hive.note-taking
hive.note-taking maintains a structured scratchpad in a shared buffer to preserve working context that would otherwise be lost during context pruning, capturing key decisions with reasoning, intermediate extracted values, unresolved questions, and blockers that fall outside the task queue schema. Use this skill at information checkpoints, before large tool outputs, and when documenting non-obvious decisions whose rationale might disappear from the tool call history.
git clone --depth 1 https://github.com/aden-hive/hive /tmp/hive.note-taking && cp -r /tmp/hive.note-taking/core/framework/skills/_default_skills/note-taking ~/.claude/skills/hive.note-takingSKILL.md
## Operational Protocol: Structured Note-Taking Maintain free-form working notes in shared buffer key `_working_notes` for data that *you* need to remember but that isn't captured by the colony task queue. **Do not duplicate the queue in here.** Per-task goal, ordered steps, and SOP gates live in `progress.db` — use `hive.colony-progress-tracker` for those. These notes are for things the DB schema doesn't cover. Update at these checkpoints: - After receiving new information that changes how you plan to approach the current step - Before any tool call that will produce substantial output you'll need to reference later - When you make a non-obvious decision whose *why* would be lost if the tool call history gets pruned Structure: ### Key Decisions — decisions made and WHY ### Working Data — intermediate results, extracted values (URLs, IDs, key snippets — not full pages) ### Open Questions — uncertainties you plan to verify ### Blockers — anything preventing progress that isn't already captured in `tasks.last_error` Update incrementally — do not rewrite from scratch each time.
SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.
Required before any hive-browser CLI command. The browser is driven from the terminal by running `hive-browser <command> ... --json` via terminal_exec — not via MCP tools. Teaches the browser lifecycle rules (the bridge attaches to the USER'S running Chrome — never kill or launch browser processes; timeouts are transport issues, not crashes), the screenshot + coordinate workflow (hive-browser interact with a fractional coordinate) that reaches shadow-DOM inputs selectors can't see, the viewport-fraction coordinate rule (not pixels), rich-text editor quirks ("send button stays disabled" failures), and CSP gotchas. Covers Chrome via CDP through the GCU Beeline extension.
Required reading whenever any chart_* tool is available. Teaches the one-tool embedding contract (call chart_render → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no chartjunk, restrained palette, proper typography, single message per chart), and the canonical spec patterns for the 12 most-common chart types. Skipping this leads to 1990s-Excel charts, missing downloads, and the agent writing markdown image links by hand instead of letting chart_render drive the UI.
Claim tasks, record step progress, and verify SOP gates in the colony SQLite queue. Applies when your spawn message includes a db_path field.
Proactively extract critical values from tool results into working notes before automatic context pruning destroys them.
Follow a structured recovery decision tree when tool calls fail instead of blindly retrying or giving up.
Required before calling image_generate. Create and edit images from a prompt — generate an image, make a picture / logo / illustration / icon / banner / poster / thumbnail / hero image / mockup / product shot / social graphic, or edit / restyle / combine existing images from reference images. Uses OpenAI gpt-image-2 through the Hive image service, billed to the user's Hive credits like an LLM call (no API key needed). Teaches the exact call shape, the quality/cost tradeoff (quality="low" is the default and cheapest), reference-image editing, how to show the result to the user with attach_file, and the failure modes (out of credits, model unavailable, moderation).
Read before automating LinkedIn with browser_* tools. LinkedIn combines shadow DOM (#interop-outlet), strict Trusted Types CSP that silently drops innerHTML, Lexical composer, native beforeunload dialogs that hang the bridge, and aggressive spam filters — each has bitten us at least once. Verified flows for profile messaging, connection-request acceptance, feed composition, and search. Requires hive.browser-automation. Verified against logged-in production 2026-04-11.