AIRI is a self-hosted virtual AI companion that gives an AI character a voice, visual presence, memory, and the ability to interact with games and coding activity. People use it as a personal digital companion on the web, macOS, or Windows, including for voice chat and gameplay. The catalogue add-ons provide workflows for working with the AIRI project.
Borrowing it
Nothing to install: this file belongs to moeru-ai/airi. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/moeru-ai/airi/main/.agents/skills/release-note-writer/SKILL.mdgit clone --depth 1 https://github.com/moeru-ai/airiWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/moeru-ai/airi/release-note-writer)<a href="https://agentmods.dev/skills/moeru-ai/airi/release-note-writer"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/release-note-writer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/moeru-ai/airi/release-note-writer"><img src="https://agentmods.dev/badge/skills/moeru-ai/airi/release-note-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 141 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00084 | $0.01886 |
| Opus 5 | $0.00042 | $0.00943 |
| Sonnet 5 | $0.00017 | $0.00377 |
| Haiku 4.5 | $0.00008 | $0.00189 |
Grade A, and why
release-note-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Note Writer
Core Rule
Write release notes in English only. Convert technical history into reader-facing changes grouped by audience and outcome. Do not mirror commit scopes directly.
Required Discovery
Before drafting, gather the release context:
- Check the current repo version and tags.
- Inspect package/version files that already exist in the repo.
- Inspect recent git tags with
git tag --sort=-v:refname. - Identify the previous release tag.
- Run changelogithub dry output:
pnpm dlx changelogithub --dry --from <previous-version>- If the command needs network and fails because of sandboxing, request approval and rerun it.
- Inspect the generated commit structure and then inspect commits directly.
- Use
git show --stat --oneline <sha>or equivalent targeted commands. - Include chore/internal commits when they affect contributor workflow, tooling, builds, CI, local development, docs generation, test infrastructure, or internal packages.
- Use
- If version boundaries are ambiguous, ask one concise question before drafting.
Audience Structure
Use a compact, aggregated structure. Prefer fewer major sections with useful subheadings over many small scope-based sections. Use multiple heading levels when that makes the audience or product surface clearer.
Recommended order:
- Product-facing sections for end users.
### To developersnear the end.### To contributorslast.### Upgrade notesonly when action is required.
Product-facing sections can be nested by surface:
### Product updates#### Local#### Cloud#### New providers#### Chat and settings
Do not force every release into these exact headings. Pick headings that make the release easy to scan.
Use a dedicated bug-fix section when fixes include critical regressions, blocked primary workflows, or issues users may scan the notes to confirm. Critical bugs deserve plain, concrete language because users may be checking whether their blocker was fixed. Minor visual, wording, and low-impact cleanup can stay grouped as polish, but do not bury important fixes inside broad product updates.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 222 lines · 84 tokens per session scan A f70786b6f62b
release-note-writer is a skill published in the GitHub repository moeru-ai/airi (48,961 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 1,886 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.
updater_guide
Guidance for checking for and installing Row-Bot updates.