Chalk Labs
Need help deploying autoskill-creator?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/riquelmechile-autoskill-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
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
autoskill-creator- Description
- None
- License
- MIT
- Instructions
- 23 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- missing YAML frontmatter
- name: missing
- description: missing
Files (2)
- SKILL.md
- skill.json
SKILL.md (first lines)
# Company AutoSkill Creator Turn repeated or discovered Company work into reusable **company-local** operational skills. This is Business Learning, not KAST. ## Law `experience / observed process → registry search → reuse existing OR create Company Skill → SkillGene → verified outcomes → challenger/champion OR silent/quarantine` 1. Search the Company/global skill catalog before creating a new skill. Prefer an existing compatible skill when it already covers the process. 2. If the process is specific to the Company, create a `company-skill-definition` CompanyAsset with sanitized instructions and evidence references. 3. Create/attach a `skill-installation` asset to the responsible department. 4. Represent learning/evolution with `CorporateGene(type=skill)`. Do not invent another candidate/promoted lifecycle. 5. Outcomes, confidence, cost and incidents belong to the Company SkillGene fitness, not to the global skill manifest. 6. Raw conversations, credentials, secrets and unbounded tool output are forbidden in skill definitions/evidence. 7. Skills never grant authority, budget or credentials. They describe how to perform work inside existing grants. 8. A company-local skill can remain private forever. If evidence later shows it is generic and valuable across Companies, propose a separate global-catalog promotion through KAST; KAST governs the shared system change, not ordinary Company learning. ## Progressive disclosure `catalog metadata → match → load one selected skill body → execute → verify outcome` Do not preload the whole catalog into model context.
From riquelmechile/XanxitoSpA, MIT.
More from riquelmechile/XanxitoSpA
- 0.281score
sales-followup
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
design-competition
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
market-research
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
operations-control
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
procurement
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
svg-craft
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
business-reporting
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
character-art
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
company-bootstrap
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
customer-support
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
executive-planning
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9 - 0.281score
finance-control
riquelmechile
No description from the publisher yet.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 22, 2026 (2 months ago)
- Last release
- Aug 22, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/riquelmechile/XanxitoSpA
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get autoskill-creator running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
autoskill-creator. Agent Mart. https://agentmart.dev/skills/riquelmechile-autoskill-creator (last updated 2026-10-24)