Agent skill

Sync Vision

by udecode in udecode/kitcn

Incrementally audit kitcn doctrine drift since the recorded baseline, classify it, update VISION.md and local planning owners, then advance the baseline only after proof.

Apache-2.0Auto-check passedProduct & Project Management

Install Sync Vision

skills CLI
$ npx skills add udecode/kitcn --skill sync-vision -a claude-code

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

GitHub CLI
$ gh skill install udecode/kitcn sync-vision --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/udecode/kitcn.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/sync-vision .claude/skills/sync-vision && 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
sync-vision
GitHub stars
450
Token cost
~1k tokens
SKILL.md length
441 words
Files
1
Skills in repo
33
Repo updated
First seen
Licence
Apache-2.0

At a glance

Incrementally audit kitcn doctrine drift since the recorded baseline, classify it, update VISION.md and local planning owners, then advance the baseline only after proof.

  • Works in 10 steps: Read baseline status and preview… → Read VISION.md, docs/README.md, and each… → Build a classification table with… → …
  • Product & Project Management work in your project
  • SKILL.md covers Autogoal Dependency, State, Commands and Input Scope, plus 4 more sections
  • Calls node

What it does

Sync Vision is an agent skill from udecode/kitcn. Incrementally audit kitcn doctrine drift since the recorded baseline, classify it, update VISION.md and local planning owners, then advance the baseline only after proof.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Product & Project Management. The repository describes itself as: Convex + Better Auth + tRPC + Drizzle + TanStack Query + shadcn. The licence is Apache-2.0.

When your agent uses it

  • Product & Project Management work in your project

Example prompts

  • “/sync-vision”

Workflow steps

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

  1. Read baseline status and preview candidates.
  2. Read VISION.md, docs/README.md, and each candidate's actual owner.
  3. Build a classification table with evidence and proposed owner.
  4. Resolve contradictions and duplicate doctrine.
  5. Update the smallest canonical owners. Keep implementation detail out of
  6. Regenerate agent mirrors when .agents sources changed.
  7. Run helper syntax/status checks, exact-term audits, and relevant repository
  8. Run agent-native-reviewer, then autoreview.
  9. Record the reviewed head and note in status.json only after all applicable
  10. Rerun --status; it must show the expected baseline and no unexplained

What it can do on your machine

Read from SKILL.md and the folder at commit c6010f5. 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:

    • node

    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

Sync Vision loads about 1k tokens when it runs. Until then it costs about 46 tokens; SKILL.md has 441 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~46
When it runs · the whole SKILL.md, loaded when a task matches
~1k

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 udecode/kitcn at commit c6010f5, republished under its Apache-2.0 licence (© udecode). 441 words, ~1,023 tokens.

Download SKILL.mdSave it as .claude/skills/sync-vision/SKILL.md (or your agent's skills folder).
name
sync-vision
description
Incrementally audit kitcn doctrine drift since the recorded baseline, classify it, update VISION.md and local planning owners, then advance the baseline only after proof.
argument-hint
[status|preview|sync|advance]

Sync Vision

sync-vision turns repository changes into an explicit doctrine-drift audit. It does not rewrite vision from commit messages.

Autogoal Dependency

Every sync or advance run is durable work. Create or resume a goal from the sync-vision template with the agent-native pack before editing.

status and preview are read-only and may run without a goal.

State

The committed baseline lives at:

text
docs/sync/vision/status.json

It records the last reviewed commit, review time, optional note, and the files whose conclusions were advanced. The baseline means “reviewed for doctrine,” not “all changes were copied into VISION.md.”

Commands

bash
node .agents/rules/sync-vision/scripts/collect-vision-diff.mjs --status
node .agents/rules/sync-vision/scripts/collect-vision-diff.mjs --preview
node .agents/rules/sync-vision/scripts/collect-vision-diff.mjs --since <sha>
  • status: show baseline and candidate count.
  • preview: print the candidate file/keyword evidence since baseline.
  • sync: inspect candidates, update owners, validate, and advance state.
  • advance: advance without doctrine edits only after recording why every candidate is already represented, implementation-only, or intentionally rejected.

Input Scope

The collector searches source-owned doctrine and planning surfaces:

  • VISION.md, .agents/AGENTS.md, and .agents/rules/**;
  • docs/README.md, plans, PRDs, milestones, ADRs, analysis, brainstorms, research, solutions, and sync records;
  • root Markdown/MDX/MDC sources.

Generated skill mirrors, build output, fixtures, temp apps, dependencies, and the current generated sync report are excluded. Source changes may still require inspection even when their text does not contain a keyword.

Classification

Classify every candidate:

ClassOwner/action
durable doctrineupdate VISION.md
planning mapupdate PRD/milestone/docs map
architecture decisionupdate ADR/analysis and link from vision if durable
repository workflowupdate .agents source and regenerate
current implementation detailkeep in source/docs; no vision edit
superseded/rejectedrecord reason; no vision edit
contradictionstop and resolve before advancing

Relevant kitcn topics include public API, cRPC/ORM, Convex import graphs, plugins, auth, CLI/DX, scaffolds, fixtures, docs, compatibility, release, proof, and agent workflow.

Show full SKILL.md (172 more words)Show less

Sync Workflow

  1. Read baseline status and preview candidates.
  2. Read VISION.md, docs/README.md, and each candidate's actual owner.
  3. Build a classification table with evidence and proposed owner.
  4. Resolve contradictions and duplicate doctrine.
  5. Update the smallest canonical owners. Keep implementation detail out of VISION.md.
  6. Regenerate agent mirrors when .agents sources changed.
  7. Run helper syntax/status checks, exact-term audits, and relevant repository checks.
  8. Run agent-native-reviewer, then autoreview.
  9. Record the reviewed head and note in status.json only after all applicable gates pass.
  10. Rerun --status; it must show the expected baseline and no unexplained candidate drift.

Baseline Advancement

Never advance merely to silence the collector. The goal plan must contain:

  • old and new commit ids;
  • candidate inventory and classification;
  • changed owners or no-change reasons;
  • contradiction resolution;
  • validation and review receipts.

If the working tree contains relevant uncommitted doctrine changes, include them in the audit and do not pretend a commit-only baseline represents them.

Final Handoff

Report updated doctrine owners, intentionally unchanged candidates, exact baseline, validation, and any open decision.

© udecode, 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

Just SKILL.md in .agents/skills/sync-vision of udecode/kitcn.

Open the folder on GitHubat commit c6010f5

Compare with similar skills

Sync Vision 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.

Sync Vision compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Sync Vision this skilludecode/kitcn450—~1kAutomated safety check: PassApache-2.0
User Story Writerdeanpeters/Product-Manager-Skills7.2k2 repos~2.9kAutomated safety check: PassCustom licence
Game Changing FeaturesopenstatusHQ/data-table-filters2.3k3 repos~2.1kAutomated safety check: PassMIT
CCPM Project Managementautomazeio/ccpm8.4k—~1.1kAutomated safety check: PassMIT
Convex Create Componentspokvulcan/poker-planning1148 repos~2.6kAutomated safety check: PassMIT
Self Improving Agentfarm-fe/farm5.6k2 repos~3.3kAutomated safety check: NotesMIT

Similar skills

  • 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
  • Game Changing Features

    openstatusHQ/data-table-filters

    Find 10x product opportunities and high-leverage improvements.

    2.3k GitHub starsUsed in 3 repos~2.1k tokens
    Product & Project ManagementAuto-check passed
  • Runs a spec-driven workflow from PRD to epic to GitHub issues to parallel agents, with status, standup and blocked-work reports from bundled scripts.

    8.4k GitHub stars~1.1k tokensUpdated 6 mo ago
    Product & Project ManagementAuto-check passed
  • Convex Create Component

    spokvulcan/poker-planning

    Builds reusable Convex components with isolated tables and app-facing APIs.

    114 GitHub starsUsed in 8 repos~2.6k tokens
    Product & Project ManagementAuto-check passed
  • A universal self-improving agent that learns from ALL skill experiences.

    5.6k GitHub starsUsed in 2 repos~3.3k tokens
    Product & Project ManagementAuto-check: notes
  • Builds a weekly engineering retrospective from git history: commit counts, per-person contributions, work patterns and code quality numbers over a chosen window.

    136k GitHub stars~2.4k tokensUpdated today
    Product & Project ManagementAuto-check passed

More from udecode/kitcn

All 33 skills in this repo
  • Walkthrough

    udecode/kitcn

    Create a short annotated visual walkthrough from real final-state screenshots or rendered artifacts.

    450 GitHub stars~1.6k tokensUpdated 6 days ago
    Auto-check passed
  • Avoid Feature Creep

    udecode/kitcn

    Prevent feature creep when building software, apps, and AI-powered products.

    450 GitHub stars~2.7k tokensUpdated 6 days ago
    Auto-check passed
  • Changeset Resolve

    udecode/kitcn

    Repair an unreleased .changeset/.md file so it matches the real branch delta against main.

    450 GitHub stars~922 tokensUpdated 6 days ago
    Auto-check passed
  • Audit newer Convex npm releases against kitcn. An agent skill from udecode/kitcn.

    450 GitHub stars~1.8k tokensUpdated 6 days ago
    Auto-check passed
  • Jotai X

    udecode/kitcn

    A skill your agent uses when working with Jotai X stores (createAtomStore), accessing state in components or callbacks, persisting state to cookies or localStorage

    450 GitHub stars~3.7k tokensUpdated 6 days ago
    Auto-check passed
  • Linear Backlog

    udecode/kitcn

    Run a scoped Linear backlog autonomously as a sequence of maximal safe parallel batches by composing orchestrator, autogoal, and task.

    450 GitHub stars~3.1k tokensUpdated 6 days ago
    Auto-check passed

Questions about Sync Vision

What does Sync Vision do?

Incrementally audit kitcn doctrine drift since the recorded baseline, classify it, update VISION.md and local planning owners, then advance the baseline only after proof. Sync Vision is an agent skill from udecode/kitcn.md and local planning owners, then advance the baseline only after proof.

When should I use Sync Vision?

Sync Vision fits situations like: product & Project Management work in your project.

How do I install Sync Vision in Claude Code?

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

How do I install Sync Vision in Codex?

Run `npx skills add udecode/kitcn --skill sync-vision -a codex`. Or copy the skill folder (.agents/skills/sync-vision in udecode/kitcn) into .agents/skills/sync-vision in your project. Codex loads it when a task matches its description.

Can I use Sync Vision 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 udecode/kitcn --skill sync-vision -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sync-vision, .gemini/skills/sync-vision, .github/skills/sync-vision and .opencode/skills/sync-vision in your project.

What does Sync Vision need to run?

Going by SKILL.md and its folder, Sync Vision needs the command-line tools its instructions call (node).

Does Sync Vision 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 Sync Vision 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 Sync Vision use?

Sync Vision 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 Sync Vision use?

About 1k tokens (SKILL.md is roughly 4.1k 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 Sync Vision?

Skills that share tags, products or a category with Sync Vision: User Story Writer (deanpeters/Product-Manager-Skills, 7.2k stars), Game Changing Features (openstatusHQ/data-table-filters, 2.3k stars), CCPM Project Management (automazeio/ccpm, 8.4k stars) and Convex Create Component (spokvulcan/poker-planning, 114 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sync Vision?

udecode (a GitHub organization) maintains it in udecode/kitcn, which has 450 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 1, 2026.

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