New: 98,000+ 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

Ak Dev Sync Skills From Branch

by yaalalabs in yaalalabs/agent-kernel

Sync Agent Kernel skills from branch changes before a feature or bugfix is merged.

Apache-2.0Auto-check passedAI & LLM Engineering

Install Ak Dev Sync Skills From Branch

skills CLI
$ npx skills add yaalalabs/agent-kernel --skill ak-dev-sync-skills-from-branch -a claude-code

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

GitHub CLI
$ gh skill install yaalalabs/agent-kernel ak-dev-sync-skills-from-branch --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/yaalalabs/agent-kernel.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/ak-dev-sync-skills-from-branch .claude/skills/ak-dev-sync-skills-from-branch && 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
ak-dev-sync-skills-from-branch
GitHub stars
192
Token cost
~2.2k tokens
SKILL.md length
1,147 words
Files
1
Skills in repo
23
Repo updated
First seen
Licence
Apache-2.0

At a glance

Sync Agent Kernel skills from branch changes before a feature or bugfix is merged.

  • Works in 8 steps: Determine the Comparison Base → Read the Branch Delta → Convert Code Changes Into Skill Impact → …
  • Implementation is ready and you need to inspect new commits plus uncommitted changes
  • SKILL.md covers Goal, When to Use This Skill, Step 1: Determine the… and Step 2: Read the Branch Delta, plus 9 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Ak Dev Sync Skills From Branch is an agent skill from yaalalabs/agent-kernel. Sync Agent Kernel skills from branch changes before a feature or bugfix is merged. Use this skill when implementation is ready and you need to inspect new commits plus uncommitted changes, then update developer skills under .agents and user skills under ak-py/src/agentkernel/skills to match the actual capability set.

Its SKILL.md is about 2.2k 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 AI & LLM Engineering. The repository describes itself as: The Operating System for Scalable Enterprise AI Agents - Run, orchestrate, and deploy Compliant Enterprise AI Agents at scale across frameworks, without lock-in, rewrites or… The licence is Apache-2.0.

When your agent uses it

  • Implementation is ready and you need to inspect new commits plus uncommitted changes
  • Then update developer skills under .agents and user skills under ak-py/src/agentkernel/skills to match the actual capability set

Example prompts

  • “/ak-dev-sync-skills-from-branch”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Determine the Comparison Base
  2. Read the Branch Delta
  3. Convert Code Changes Into Skill Impact
  4. Decide Whether to Add, Update, or Remove Skills
  5. Update Both Skill Trees Together
  6. Required Files to Consider
  7. Skill Authoring Rules
  8. Validation Checklist

What it can do on your machine

Read from SKILL.md and the folder at commit 97fa8d9. 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.

    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

Ak Dev Sync Skills From Branch loads about 2.2k tokens when it runs. Until then it costs about 87 tokens; SKILL.md has 1,147 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~87
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 yaalalabs/agent-kernel at commit 97fa8d9, republished under its Apache-2.0 licence (© yaalalabs). 1,147 words, ~2,189 tokens.

Download SKILL.mdSave it as .claude/skills/ak-dev-sync-skills-from-branch/SKILL.md (or your agent's skills folder).
name
ak-dev-sync-skills-from-branch
description
Sync Agent Kernel skills from branch changes before a feature or bugfix is merged. Use this skill when implementation is ready and you need to inspect new commits plus uncommitted changes, then update developer skills under .agents and user skills under ak-py/src/agentkernel/skills to match the actual capability set.
license
Apache-2.0
metadata.author
yaalalabs
metadata.category
developer

Sync Skills From Branch Changes

Use this skill when a feature branch or bugfix branch is functionally ready and you need to align Agent Kernel's skills with what actually changed.

This skill is for skill maintenance driven by code diff, not for implementing the feature itself.

Goal

Read the branch delta, infer what contributor-facing and user-facing capabilities changed, then:

  • update existing developer skills under .agents/skills/
  • add new developer skills if a new reusable contributor workflow now exists
  • update existing user skills under ak-py/src/agentkernel/skills/
  • add new user skills if a new reusable end-user workflow now exists
  • remove obsolete skills only when the codebase no longer supports that capability and no replacement path remains
  • update evals and skill catalogs/docs so the inventory remains consistent

When to Use This Skill

Use this skill when all of the following are true:

  1. The developer is on a feature or bugfix branch.
  2. The implementation is already done or nearly done.
  3. There are new commits on the branch and/or uncommitted local changes.
  4. The change may affect capabilities, workflows, supported integrations, deployment paths, contributor workflows, or examples.

Do not use this skill as the first step of a feature. Use it near the end, before merge or PR finalization.

Step 1: Determine the Comparison Base

Find the correct baseline branch first.

Preferred order:

  1. The PR target branch if it is known.
  2. The upstream tracking branch for the current branch.
  3. origin/develop.
  4. develop.

For this repository, prefer origin/develop or develop as the default base branch unless the PR target or upstream tracking branch says otherwise.

Use Git to identify the merge base between the current branch and that baseline.

Minimum evidence to gather:

  • current branch name
  • merge base commit
  • commits since merge base
  • staged changes
  • unstaged changes

If the baseline is ambiguous, state the assumption you are using and continue.

Step 2: Read the Branch Delta

Inspect both committed and uncommitted work.

Required diff inputs:

  1. Committed changes on the branch
    • commits since merge base
    • file list and diff summary
  2. Current local changes
    • staged diff
    • unstaged diff

Pay special attention to changes in:

  • ak-py/src/agentkernel/
  • .agents/skills/
  • ak-py/src/agentkernel/skills/
  • examples/
  • ak-deployment/
  • docs/
  • tests and evals

Step 3: Convert Code Changes Into Skill Impact

Classify the branch delta into these buckets:

  1. New contributor workflow

    • Example: a new extension surface, new adapter type, new storage/provider/integration pattern.
    • Result: add or expand a developer skill under .agents/skills/.

  2. New end-user workflow

    • Example: a new deploy mode, capability, integration, framework, or testing path that users can adopt in their own projects.
    • Result: add or expand a user skill under ak-py/src/agentkernel/skills/.

  3. Behavior drift in an existing skill

    • Example: configuration keys changed, module inputs changed, supported backends changed, examples changed, packaging changed.
    • Result: patch the existing skill instead of creating a new one.

  4. Capability removal or consolidation

    • Example: a path is deprecated or replaced by another workflow.
    • Result: remove or merge the obsolete skill only if the replacement is clear and documented.

Step 4: Decide Whether to Add, Update, or Remove Skills

Apply these rules.

Add a New Developer Skill When
  • the branch introduces a repeatable contributor task
  • that task spans multiple files or subsystems
  • contributors would otherwise need architecture/context not obvious from local code
  • the workflow is likely to be reused for future features
Update an Existing Developer Skill When
  • the branch extends or changes an already-covered contributor workflow
  • the new work fits naturally into an existing skill's scope
Add a New User Skill When
  • the branch creates a new reusable user-facing workflow
  • that workflow cannot be explained as a small subsection inside an existing user skill
Update an Existing User Skill When
  • the branch changes supported options, code templates, configuration, examples, or eval expectations
  • the workflow already belongs to one of the existing user skills (ak-init, ak-build, ak-add-capabilities, ak-add-integration, ak-cloud-deploy, ak-test)
Remove a Skill When
  • the capability is no longer supported
  • no documented example or implementation path remains
  • a replacement skill or replacement workflow is identified in the same edit

Do not remove a skill just because the current branch did not touch that area.

Show full SKILL.md (468 more words)Show less

Step 5: Update Both Skill Trees Together

Whenever branch changes justify skill work, inspect both locations:

  • developer skills: .agents/skills/
  • user skills: ak-py/src/agentkernel/skills/

Do not stop after updating only one side if the branch change clearly affects both contributor and end-user workflows.

Examples:

  • A new pluggable subsystem may need:
    • a developer skill explaining how contributors add new implementations
    • a user skill update explaining how users enable or consume that subsystem
  • A new integration may need:
    • a developer skill update for extending integrations
    • a user skill update for enabling the new integration

Step 6: Required Files to Consider

After deciding the skill impact, update the relevant files from this list.

Potential developer-skill files:

  • .agents/skills/*/SKILL.md

Potential user-skill files:

  • ak-py/src/agentkernel/skills/*/SKILL.md
  • ak-py/src/agentkernel/skills/*/evals/evals.json

Required inventory/docs files when the skill set changes:

  • docs/docs/agent-skills.md (developer and user skill tables and counts). The landing page no longer lists individual skills (its hero shows only the install commands), so a bundled skill change needs no edit under docs/src/

Also update other contributor docs if they explicitly enumerate developer skills.

Step 7: Skill Authoring Rules

When writing or updating skills:

  • prefer extending an existing skill over creating overlapping skills
  • keep scope narrow and reusable
  • ground instructions in real code paths, examples, and current module inputs
  • use current versions and current configuration keys
  • include gotchas only when they are real and recurring
  • keep examples aligned with live examples in examples/ or ak-deployment/
  • update evals when user skills change materially

Step 8: Validation Checklist

Before finishing, validate the skill sync work.

Minimum validation:

  1. Confirm the diff-backed rationale for every added/updated/removed skill.
  2. Check that user-skill eval JSON still parses.
  3. Check edited markdown/JSON files for diagnostics.
  4. Verify skill inventory counts and tables in docs/specs match the actual .agents/skills/ directory.
  5. Search for stale capability names, old counts, or old version references introduced by the branch delta.

Output Expectations

When using this skill, the coding agent should produce:

  1. A short branch-impact summary based on commits plus uncommitted changes.
  2. A decision summary for each affected skill area:
    • update existing skill
    • add new skill
    • remove obsolete skill
    • no skill change needed
  3. The actual file edits.
  4. A validation summary.

Common Pitfalls

  • Looking only at committed changes and ignoring staged/unstaged work.
  • Updating user skills but forgetting developer skills, or the reverse.
  • Adding a new skill when an existing skill should simply be expanded.
  • Forgetting eval updates after changing a user skill.
  • Forgetting docs/spec inventory counts after adding or removing a developer skill.
  • Describing a capability from memory instead of checking the live example/module/test files.

Quick Heuristic

Use this branch-sync heuristic:

  • Code shape changed, workflow same → update an existing skill.
  • New reusable workflow appeared → add a new skill.
  • Workflow disappeared or was fully replaced → remove or merge a skill.
  • Only one-off implementation details changed → no new skill; at most patch wording/examples.

© yaalalabs, 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/ak-dev-sync-skills-from-branch of yaalalabs/agent-kernel.

Open the folder on GitHubat commit 97fa8d9

Compare with similar skills

Ak Dev Sync Skills From Branch 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.

Ak Dev Sync Skills From Branch compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Ak Dev Sync Skills From Branch this skillyaalalabs/agent-kernel192—~2.2kAutomated safety check: PassApache-2.0
Safactory WorkflowsAI45Lab/SAfactory236—~1.8kAutomated safety check: PassNone
Langfuselangfuse/skills301—~2.1kAutomated safety check: NotesMIT
Evalagentevals-dev/agentevals163—~904Automated safety check: PassApache-2.0
Wa Guardrailsaws-samples/sample-well-architected-skills-and-steering275—~2.8kAutomated safety check: PassMIT-0
Yolo Detection 2026 OpenvinoSharpAI/DeepCamera3.1k—~1.3kAutomated safety check: PassMIT

Similar skills

  • Safactory Workflows

    AI45Lab/SAfactory

    Integrate a benchmark or custom environment into SAfactory using fixed adapter templates and local contract tests, optionally run Docker/RJob evaluation, or prepare GRPO/RL training.

    236 GitHub stars~1.8k tokensUpdated 17 days ago
    AI & LLM EngineeringAuto-check passed

  • Langfuse

    langfuse/skills

    Interact with Langfuse and access its documentation: tracing, monitoring, creating datasets, running experiments, and evaluating AI applications.

    301 GitHub stars~2.1k tokensUpdated 10 days ago
    AI & LLM EngineeringAuto-check: notes

  • Eval

    agentevals-dev/agentevals

    Evaluate and score agent behavior against a golden reference.

    163 GitHub stars~904 tokensUpdated yesterday
    AI & LLM EngineeringAuto-check passed

  • Wa Guardrails

    aws-samples/sample-well-architected-skills-and-steering

    Official

    Generate preventive Well-Architected guardrails — AWS Config rules, Service Control Policies, permission boundaries, CloudWatch alarms, and IaC policy checks (CDK Aspects, cfn-guard, OPA/Sentinel) —…

    275 GitHub stars~2.8k tokensUpdated 5 days ago
    AI & LLM EngineeringAuto-check passed

  • Yolo Detection 2026 Openvino

    SharpAI/DeepCamera

    OpenVINO — real-time object detection via Docker (NCS2, Intel GPU, CPU)

    3.1k GitHub stars~1.3k tokensUpdated 24 days ago
    AI & LLM EngineeringAuto-check passed

  • Langsmith Observability

    Orchestra-Research/AI-Research-SKILLs

    LLM observability platform for tracing, evaluation, and monitoring.

    13k GitHub starsUsed in 2 repos~2.4k tokens
    AI & LLM EngineeringAuto-check passed

More from yaalalabs/agent-kernel

All 23 skills in this repo

  • Ak Dev Code Quality

    yaalalabs/agent-kernel

    Code quality standards, formatting, Python style rules (classes over script-style functions, configuration-field rules), commit conventions, and PR workflow for Agent Kernel development.

    192 GitHub stars~2.5k tokensUpdated yesterday
    Auto-check passed

  • Ak Dev New Evaluator Provider

    yaalalabs/agent-kernel

    Step-by-step guide for adding a new built-in test evaluator provider to Agent Kernel (beyond DeepEval, Opik and JEV).

    192 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed

  • Ak Dev New Guardrail Provider

    yaalalabs/agent-kernel

    Step-by-step guide for adding a new guardrail provider to Agent Kernel.

    192 GitHub stars~3.5k tokensUpdated yesterday
    Auto-check passed

  • Ak Dev New Knowledgebase Integration

    yaalalabs/agent-kernel

    Step-by-step guide for adding a new knowledge base backend to Agent Kernel.

    192 GitHub stars~5.1k tokensUpdated yesterday
    Auto-check passed

  • Ak Dev New Messaging Integration

    yaalalabs/agent-kernel

    Step-by-step guide for adding a new messaging platform integration to Agent Kernel.

    192 GitHub stars~4.6k tokensUpdated yesterday
    Auto-check passed

  • Ak Dev New Multimodal Storage

    yaalalabs/agent-kernel

    Step-by-step guide for adding a new multimodal attachment storage backend to Agent Kernel.

    192 GitHub stars~4.3k tokensUpdated yesterday
    Auto-check passed

Categories

Questions about Ak Dev Sync Skills From Branch

What does Ak Dev Sync Skills From Branch do?

Sync Agent Kernel skills from branch changes before a feature or bugfix is merged. Ak Dev Sync Skills From Branch is an agent skill from yaalalabs/agent-kernel. Sync Agent Kernel skills from branch changes before a feature or bugfix is merged.

When should I use Ak Dev Sync Skills From Branch?

Ak Dev Sync Skills From Branch fits situations like: implementation is ready and you need to inspect new commits plus uncommitted changes; then update developer skills under .agents and user skills under ak-py/src/agentkernel/skills to match the actual capability set.

How do I install Ak Dev Sync Skills From Branch in Claude Code?

Run `npx skills add yaalalabs/agent-kernel --skill ak-dev-sync-skills-from-branch -a claude-code`. Or copy the skill folder (.agents/skills/ak-dev-sync-skills-from-branch in yaalalabs/agent-kernel) into .claude/skills/ak-dev-sync-skills-from-branch in your project. Claude Code loads it when a task matches its description.

How do I install Ak Dev Sync Skills From Branch in Codex?

Run `npx skills add yaalalabs/agent-kernel --skill ak-dev-sync-skills-from-branch -a codex`. Or copy the skill folder (.agents/skills/ak-dev-sync-skills-from-branch in yaalalabs/agent-kernel) into .agents/skills/ak-dev-sync-skills-from-branch in your project. Codex loads it when a task matches its description.

Can I use Ak Dev Sync Skills From Branch 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 yaalalabs/agent-kernel --skill ak-dev-sync-skills-from-branch -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ak-dev-sync-skills-from-branch, .gemini/skills/ak-dev-sync-skills-from-branch, .github/skills/ak-dev-sync-skills-from-branch and .opencode/skills/ak-dev-sync-skills-from-branch in your project.

What does Ak Dev Sync Skills From Branch need to run?

SKILL.md names no scripts, command-line tools or credentials: Ak Dev Sync Skills From Branch is instructions for the agent only.

Does Ak Dev Sync Skills From Branch 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 Ak Dev Sync Skills From Branch 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 Ak Dev Sync Skills From Branch use?

Ak Dev Sync Skills From Branch is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Ak Dev Sync Skills From Branch use?

About 2.2k tokens (SKILL.md is roughly 8.8k 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 Ak Dev Sync Skills From Branch?

Skills that share tags, products or a category with Ak Dev Sync Skills From Branch: Safactory Workflows (AI45Lab/SAfactory, 236 stars), Langfuse (langfuse/skills, 301 stars), Eval (agentevals-dev/agentevals, 163 stars) and Wa Guardrails (aws-samples/sample-well-architected-skills-and-steering, 275 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Ak Dev Sync Skills From Branch?

yaalalabs (a GitHub organization) maintains it in yaalalabs/agent-kernel, which has 192 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 9, 2026.

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