AgentStack
SKILL verified MIT Self-run

Skillctl

skill-xfurti-skillctl-skillctl · by xFurti

>

No reviews yet
0 installs
17 views
0.0% view→install

Install

$ agentstack add skill-xfurti-skillctl-skillctl

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README — it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-xfurti-skillctl-skillctl)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
16d ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.

Preview Execution monitoring

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 →
Are you the author of Skillctl? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

skillctl

Operational playbook for managing Agent Skills with the skillctl CLI. Run real commands; do not simulate output or copy SKILL.md files between agent directories by hand.

Golden rules

  1. One canonical store — skills live in ~/.skillctl/skills//; agents get symlinks via sync.
  2. Commit manifest + lock — track agent-skills.json and agent-skills.lock in git for team reproducibility.
  3. Portable specifiers only — use file:./, local:imported/, github:, npm:, or skills.sh/; never commit absolute homedir paths.
  4. Install before syncinstall materializes the store; sync only re-links agents.
  5. Verify after changes — run skillctl doctor (and skillctl audit in CI).
  6. Prefer import over manual copy — use import from-project or import from-npx instead of duplicating skill folders.

Decision tree

| Situation | Command | |-----------|---------| | New project, no manifest | skillctl init or skillctl init --with-skill | | Add a remote or local skill | skillctl add then skillctl install | | Skills already in .claude/skills, .codex/skills, etc. | skillctl import from-project | | Migrating from npx skills | skillctl import from-npx | | Re-link only (lock unchanged) | skillctl sync | | Re-fetch from upstream | skillctl update or skillctl update | | CI reproducible install | skillctl install --frozen then skillctl audit --strict | | Non-portable paths in lock | skillctl install to rewrite; check skillctl doctor warnings |

Quick recipes

# Bootstrap
skillctl init --with-skill
skillctl add github:vercel-labs/agent-skills#web-design-guidelines
skillctl install

# Project-local skill
skillctl add file:./my-skill
skillctl install
skillctl sync

# Import existing agent dirs
skillctl import from-project --dry-run
skillctl import from-project

# Inspect
skillctl list
skillctl doctor
skillctl audit --json

Expected after add file:./my-skill + install: manifest specifier file:./my-skill, lock canonicalPath like ~/.skillctl/skills/my-skill.

Portability (0.3.1+)

  • Portable: file:./rel, local:imported/, remote specifiers, canonicalPath: ~/.skillctl/skills/.
  • Not portable: absolute file:/Users/..., local:/abs/path, absolute canonicalPath from another machine.
  • If doctor warns about non-portable paths, run skillctl install to rewrite lock from manifest.

Failure modes

| Symptom | Action | |---------|--------| | canonical path missing | skillctl install | | Integrity mismatch | skillctl update or skillctl install | | Symlink fails (Windows) | doctor notes; config defaultMode: copy | | No agents linked | skillctl sync; enable agents in ~/.skillctl/config.json | | Frozen install failed | Store out of sync; run install without --frozen |

References

  • [commands.md](references/commands.md) — full command cheat sheet
  • [specifiers.md](references/specifiers.md) — specifier grammar
  • [manifest-lock.md](references/manifest-lock.md) — manifest and lock semantics
  • [workflows.md](references/workflows.md) — team onboarding, migration, CI
  • [troubleshooting.md](references/troubleshooting.md) — doctor, Windows, coexistence

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.