Scan the web for coding agents and agent orchestrators, track GitHub stars and trends, rank by popularity+momentum, and publish a report to the irrlicht site. Shows which agents irrlicht already supports. Use when user says 'agent landscape', 'scan agents', 'coding agent tracker', 'agent popularity'…
Check latest releases of coding agents monitored by irrlicht (Claude Code, OpenAI Codex, Pi, Gas Town, Aider, OpenCode, Gemini CLI, Kiro CLI, Antigravity, Mistral Vibe) and report new features that impact session monitoring. Use when user says 'agent releases', 'check releases', 'agent updates', '/ir:agent-releases'…
Review a working diff for defects and report findings worst-first — the repo-owned, agent-invocable counterpart to the built-in /code-review, which is disable-model-invocation and can only be run by a human. Scales from a single read to an adversarially-verified pass, and checks this repo's own conventions (the…
Audit all project documentation for understandability, completeness, and validity using objective, binary criteria, then fix every finding directly in place. Filing a GitHub issue is the rare fallback — only for a finding whose fix is genuinely ambiguous or that fails verification after being applied. Every finding is…
End-to-end execution of a GitHub issue via /ir:exec [mode] — open a worktree, investigate, then either present a visual HTML plan for approval or proceed straight to implementation (mode-dependent), open a PR, review it with a dedicated review subagent, fix findings, simplify, hand back the PR link with a…
Maintain the canonical scenario × agent fixture matrix for irrlicht. A slim dispatcher that routes intent to four focused subagents — create-scenario (add a matrix row), create-agent (add a matrix column), assess (judge one cell across the three pillars and write its spec), and record (drive the live agent and verify…
Judge one (agent, scenario) cell across the three pillars — agent capability, daemon sensor capture, driver capability — on cited evidence, then author the cell's recipe and machine-checkable spec. Writes the cell metadata via of cell write and the spec (expected.jsonl) via of cell spec. No live recording. Invoked as…
Onboard a brand-new agent CLI as a matrix COLUMN: research its identity + recording prerequisites, register it via of agent add, scaffold its interactive driver from the template, and predict which step types each scenario's recipe will need (the driver-needs punch-list). No live recording. Invoked as…
Add a brand-new scenario ROW to the matrix: one agent-agnostic {id, name, description, acceptancecriteria, process} entry written through of scenario add. Researches how the behavior manifests across every onboarded agent (and what the daemon would observe) before synthesizing the agent-agnostic spec. No agent CLI…
Carry one assessed cell to a committed, verified recording: check prerequisites, port any missing driver step, drive the live agent CLI under a recording daemon via of record run, verify EVERY websocket observation (state + model + cost + tokens + agent) via of record verify, refresh the replay golden, and commit.…
Sync irrlicht's model-name alias map against codeburn's upstream BUILTINALIASES. Fetches codeburn's src/models.ts, diffs entries against core/pkg/capacity/aliases.go, and proposes additions/changes as a PR. Use when user says '/ir:refresh-aliases', 'refresh aliases', 'sync codeburn aliases', 'check alias map', or when…
Build and publish an irrlicht release. Bumps version, builds Go daemon + Swift app, creates signed app bundle with icon, packages DMG (branded installer) + PKG, updates docs/changelog/landing page, commits, tags, pushes, and creates GitHub release with assets. Default: patch bump. Use "/ir:release minor" or…
Build and run a dev irrlicht daemon and/or macOS Swift app for local testing, by invoking this skill's own test-mac.sh. Two independent axes: MODE (replace, default — takes over production on port 7837/production state; separate — coexists on port 7838/isolated state) and TARGET (full, default — daemon + app; daemon …
Autonomously triage GitHub issues on ingo-eichhorst/Irrlicht. Diagnostic-only: assesses the spec, scores a 7-axis readiness rubric, lands the issue at ready-for-agent or needs-info, and emits an effective complexity level (1-10) plus the run plan ir:exec should spend on it and a two-part time estimate (agent-active…
Use this skill to generate well-branded interfaces and assets for Irrlicht, either for production or throwaway prototypes/mocks/etc. Contains essential design guidelines, colors, type, fonts, assets, and UI kit components for prototyping.
The frontmatter is well-formed, but description: — the field the skill loader matches on — still carries its template token. It is not empty, so the frontmatter check alone would pass it.
A nested skill, whose frontmatter name carries the parent prefix — the shape .claude/skills/ir:onboarding-factory/assess/SKILL.md uses. Folded scalars count as a present description.
95 4d agoA49 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: