Showing 45691–45720 of 45757 skills
1Password environment management for AI agents and development. Load secrets as environment variables from 1Password, supporting .env and .env.1pass formats. Use when configuring API keys, tokens, or secrets for AI models, CI/CD, or local development.
kylebrodeur/1password-ssh-setup
SSH agent management with 1Password for passphrase handling and keychain integration. Use when working with SSH keys on Linux/WSL/Windows. Features keychain-based key persistence and 1Password-stored passphrases for secure, passwordless SSH operations.
kylebrodeur/1password-ssh-setup
Author and maintain the MAW project-context overlay (`maw/project-context/`) — the project knowledge the pipeline injects into agents. Use when the user says "add project context", "set up MAW for this project", "register a project invariant / rule / lesson / tool / skill / domain for the pipeline", or "review MAW context proposals". Supports flag: --review to go straight to folding pending PCTX_PROPOSALS.md entries.
pockerhead/maw
Adversarial multi-agent development pipeline. Use when the user says "take the next task", "work through tasks", "run the pipeline", or wants to implement a task from the task board with full planning, review, implementation, and QA cycle. Supports flags: --worktree (force worktree mode), --no-worktree (force branch-only mode). These override the saved setting for the current run only. Supports positional arg: a task number or ID (e.g. `/maw-execute-task 3`, `/maw-execute-task TASK-003`) to run a specific task out of priority order instead of picking the highest-priority pending task. Model-invocation is guarded: if invoked by the model rather than an explicit user command, the auto-invoke guard applies (see Invocation guard) — confirmation is required before any state change unless the user disabled the guard in maw/settings.json.
pockerhead/maw
Expensive, human-invoked adversarial deliberation over a QUESTION (not a task). Runs a five-role chain — premise check, generator, compressor, attacker, synthesizer — as real isolated spawns, and returns a synthesis with an explicit disagreement ledger and what-would-change-my-mind. Use when the cost of being wrong is high and genuine uncertainty exists: architecture forks, irreversible migrations, "should we X or Y" with real stakes. Do NOT use for lookups, trivia, or questions a single careful answer settles — it costs roughly 200-350k tokens and several minutes. Supports flags: --fast (lower compressor/attacker/synthesizer effort for speed, at the cost of a thinner attack surface), --keep (persist the trace for audit), --passes N (extra attack passes, default 1), --high-assurance (dual independent generators on distinct profiles, +1 spawn), --seed N (reproduce a previous run's role assignment), --force-premise (run the full chain even if the premise check flags the question). Model-invocation is guarded: if the model reaches for this rather than the user typing it, the auto-invoke guard applies — the human sees the question, profile, and cost estimate and confirms before anything spawns.
pockerhead/maw
One-stage adversarial review of your own uncommitted diff, run by a different vendor than the one that wrote it. Use before committing work you produced in an ordinary session — no task folder, no pipeline, no branch handling. Costs one spawn and about a minute, against nine stages for the full pipeline. Reviews the diff only; it never edits code. Normally fires automatically from the pre-commit gate rather than being called by hand — the moment you would think to ask for it is the moment you are least likely to.
pockerhead/maw
Create well-formed tasks for the MAW pipeline. Use when the user says "add a task", "create a task", "new task", or describes a feature/fix/refactor that should be tracked — even if they don't explicitly ask to create a task. Supports flag: --mode <full|small-fix|brainstorm|deep-research> to skip mode suggestion and set the mode directly.
pockerhead/maw
Update the MAW installation in this project to the latest published version. Use when the user says "update MAW", "upgrade MAW", "reinstall MAW", "обнови maw", or asks for the newest pipeline prompts. Reruns the official installer with the same surfaces and options that are installed now, so nothing optional is dropped. Never touches `maw/` (tasks, settings, project context).
pockerhead/maw
Design or validate API wire contracts after business acceptance, or reconstruct API source evidence as an observed candidate without defining unknown wire rules.
idaibin/skills
Prepare or obtain a requested external-AI result for review, research, images, cross-review/互审, or a saved instruction such as 进行三方会审.
idaibin/skills
Implement frontend UI and project-native UI guidance in the existing stack. Route change-based reviews to repo-review and existing-surface audits without a change basis to repo-audit.
idaibin/skills
Implement Java source and Java-owned Maven or Gradle changes.
idaibin/skills
Implement, port, or refactor Rust source, including native Rust UI, in the existing Cargo workspace.
idaibin/skills
Plan risk-based coverage and execute functional acceptance across backend, APIs, pages, UI, business logic and end-to-end journeys. Run existing scoped checks; route source fixes to their owner.
idaibin/skills
Implement non-browser TypeScript or JavaScript changes for Node.js, Bun, or Deno.
idaibin/skills
Resolve shared business terms, rules, and lifecycle ambiguity; use product-spec for feature-local behavior.
idaibin/skills
Draft, rewrite, proofread/校对, or adapt source-grounded prose for the requested document type while preserving meaning; owns wording, not test coverage, API contracts, or product facts; not translation-only work or fiction.
idaibin/skills
Operate browser pages, including mobile-browser content, and capture runtime evidence; use ops-device for device/app state.
idaibin/skills
Operate desktop clients through semantic protocols or UI controls, including background task submission and progress queries; use ops-device for mobile devices.
idaibin/skills
Operate and verify a specified mobile physical device, emulator, or simulator and its installed app; use ops-browser for browser-page evidence.
idaibin/skills
Define product behavior and acceptance, or reconstruct source-grounded product evidence as an explicitly unaccepted candidate.
idaibin/skills
Audit existing frontend, Java, or Rust surfaces read-only. Use repo-review for change-based reviews.
idaibin/skills
Execute authorized Git commits, pushes, integration, history changes, or cleanup.
idaibin/skills
Scan or query repository assets, relationships, coverage, and drift; not routine task-local file discovery.
idaibin/skills
Review current changes or a fixed revision read-only. Use repo-audit for existing-surface audits without a change basis.
idaibin/skills
Create or reconcile a durable project task ledger from accepted contracts and findings; not task execution or scheduling.
idaibin/skills
Turn selected visual evidence into a UI Feature Spec or project-owned shared visual contract; not image generation or implementation.
idaibin/skills
Retrospect on personal work across conversations, projects, domains, and shared practices; produce evidence-backed improvement proposals. Not repository mapping, task execution, or automatic rule changes.
idaibin/skills
Use when administering a Synapse / Matrix homeserver — list or snapshot all rooms, rate room health (public, unencrypted, orphaned), render a Graphviz map of the room/space tree, force-join users, promote room admins, harden rooms (add-to-space + restrict + encrypt), deactivate Matrix users (with GDPR erase), find biggest rooms by DB size, audit where a user is admin or member, replay join/leave timelines, or search unencrypted history. Trigger on any '/_synapse/admin', server-wide room operation, Matrix user offboarding, or anything requiring a homeserver-admin token — even without 'admin API' in the prompt. Companion to matrix-communication.
netresearch/matrix-skill
Use when composing a Matrix announcement — skill release, version bump, weekly digest, breaking-change heads-up, postmortem, RFC, multi-skill pipeline summary, or any agent-authored room post longer than a single line. Trigger before any matrix-send call that produces structured content. Companion to matrix-communication.
netresearch/matrix-skill