Skills — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Skills (Plugin) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Open-source agent skills from Temi. Works with Claude Code, Claude Cowork, Codex, Cursor, Gemini CLI, and anything else that supports the Agent Skills spec.
In the Codex plugin UI, open Plugins → Add Marketplace and enter:
usetemi/skillsOr from the CLI:
codex plugin marketplace add usetemi/skills/plugin marketplace add usetemi/skills
/plugin install usetemi@useteminpx skills add usetemi/skillsEach skill ships as a zip on the latest release. Download the one you want and upload it via Settings → Capabilities → Skills.
| Skill | What it does |
|---|---|
ask-clarifying-questions | Conduct clarification interviews before ambiguous implementation, investigation, or design work, showing a visible prediction with each question, then use the resulting model of how the user decides for implementation-time decisions. |
software-design | Design judgment for modules, interfaces, and where information lives. |
observability | Opinionated judgment for instrumentation, logging, tracing, alerting, and production feedback: explainability as the goal, structured records with bound context, one terminal record on every exit path, severity as an alert decision, and telemetry tools chosen by the question they answer. |
ddd | Write, revise, and consolidate DOMAIN.md, a repository's domain model (ubiquitous language, model, rules and invariants), by interviewing the user as the domain expert. |
fly-io | Deploy, review, troubleshoot, and design Fly.io apps, Machines, networking, and storage; operate and integrate Sprites persistent environments. |
sprite-apps | Umbrella workflow for building and shipping Elixir/Ash/Phoenix web apps on Fly Sprites: composes software-design, observability, web design, and fly-io, with the Sprites app pattern (co-located Postgres, one origin, object-storage backups) and an Elixir anti-patterns pass. |
node-26 | Upgrade and modernize Node.js projects for Node.js 26: Temporal, Map/WeakMap get-or-insert helpers, Iterator.concat, raw crypto key formats, removed APIs, and Current vs LTS rollout guidance. |
pdf | Fill, redline, and generate PDFs with the right tool for the source. Auto-detects AcroForm vs flat PDFs, handles AES-encrypted government forms, navigates appearance-stream gotchas (/NeedAppearances, /Ch comboboxes, /Sig widgets, multi-page header carry-forward), and verifies output by rendering. |
tailscale | Deploy, configure, review, troubleshoot, and automate tailnets: grants and ACLs, SSH, Tailnet Lock, PAM, Serve, Funnel, Services, tsidp, subnet routers, exit nodes, app connectors, peer relays, MagicDNS, Kubernetes, containers and tsnet, workload identity federation and OAuth, API and GitOps, Aperture, and production diagnostics. |
Each skill folder is self-contained. SKILL.md is the entry point, with references/ for deeper docs the agent loads on demand.
MIT. See LICENSE.
These skills come out of work at Temi. We open-source the parts of our agent toolkit that we find generally useful.
If you build something with them, we'd love to hear about it.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.