Install
$ agentstack add skill-alfredxw-denova-skills-creator ✓ 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.
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
Skills Creator
Help the user create or revise a Denova Skill compatible with Denova's Skills layout:
//SKILL.md
Use this workflow:
- Confirm the target scope when it is not explicit:
- user scope: reusable across books, stored under the Denova user skills directory
- workspace scope: specific to the current book, stored under
/.denova/skills - built-in or preset Skills are read-only; to customize one, create or update a same-name user scope Skill by default, falling back to workspace scope only when the user scope is unavailable, instead of editing
DENOVA_SKILLS_DIR/skills_dir
- Choose a slash-command-friendly skill name: lowercase letters, digits,
_, or-; start with a letter or digit. - Write one concise
SKILL.mdwith YAML frontmatter:
name: exact skill name and directory namedescription: when the agent should use this skill
- Keep the body actionable:
- when to use the skill
- what context to gather
- concrete steps the agent should follow
- output or safety constraints
- Do not add README, guide, docs, or sample files unless the user explicitly needs supporting assets.
- If editing files is available and the user has already confirmed the goal, write the skill to the selected scope. For built-in Skill customization, write the override to user scope with the same name by default, and use workspace scope only when user scope is unavailable. Otherwise, show the proposed
SKILL.mdand ask for confirmation.
After creating or updating the skill, tell the user they can trigger it in the writing agent or other Skills-enabled agents with:
/
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: alfredxw
- Source: alfredxw/denova
- License: Apache-2.0
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.