Write Skill
Draft or update a portable Agent Hub skill with clean frontmatter and a practical workflow.
Install
$ agentstack add skill-sdwolf4103-opencode-agenthub-write-skill ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-sdwolf4103-opencode-agenthub-write-skill) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
write-skill
Purpose
Create a portable Agent Hub skill as markdown, not a product-internal code registration. The outcome should be a SKILL.md that another hub can read, validate, and reuse.
Workflow
- Gather the skill's job, trigger conditions, audience, constraints, and expected outputs.
- Draft required frontmatter first:
name,description, andwhen_to_use. - Add optional keys only when they genuinely help, such as
allowed-tools,paths,model, oragent. - Draft the markdown body with focused sections like purpose, workflow, boundaries, verification, and anti-patterns.
- Run
validateSkillFrontmatteron the draft content before presenting it as done. - Write the file to the correct target:
- user home skill:
agenthub-home/skills//SKILL.md - built-in hub-local skill:
src/skills//SKILL.md
- Verify the file exists, frontmatter parses cleanly, and the body still matches the requested behavior.
Frontmatter quick reference
| Key | Required | Use it for | |---|---|---| | name | yes | Stable skill id | | description | yes | Short operator-facing summary | | when_to_use | yes | Trigger guidance for the host agent | | allowed-tools | optional | Tool restrictions or hints | | paths | optional | Relevant repo areas | | model / agent / effort | optional | Special runtime guidance only when justified |
Drafting rules
- Prefer one focused job per skill.
- Keep instructions reusable across repos when possible.
- Explain the decision flow, not just the final output format.
- If the skill will edit files, say what must be verified after the edit.
Anti-patterns
- Do not stuff multiple unrelated workflows into one skill.
- Do not add optional keys just because they exist.
- Do not describe skills as Claude-only internal bundles or code-registered objects.
- Do not skip frontmatter drafting and "add it later."
Verification
- Confirm the frontmatter has the required keys.
- Run
validateSkillFrontmatterand fix any hard errors. - Treat unknown-key warnings as a prompt to simplify unless the extra key is intentionally supported.
- Re-read the body to ensure headings and workflow steps are present.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: sdwolf4103
- Source: sdwolf4103/opencode-agenthub
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.