// Render an Octocode MCP usage dashboard from `${OCTOCODE_HOME}/stats.json` or `~/.octocode/stats.json`. Use when the user asks to show Octocode stats, usage, tokens/chars saved, cache hits, errors, rate limits, or visualize `stats.json`.
Use when the user asks to "research code", "how does X work", "where is Y defined", "who calls Z", "trace code flow", "find usages", "explore this library", "understand the codebase", or needs deep code exploration with HTTP-based tool orchestration. For direct MCP tool research without the HTTP server, use octocode-researcher instead.
Use this skill when the user asks to find, evaluate, preview, install, rate, review, score, improve, refactor, or synthesize Agent Skills (the `SKILL.md` folder format) across GitHub, local skill folders, and skill marketplaces. Covers searching for a skill for a task, deep-diving a candidate, installing one or more skills into one or more agents at user or project scope, rating or reviewing an existing SKILL.md, refactoring a skill, or creating a new local skill from researched patterns. Do NOT activate for general package search (npm, PyPI, cargo), web search, or code research not involving SKILL.md files.
Use when the user asks to design, review, implement, debug, or evaluate an agentic workflow or AI-agent harness: MCP tools/resources/prompts, multi-agent routing or handoffs, agent memory/context/cache, Zod/JSON-schema protocols, human gates, observability, evals, or production safety. Do not use for ordinary app code, generic prompt writing, or model comparison unless an agentic flow boundary is involved.
System-engineering skill for codebase understanding, bug investigation, refactors, PR safety, architecture review, and RFC validation. Enforces Clean Architecture and Clean Code with AST, LSP, and scanner evidence. Produces a flows / boundaries / architecture-health artifact with file:line citations before recommending action.
Generates polished multi-file HTML presentations. Six-phase flow: brief → research → outline → design → implementation → review. Each slide is a standalone HTML file loaded via iframe. Use when asked to 'create slides', 'make a presentation', 'generate HTML slides', 'build a deck', or turn notes/docs/code into a polished presentation.
Use Chrome DevTools Protocol (CDP) for browser debugging, inspection, and automation when DevTools-grade evidence is needed: network, console, performance, DOM/CSS, screenshots/PDF, security, storage, auth-gated, live-page, and source-traced findings. Opens or attaches to Chrome, runs sandboxed CDP scripts, and keeps sessions reusable. Prefer lighter browser tools for simply opening a page.
| name | octocode-stats |
| description | Render an Octocode MCP usage dashboard from `${OCTOCODE_HOME}/stats.json` or `~/.octocode/stats.json`. Use when the user asks to show Octocode stats, usage, tokens/chars saved, cache hits, errors, rate limits, or visualize `stats.json`. |
Generate a local HTML dashboard from Octocode usage stats. The build script owns all parsing, calculations, rendering, and browser-opening behavior; do not reimplement those calculations in chat or another script.
Use this skill when the user asks to:
stats.json or data under ~/.octocode/Do not use it for session ID lookup, credentials, or unrelated configuration files.
Resolve the stats file:
${OCTOCODE_HOME}/stats.json when OCTOCODE_HOME is set~/.octocode/stats.json otherwise--stats <path> when explicitly requestedIf the stats file is missing, say:
No stats yet — run any Octocode MCP tool first, then re-run this skill.
Run the dashboard builder from the repo root:
node skills/octocode-stats/scripts/build_dashboard.mjs
Common flags:
--stats <path>: read a non-default stats file--output <path>: write the dashboard somewhere else--no-open: generate without opening the browser--allow-empty: render an empty-state dashboard even when stats are missing--help: print script usageIf the browser did not open, include a manual open <dashboard-path> command on macOS.
estimatedTokensSaved = savedChars / 4. Always describe them as approximate.charsSavedByTool is cumulative response-savings data, not a recent activity log and not a complete per-tool call ledger.rawChars, responseChars, and savedChars are measurements from the response pipeline, not a perfect partition where raw = response + saved.responseChars is the final tool response after output pagination; rawChars counts upstream API/command/file payloads that were actually fetched or read.