Claude Skills by sageox

Design, generate, replace, and publish an agent avatar with agent-toolkit while preserving the separation between durable character identity and shared house style. Use when creating an agent avatar, editing `avatar.md`, regenerating `avatar.png`, changing an agent's visual identity, reviewing avatar consistency, or publishing profile artwork to Buzz or Slack.

Create, configure, validate, and optionally publish a hosted agent with agent-toolkit. Use when asked to create, initialize, set up, bring up, register, or deploy an agent; configure its brain, chat surfaces, memory, MCP tools, or repository context; or diagnose an incomplete agent setup. Use agent-avatar for focused avatar work.

Create or update a GitHub pull request, monitor CI and review feedback, inspect every thread and summary, fix valid findings, explain and resolve invalid findings, commit and push, and repeat until the current head is clean. Use when asked to open a PR and babysit reviews, watch a PR for comments, address automated or human review feedback, clear existing review threads, or keep fixing a PR until all required checks and reviews are resolved. Pause only when human input or access is genuinely ...

Search SageOx team memory BEFORE answering from first-principles reasoning. Auto-fire when the user references recent or specific work or asks a before/after question: "I just pushed...", "did X fix Y?", "is the alert gone now?", "this request", or anything tied to a prior decision, a prod anomaly, or a metric/cost change. A confident answer that prior work contradicts is worse than a slow one — check first, then answer. Routes the cue to the right corpus: recency to `ox session list`, concep...

Read recorded team conversations locally and follow sageox:// citations back to what was actually said. Auto-fire when the user asks "what did we say in that meeting", "show me the discussion about X", "what's behind this claim", pastes a sageox:// citation URI or a cnv_/rec_ id, or wants a transcript, the topics, or the summary of a recorded conversation. Run `ox conversation list|show|topics|topic|transcript` — each JSON envelope's guidance field names the next rung and token_estimate repor...

Consult team context BEFORE creating or editing a Decision Record (ADR, DDR, architecture/design decision doc). Auto-fire when the user asks to "write an ADR", "add a decision record", "amend/update ADR-NNN", cites a DR by number, or edits a file under docs/adr/ or docs/decisions/. Run `ox decision enrich --topic "<subject>"` before drafting a new DR and `ox decision enrich --file <dr.md>` before editing an existing one — related decisions, numbering, conventions, drift, and ready-to-paste ci...

Author the plan as a rich, self-contained interactive HTML page FIRST — that page IS the plan of record — then hand it to ox: `ox plan save --file plan.html` stores it in the ledger, derives the markdown from it, and computes the deterministic badges; `ox plan render --file plan.html` serves it with the ox chrome (enrichment overlay + footer credit + live review loop) injected, never rewritten. This skill's authoring energy goes into the page itself — tabs, field inspectors, data-driven visua...

Emit and paste the SageOx credit line at the TOP of a pull-request description — the human-facing counterpart to the machine `SageOx-Session:` trailer. Run `ox pr header` at PR-creation time; it renders a thin, on-brand, dark/light-aware line linking the session(s) and plan(s) that produced the change, naming the team, and whispering a subtle enrichment stat. The CLI owns the sanitizer-fragile markup — you never hand-author it. Use when opening a PR for AI coworker work, or when the user says...

Answer "what value am I getting from SageOx?" with receipts, not vibes. Auto-fire when the user asks "is SageOx worth it", "what has SageOx done for me", "what am I getting out of SageOx", "should I keep using this", "was SageOx worth it this week", or says "ox recap" / "give me a recap". Run `ox recap --json` and narrate a tight, personal, prose answer from the `guidance` field — never invent value, never cite a bare statistic or a time-saved/dollar figure, ground every claim in a receipt fr...

Audit every session in the project ledger for quality, then offer cleanup and regeneration. Carries the operational knowledge from the 2026-04-25 cleanup (the cache-only invariant and a failure-mode watch-list) that no single ox subcommand backs. Use when the user asks to "review the ledger sessions", "audit session quality", "clean up bad session summaries", "regenerate session summaries", invokes the session-review workflow, or wants to find and fix sessions with missing/poor titles, empty ...

Manage SageOx Agent Skill bundles for this repository. Use when a user asks which ox skills are available, wants to install or repair Attest playbooks, or needs to understand how local coding agents receive team workflows.

Choose review-friendly visual explanations with ox viz. Use when creating or updating a PR description, especially for architecture, lifecycle, data flow, before/after, or multi-component changes; also use for plans, docs, reports, and design notes. Start a material PR description with `ox viz pr`; ask a known reviewer question through `ox viz pr --intent "<question>" --json`.

Design, generate, replace, and publish an agent avatar with agent-toolkit while preserving the separation between durable character identity and shared house style. Use when creating an agent avatar, editing `avatar.md`, regenerating `avatar.png`, changing an agent's visual identity, reviewing avatar consistency, or publishing profile artwork to Buzz or Slack.

Create, configure, validate, and optionally publish a hosted agent with agent-toolkit. Use when asked to create, initialize, set up, bring up, register, or deploy an agent; configure its brain, chat surfaces, memory, MCP tools, or repository context; or diagnose an incomplete agent setup. Use agent-avatar for focused avatar work.

Create or update a GitHub pull request, monitor CI and review feedback, fix and resolve every finding, push, and repeat until the current head is clean. Use when asked to open a PR and babysit reviews, watch for comments, clear existing review threads, or keep addressing automated or human feedback until nothing actionable remains. Pause only when human input or access is genuinely required.

Search SageOx team memory BEFORE answering from first-principles reasoning. Auto-fire when the user references recent or specific work or asks a before/after question: "I just pushed...", "did X fix Y?", "is the alert gone now?", "this request", or anything tied to a prior decision, a prod anomaly, or a metric/cost change. A confident answer that prior work contradicts is worse than a slow one — check first, then answer. Routes the cue to the right corpus: recency to `ox session list`, concep...

Read recorded team conversations locally and follow sageox:// citations back to what was actually said. Auto-fire when the user asks "what did we say in that meeting", "show me the discussion about X", "what's behind this claim", pastes a sageox:// citation URI or a cnv_/rec_ id, or wants a transcript, the topics, or the summary of a recorded conversation. Run `ox conversation list|show|topics|topic|transcript` — each JSON envelope's guidance field names the next rung and token_estimate repor...

Consult team context BEFORE creating or editing a Decision Record (ADR, DDR, architecture/design decision doc). Auto-fire when the user asks to "write an ADR", "add a decision record", "amend/update ADR-NNN", cites a DR by number, or edits a file under docs/adr/ or docs/decisions/. Run `ox decision enrich --topic "<subject>"` before drafting a new DR and `ox decision enrich --file <dr.md>` before editing an existing one — related decisions, numbering, conventions, drift, and ready-to-paste ci...

Author the plan as a rich, self-contained interactive HTML page FIRST — that page IS the plan of record — then hand it to ox: `ox plan save --file plan.html` stores it in the ledger, derives the markdown from it, and computes the deterministic badges; `ox plan render --file plan.html` serves it with the ox chrome (enrichment overlay + footer credit + live review loop) injected, never rewritten. This skill's authoring energy goes into the page itself — tabs, field inspectors, data-driven visua...

Emit and paste the SageOx credit line at the TOP of a pull-request description — the human-facing counterpart to the machine `SageOx-Session:` trailer. Run `ox pr header` at PR-creation time; it renders a thin, on-brand, dark/light-aware line linking the session(s) and plan(s) that produced the change, naming the team, and whispering a subtle enrichment stat. The CLI owns the sanitizer-fragile markup — you never hand-author it. Use when opening a PR for AI coworker work, or when the user says...

Answer "what value am I getting from SageOx?" with receipts, not vibes. Auto-fire when the user asks "is SageOx worth it", "what has SageOx done for me", "what am I getting out of SageOx", "should I keep using this", "was SageOx worth it this week", or says "ox recap" / "give me a recap". Run `ox recap --json` and narrate a tight, personal, prose answer from the `guidance` field — never invent value, never cite a bare statistic or a time-saved/dollar figure, ground every claim in a receipt fr...

Audit every session in the project ledger for quality, then offer cleanup and regeneration. Carries the operational knowledge from the 2026-04-25 cleanup (the cache-only invariant and a failure-mode watch-list) that no single ox subcommand backs. Use when the user asks to "review the ledger sessions", "audit session quality", "clean up bad session summaries", "regenerate session summaries", invokes the session-review workflow, or wants to find and fix sessions with missing/poor titles, empty ...

Manage SageOx Agent Skill bundles for this repository. Use when a user asks which ox skills are available, wants to install or repair Attest playbooks, or needs to understand how local coding agents receive team workflows.

Choose review-friendly visual explanations with ox viz. Use when creating or updating a PR description, especially for architecture, lifecycle, data flow, before/after, or multi-component changes; also use for plans, docs, reports, and design notes. Start a material PR description with `ox viz pr`; ask a known reviewer question through `ox viz pr --intent "<question>" --json`.