Skill Lifecycle

OrganizationPopular

iflytek

skill-lifecycle

The authoritative skill lifecycle state model including container states, version states, review workflow states, visibility overlay, and governance actions. Ensures agents don't introduce invalid states or transitions.

Overview

Publisher	iflytek
Repository	`skillhub`
Skill name	`skill-lifecycle`
Stars	5.2K
Forks	841
Bundled files	Instructions only
License	Apache-2.0
Links	Skill source Repository Homepage

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by iflytek on GitHub. Read the source before you install it.

Installation

Install the Skill Lifecycle AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/iflytek/skillhub/tree/main/.agents/skills/skill-lifecycle
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/iflytek/skillhub.git /tmp/skillhub
mkdir -p .claude/skills
cp -r /tmp/skillhub/.agents/skills/skill-lifecycle .claude/skills/skill-lifecycle

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Skill Lifecycle in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Skill Lifecycle on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Skill Lifecycle is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Skill Lifecycle Skill

Trigger

Use this skill when:

Modifying skill publish, review, or unpublish flows
Adding or changing skill/version status fields
Working on search, detail pages, or listing pages that show skill state
Implementing governance actions (hide, yank, archive)
Adding new state transitions or permission checks

State Model

Skill Container States

Enum SkillStatus (domain/skill/SkillStatus.java):

Value	Meaning
`ACTIVE`	Skill is operational and can have versions published
`HIDDEN`	Skill hidden by platform governance (design doc says prefer boolean `hidden` flag instead)
`ARCHIVED`	Skill archived by owner/namespace admin, cannot publish new versions

Design-vs-code note: docs/14-skill-lifecycle.md specifies hidden should be a governance overlay (boolean flag) rather than a lifecycle enum state. The current code still defines SkillStatus.HIDDEN. New code should use the skill.hidden boolean field, not the enum value.

SkillVersion States

Enum SkillVersionStatus (domain/skill/SkillVersionStatus.java):

Value	Meaning
`DRAFT`	Non-public draft, can resubmit or delete
`SCANNING`	Undergoing security scan
`SCAN_FAILED`	Security scan failed
`UPLOADED`	Uploaded but not yet submitted for review (or withdrawn from review)
`PENDING_REVIEW`	Frozen pending reviewer action
`PUBLISHED`	Currently distributable
`REJECTED`	Review denied, retained
`YANKED`	Was published, withdrawn from distribution

ReviewTask States

Enum ReviewTaskStatus (domain/review/ReviewTaskStatus.java):

Value	Meaning
`PENDING`	Awaiting reviewer
`APPROVED`	Reviewer approved
`REJECTED`	Reviewer rejected

Visibility Model

Enum SkillVisibility (used in SkillPublishService):

Value	Publish Path
`PUBLIC`	Creates `PENDING_REVIEW` version, review task, security scan
`NAMESPACE_ONLY`	Same as PUBLIC but limited visibility scope
`PRIVATE`	Goes directly to `UPLOADED` status, no review task

SUPER_ADMIN role bypasses review — versions go directly to PUBLISHED.

Latest Version Pointer

Skill.latestVersionId is only the latest published pointer:

Can only point to a PUBLISHED version
May be null if no published version exists
latest tag auto-follows this pointer (read-only)
When yanking: recalculates to newest remaining PUBLISHED version, or null

Key Transitions

Action	From	To	Notes	Source
First upload (PUBLIC/NAMESPACE_ONLY)	—	`PENDING_REVIEW`	Review task created	`SkillPublishService`
First upload (SUPER_ADMIN)	—	`PUBLISHED`	Direct publish, `SkillPublishedEvent` emitted	`SkillPublishService`
First upload (PRIVATE)	—	`UPLOADED`	No review task, `latestVersionId` updated	`SkillPublishService`
Review approve	`PENDING_REVIEW`	`PUBLISHED`	Updates `latestVersionId`	Review workflow
Review reject	`PENDING_REVIEW`	`REJECTED`	Version retained	Review workflow
Withdraw review	`PENDING_REVIEW`	`UPLOADED`	Deletes pending `ReviewTask`	`SkillGovernanceService.withdrawPendingVersion`
Yank	`PUBLISHED`	`YANKED`	Recalculates `latestVersionId`	`SkillGovernanceService.yankVersion`
Hide	—	`hidden=true`	Independent overlay	`SkillGovernanceService.hideSkill`
Restore	—	`hidden=false`	Independent overlay	`SkillGovernanceService.unhideSkill`
Archive	`ACTIVE`	`ARCHIVED`	`SkillStatusChangedEvent` emitted	`SkillGovernanceService.archiveSkill`
Unarchive	`ARCHIVED`	`ACTIVE`	`SkillStatusChangedEvent` emitted	`SkillGovernanceService.unarchiveSkill`
New publish (existing pending)	`PENDING_REVIEW`	`UPLOADED`	Auto-withdraw + delete review task	`SkillPublishService`
Delete version	`DRAFT`/`REJECTED`/`SCAN_FAILED`/`UPLOADED`	—	Last version protected	`SkillGovernanceService.deleteVersion`

Yank Pointer Recalculation

When yanking the current latestVersionId (SkillGovernanceService):

Query all remaining PUBLISHED versions for the skill
Sort by publishedAt DESC, then createdAt DESC, then id DESC
Point latestVersionId to the top result, or null if none remain

Lifecycle Projection

Read models (detail, my-skills, favorites, search) use *QueryRepository patterns:

headlineVersion — Main display version for the page
publishedVersion — Latest published version
ownerPreviewVersion — Pending review version (visible to owner/namespace admin)
resolutionMode — PUBLISHED, OWNER_PREVIEW, or NONE

Public browsing, install, download, search only use publishedVersion.

Permission Boundaries

Action	Who
Withdraw review	Submitter only
Delete version	Owner or namespace admin, only `DRAFT`/`REJECTED`/`SCAN_FAILED`/`UPLOADED`
Archive/unarchive	Owner or namespace admin (`ADMIN` or `OWNER` role)
Hide/restore	Platform governance (no permission check in code)
Yank	Platform governance (no permission check in code)
Publish PUBLIC skill	Namespace member (or `SUPER_ADMIN`)
Publish PRIVATE skill	Namespace member (or `SUPER_ADMIN`)

Delete Version Constraints

SkillGovernanceService.deleteVersion enforces:

Only DRAFT, REJECTED, SCAN_FAILED, or UPLOADED versions can be deleted
Cannot delete the last remaining version of a skill
Deletes associated storage keys (individual files + bundle.zip)
Deletes associated security scan records
Updates latestVersionId if the deleted version was the pointer
Storage deletion happens after transaction commit with compensation recording

Domain Events

Event	When Emitted
`SkillStatusChangedEvent`	Archive or unarchive
`SkillPublishedEvent`	SUPER_ADMIN direct publish
`SkillVersionYankedEvent`	Yank action
`ReviewSubmittedEvent`	Create review task for PUBLIC/NAMESPACE_ONLY

Common Pitfalls

Setting SkillStatus.HIDDEN directly — use skill.setHidden(true) via SkillGovernanceService instead
Forgetting to recalculate latestVersionId after yank or version deletion
Not auto-withdrawing pending versions when publishing a new version
Missing the confirmWarnings two-step publish flow (warnings require explicit confirmation)
Assuming all publish flows create review tasks — PRIVATE visibility skips review

Frequently asked questions

What does the Skill Lifecycle AI skill do?

Why use Skill Lifecycle on TypingMind?

Because you install it once and use it with any model. Skill Lifecycle is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Skill Lifecycle in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/iflytek/skillhub/tree/main/.agents/skills/skill-lifecycle. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Skill Lifecycle?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Skill Lifecycle?

As many as you like. As long as a model supports skills, you can use Skill Lifecycle with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Skill Lifecycle AI skill free?

Yes. It is published on GitHub by iflytek under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Openclaw Test Performance

openclaw

OrganizationPopular

Benchmark, diagnose, and optimize OpenClaw test and plugin-suite runtime, import hotspots, CPU/RSS, heap growth, and slow coverage paths.

Openclaw Testing

Choose proportional OpenClaw tests and checks, diagnose failures, and route environment-sensitive or release proof to its owner.

Release Openclaw Ci

Run, watch, debug, and summarize OpenClaw full release CI, release checks, live provider gates, install/update proofs, and release-secret preflights.

Release Openclaw Mac

Run or recover OpenClaw macOS release signing, notarization, appcast, and asset promotion.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Skill Lifecycle Skill

Trigger

State Model

Skill Container States

SkillVersion States

ReviewTask States

Visibility Model

Latest Version Pointer

Key Transitions

Yank Pointer Recalculation

Lifecycle Projection

Permission Boundaries

Delete Version Constraints

Domain Events

Common Pitfalls

Frequently asked questions

Related AI Skills

Set up your own AI workspace now