universal-skill-creator
Create, adapt, validate, and optimize reusable agent skills across agentic platforms.
- License 许可
- MIT
- 所属仓库
- domehahn/skcr
- 最近更新
- 2026-09-11
- Stars
- ★ 0
- Forks
- 0
01 前言 Front Matter
- name
- universal-skill-creator
- since
- 2026-06-10
- authors
- [ "platform-engineering" ]
- version
- 1.2.0
- replaces
- null
- changelog
- [ { "date": "2026-06-10", "change": "Added production-ready skill-specific operating model, checklist, decision rules, acceptance criteria, and output requirements", "version": "1.2.0" }, { "date": "2026-06-10", "change": "Explicitly require applying the versioning schema while creating every new skill", "version": "1.1.1" }, { "date": "2026-06-10", "change": "Mandatory versioning schema for generated skills: full YAML frontmatter, stability, min_platform_version, changelog", "version": "1.1.0" }, { "date": "2025-01-01", "change": "Initial release", "version": "1.0.0" } ]
- stability
- stable
- supersedes
- []
- description
- Create, adapt, validate, and optimize reusable agent skills across agentic platforms.
- last_modified
- 2026-06-10
- deprecated_since
- null
- min_platform_version
- { "kiro": "unknown", "codex": "unknown", "junie": "unknown", "cursor": "unknown", "ollama": "unknown", "opencode": "unknown", "roo-code": "unknown", "windsurf": "unknown", "openhands": "unknown", "gemini-cli": "unknown", "gitlab-duo": "unknown", "claude-code": "unknown", "github-copilot": "unknown" }
02 资源文件 6
- 参考文档CHANGELOG.md190 B
- 许可证LICENSE214 B
- 参考文档README.md367 B
- 参考文档skill.yaml392 B
- 参考文档tests/README.md99 B
- 其他VERSION6 B
03 SKILL.md 正文
Universal Skill Creator
Purpose
Create, adapt, validate, and optimize reusable agent skills across agentic platforms.
When to use
Use this skill when the task matches the description above or when the central agent instructions route work to $universal-skill-creator.
Operating model
- Clarify the goal and constraints.
- Inspect the minimum relevant repository context.
- Produce a concise execution plan for non-trivial work.
- Execute with tools when implementation is requested.
- Validate the result with repository-native checks.
- Summarize changed files, validation results, and residual risks.
DevSecOps guardrails
- Do not read secrets,
.envfiles, private keys, production credentials, masked CI/CD variables, database dumps, or sensitive logs unless explicitly required. - Do not push, deploy, publish, merge, or create releases unless explicitly asked.
- Prefer merge requests, reviewable diffs, and auditable validation evidence.
- Prefer least privilege, minimal changes, and explicit rollback notes.
- Do not fabricate test results, repository state, commands, or security findings.
Skill-Specific Operating Model
- Clarify skill domain, target users, triggering conditions, supported platforms, and governance level before drafting.
- Design skills around repeatable decisions and concrete checks, not generic role descriptions.
- Apply the mandatory versioning schema before finalizing every new or updated skill.
Skill-Specific Checklist
- Metadata includes complete YAML frontmatter, SemVer, stability, authors, dates, platform map, and changelog.
- Content includes domain-specific operating model, checklist, decision rules, acceptance criteria, and output requirements.
- Routing, platform-copy behavior, governance, security review, and validation expectations are explicit.
Decision Rules
- Never create a new skill that only differs by name and description. Every generated skill must contain domain-specific checklists, decision rules, acceptance criteria, and output requirements.
- Do not invent platform minimum versions; use
unknownwhen not verified and document the production routing risk. - Bump the skill version when instructions, operating model, guardrails, or required outputs change materially.
Acceptance Criteria
- A generated skill can guide real work in its domain without placeholder text.
- Frontmatter changelog and body changelog agree on the latest version.
- Duplicate platform copies are synced from the canonical source or their divergence is documented.
Output Requirements
- Provide changed skill paths, canonical source used, version changes, and changelog entries.
- List schema and content-readiness validation performed.
- Call out unknown platform compatibility and required human review.
Mandatory versioning schema for new skills
Every skill created by this skill MUST apply this versioning schema. Do not create, scaffold, or finalize a new skill unless its SKILL.md includes a complete YAML frontmatter block and a ## Changelog body section.
Required YAML frontmatter
---
name: <skill-name>
description: <one-line description>
version: "0.1.0"
since: "2026-06-10"
last_modified: "YYYY-MM-DD"
authors:
- <team-or-person>
stability: experimental
min_platform_version:
codex: "unknown"
claude-code: "unknown"
github-copilot: "unknown"
gitlab-duo: "unknown"
opencode: "unknown"
openhands: "unknown"
cursor: "unknown"
roo-code: "unknown"
kiro: "unknown"
junie: "unknown"
gemini-cli: "unknown"
windsurf: "unknown"
ollama: "unknown"
deprecated_since:
replaces:
supersedes: []
changelog:
- version: "0.1.0"
date: "YYYY-MM-DD"
change: "Initial release"
---
Versioning rules
- Use SemVer without a leading
v(e.g.1.0.0,0.1.0,2.1.0-beta.1). - New skills start at
0.1.0if experimental or1.0.0if immediately stable. - Set
stability: experimentalfor skills that are still being validated. - Set
stability: stablefor skills that are ready for production use. - Set
stability: deprecatedand filldeprecated_sincewhen a skill is retired. - Set
sinceandlast_modifiedto the current date inYYYY-MM-DDformat. - Set
min_platform_versionfor every target platform supported by the repository. Use"unknown"if the minimum version is not known; do not omit configured platforms or invent versions. - Set
replacesif this skill directly succeeds a previously named skill. - Set
supersedesif this skill functionally replaces multiple older skills. - The
changelogin the frontmatter is machine-readable. Keep it in sync with the## Changelogbody section. - The most recent changelog entry always appears first.
Required body section
Every skill MUST also have a ## Changelog section in the markdown body:
## Changelog
### 0.1.0 - YYYY-MM-DD
- Initial release.
Add a new entry whenever the skill's instructions, operating model, or guardrails change materially.
Validation
Before finalising a new or updated skill, verify:
- YAML frontmatter is present and parseable.
namematches the skill directory name.versionis valid SemVer without a leadingv.sinceandlast_modifiedare inYYYY-MM-DDformat.stabilityis one ofexperimental,stable,deprecated.deprecated_sinceis set whenstability: deprecated.min_platform_versionis present and includes every configured target platform.changelogin frontmatter has at least one entry matchingversion.## Changelogsection exists in the body.- Frontmatter
versionmatches the most recent body changelog entry. - Skill-specific operating model, checklist, decision rules, acceptance criteria, and output requirements are present and domain-specific.
Changelog
1.2.0 - 2026-06-10
- Added production-ready skill-specific operating model, checklist, decision rules, acceptance criteria, and output requirements.
0.1.0 - YYYY-MM-DD
- Initial release.
Add a new entry whenever the skill's instructions, operating model, or guardrails change materially.
### Validation
Before finalising a new or updated skill, verify:
1. YAML frontmatter is present and parseable.
2. `name` matches the skill directory name.
3. `version` is valid SemVer without a leading `v`.
4. `since` and `last_modified` are in `YYYY-MM-DD` format.
5. `stability` is one of `experimental`, `stable`, `deprecated`.
6. `deprecated_since` is set when `stability: deprecated`.
7. `min_platform_version` is present and includes every configured target platform.
8. `changelog` in frontmatter has at least one entry matching `version`.
9. `## Changelog` section exists in the body.
10. Frontmatter `version` matches the most recent body changelog entry.
## Output
Provide:
- Actions taken
- Files changed or reviewed
- Validation performed
- Findings or risks
- Recommended next step
## Changelog
### 1.1.1 - 2026-06-10
- Made schema application an explicit required step in the skill creation workflow.
- Expanded the required frontmatter example to include all currently configured target platforms.
- Tightened validation so `min_platform_version` must cover every configured target platform.
### 1.1.0 - 2026-06-10
- Added mandatory versioning schema section for all newly created skills.
- Added explicit rules for `stability`, `since`, `last_modified`, `min_platform_version`, `replaces`, `supersedes`, and `changelog`.
- Added validation checklist to ensure generated skills are spec-compliant.
### 1.0.0 - 2025-01-01
- Initial release.
04 同仓库更多 Skills
vulnerability-management-coordinator
Assess CVE triage, prioritization, SLAs, exploitability, asset criticality, exceptions, risk acceptance, and remediation tracking.
verification-reviewer
Review diffs, validate acceptance criteria, inspect test results, and find missed requirements.
universal-skill-creator
Create, adapt, validate, and optimize reusable agent skills across agentic platforms.
threat-modeler
Identify assets, trust boundaries, abuse cases, attack paths, threats, and required security controls.
test-strategy-engineer
Design and generate unit, integration, regression, security, and end-to-end test strategies.
sre-reliability-reviewer
Assess SLOs, SLIs, error budgets, capacity, degradation, timeouts, retries, circuit breakers, load shedding, and operational risks.