skill-creator
Create or improve skills using the Claude Code skill standard.
Skill by lshtram
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/lshtram-skill-creator
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/skill-creator
What's inside
- Skill name
skill-creator- Description
- Create or improve skills using the Claude Code skill standard.
- License
- MIT
- Instructions
- 34 lines in SKILL.md · view on GitHub
Files (3)
- SKILL.md
- output-patterns.md · references/
- workflows.md · references/
SKILL.md (first lines)
# Role Oracle or Builder # Trigger - When asked to add or improve a skill. # Inputs - Skill intent and target agent role. - NSO standards in `.opencode/context/00_meta/`. - Claude Code skills docs and canonical skill-creator reference. # Outputs - New or updated `.opencode/skills/<skill-name>/SKILL.md`. - Optional `references/` files for extended guidance. # Steps 1. Capture the skill goal, trigger conditions, and expected outputs. 2. Choose a lowercase, hyphenated name (≤64 chars). 3. Draft YAML frontmatter with `name` and `description`. 4. Write concise sections for Role, Trigger, Inputs, Outputs, Steps. 5. Move bulky guidance into `references/` for progressive disclosure. 6. Validate: - Directory structure matches `.opencode/skills/<skill-name>/SKILL.md`. - Frontmatter contains `name` and `description`. - No flat `.opencode/skills/*.md` files remain. 7. Update documentation references if the skill list changes. # References - `.opencode/skills/skill-creator/references/workflows.md` - `.opencode/skills/skill-creator/references/output-patterns.md` - https://code.claude.com/docs/en/skills - https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md
From lshtram/nso, MIT.
More from lshtram/nso
- 0.408score
integration-verifier
lshtram
Verify integration tests and E2E scenarios, detect failures, and provide rollback options
SkillDFreshness: DClaude Code +9 - 0.406score
tdd
lshtram
Test-Driven Development enforcement with rationalization prevention, verification checklist, and delete-and-restart rule.
SkillDFreshness: DClaude Code +9 - 0.406score
router
lshtram
Intelligent intent detection and workflow routing for NSO.
SkillDFreshness: DClaude Code +9 - 0.404score
memory-update
lshtram
Force an on-demand update of NSO memory files with comprehensive context.
SkillDFreshness: DClaude Code +9 - 0.404score
verification-gate
lshtram
IDENTIFY→RUN→READ→VERIFY→CLAIM gate function with forbidden language detection and fresh evidence requirement.
SkillDFreshness: DClaude Code +9 - 0.404score
post-mortem
lshtram
Session analysis, pattern detection, and self-improvement orchestration for workflow closure.
SkillDFreshness: DClaude Code +9 - 0.404score
ui-design-system
lshtram
Comprehensive UI/UX design system skill — component generation, design tokens, accessibility, and responsive design.
SkillDFreshness: DClaude Code +9 - 0.404score
architectural-review
lshtram
Multi-expert architecture review with simplicity checklist and debate-driven analysis.
SkillDFreshness: DClaude Code +9 - 0.404score
bug-investigator
lshtram
Investigate bugs with LOG FIRST approach, regression tests, and variant coverage.
SkillDFreshness: DClaude Code +9 - 0.404score
code-reviewer
lshtram
Review code with confidence scoring (≥80), two-stage review, and CRITICAL issue blocking.
SkillDFreshness: DClaude Code +9 - 0.404score
systematic-debugging
lshtram
4-phase debugging methodology with root cause analysis, 3-fix escalation, and scientific method enforcement.
SkillDFreshness: DClaude Code +9 - 0.401score
rm-multi-perspective-audit
lshtram
Audit requirements from multiple stakeholder perspectives.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Feb 8, 2026 (8 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/lshtram/nso
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from lshtram
- 0.408score
integration-verifier
lshtram
Verify integration tests and E2E scenarios, detect failures, and provide rollback options
SkillDFreshness: DClaude Code +9 - 0.406score
tdd
lshtram
Test-Driven Development enforcement with rationalization prevention, verification checklist, and delete-and-restart rule.
SkillDFreshness: DClaude Code +9 - 0.406score
router
lshtram
Intelligent intent detection and workflow routing for NSO.
SkillDFreshness: DClaude Code +9 - 0.405score
platform-agentic-cicd-orchestrator
lshtram
Use when doing cross-layer planning, drift reconciliation, and CI/CD promotion across UI, n8n, and backend layers
SkillDFreshness: DClaude Code +9 - 0.404score
bug-investigator
lshtram
Investigate bugs with LOG FIRST approach, regression tests, and variant coverage.
SkillDFreshness: DClaude Code +9 - 0.404score
code-reviewer
lshtram
Review code with confidence scoring (≥80), two-stage review, and CRITICAL issue blocking.
SkillDFreshness: DClaude Code +9
Cite this page
skill-creator. Agent Mart. https://agentmart.dev/skills/lshtram-skill-creator (last updated 2026-10-24)