k stars) and Story Readiness (Donchitos/Claude-Code-Game-Studios, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Validation Protocol?

Inebrio (a GitHub organization) maintains it in Inebrio/Routerly, which has 100 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on October 6, 2026.

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