Skill reviews

End-of-session closure. Records what changed into the project's own handoff and log files, separating verified from attempted work, and reports what is uncommitted. Use when wrappi

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

OCR scanned or image-only corpora with vision-language models in four phases: `triage` inventories the scans, identifies script and language, and shortlists models by script, hardw

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill ranks results itself: that belongs to the system behind the tool, not the model
• The skill tells the model to perform an irreversible action with no human approval

Start up, tear down, and configure the local Kubernetes development environment for OpenShell. Uses k3d (Docker-backed k3s) + Skaffold + Helm. Covers cluster lifecycle, optional ad

• References files that are not bundled: scripts/keycloak-realm.json
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: scripts/keycloak-realm.json

Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use for gateway health failures, Docker/Podman runtime issues, Helm failures, Ku

• References files that are not bundled: templates/certgen.yaml
• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval

Generate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and ordered network middlew

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Neovim is a terminal text editor configured in Lua, with a built-in LSP client, Treesitter parsing and, since 0.12, a built-in plugin manager (vim.pack). Use this skill to install

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (8 tags): a typed call is more reliable
• Does not say what the process needs to start

Hugo is a static site generator that turns Markdown content and templates into a complete HTML website in seconds, with no database or server runtime. Use when a user asks to creat

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable
• Does not say what the result is

Sync the current session branch with its upstream branch, or publish the current session branch to a remote. Use when the user asks to sync a branch, pull latest changes, rebase on

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Use when running VS Code smoke tests or working on smoke-test CI steps. Covers npm run smoketest / smoketest-no-compile, grep filtering tests, and a temporary repeat-loop technique

• References files that are not bundled: scripts/test.sh, scripts/test-integration.sh
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (17 tags): a typed call is more reliable

Publish a finished static site to a free HTTPS link with DropTheHassle: build it if needed, deploy, hand over the claim link, verify it is live, never spend money.

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meanin

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Use a headed browser to automatically complete DingTalk channel integration for QwenPaw. Applicable when the user mentions DingTalk, developer console, Client ID, Client Secret, bo

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Create a PR to publish a new version of the rendercv-typst package to the Typst Universe (typst/packages repository). Validates package integrity, forks/clones the repo, copies fil

• References files that are not bundled: examples/<theme-name>.png
• The skill tells the model to perform an irreversible action with no human approval
• 1 referenced file(s) missing: examples/<theme-name>.png

Run an Anthropic Claude Managed Agent — a cloud agent harness (container + filesystem + tools), the cloud counterpart of the local wasm-agent runtime

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Coordinate with the open ruflo swarm federation at x.ruv.io (signed Nostr, membership-gated) and ask Seraphina — the swarm queen / primary coordinator — for guidance. Use when: see

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• Does not say what the process needs to start

Claims-based authorization for agents and operations. Grant, revoke, and verify permissions for secure multi-agent coordination. Use when: permission management, access control, se

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Review a skill-requested filesystem, command, network, secret, or destructive action against an explicit sandbox policy without executing it.

• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is
• No condition that starts the skill

Cut an OpenSEO release — bump the version, draft user-facing release notes from commits since the last tag, run a review + subagent-verification pass, and open a "release: vX.X.X"

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (11 tags): a typed call is more reliable
• Does not say what the result is

Create or update a skill in this repository the right way — canonical home in .agents/skills, internal-vs-public marking, symlink mirroring into .claude/skills, and public docs reg

• References files that are not bundled: scripts/sync-plugin-skills.mjs
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (5 tags): a typed call is more reliable

Invoke whenever writing, changing, reviewing, or sweeping Vitest tests in this repo. Authoring gate for new or changed tests, plus an audit workflow for low-value, implementation-c

• Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
• 11 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval

Proves a Voyager change on the live host page and shows the evidence as screenshots. Use after changing content scripts, injected CSS, MAIN-world scripts or plugin site code, when

• References files that are not bundled: ../voyager-contribute/references/browser-testing.md
• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (3 tags): a typed call is more reliable

GitHub Actions ${{ }} expression injection — attacker-controlled context (issue/PR title, body, branch name, commit message) substituted into run: steps, unsafe pull_request_target

• 14 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is

Detect and claim dangling S3 buckets referenced by subdomains (CNAME → s3 hostnames where bucket no longer exists).

• The skill tells the model to perform an irreversible action with no human approval
• The response is described with custom markup (4 tags): a typed call is more reliable
• Does not say what the result is

SAML 2.0 attacks — XSW (XML Signature Wrapping) variants 1-8, comment injection, signature stripping, assertion forgery, IdP metadata abuse.

• 15 top-level sections: this looks like several domains in one skill
• The skill tells the model to perform an irreversible action with no human approval
• Does not say what the result is