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.
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.
Periodically self-assess output quality to catch degradation before the judge does.
Author a new Agent Skill for a Hive agent that conforms to the Agent Skills specification (SKILL.md with YAML frontmatter, optional scripts/references/assets directories). Use when the user asks to create, scaffold, add, or package a new skill for a Hive agent.