Read or write Airtable data — bases, tables, tbl…/rec…/fld… IDs, filterByFormula syntax, field types and their coercion rules, batch limits, and the Meta API's boundaries. Covers the MCP tools, the REST API, and pyairtable. Triggers: 'read the Airtable records', 'update this base', 'what is the filterByFormula for…'…
Plan non-trivial work BEFORE coding — a feature, a bug fix with architectural reach, a refactor, a UI or workflow change, or anything touching multiple files — via the Stop & Think protocol: clarify the ask, research the current code and prior design logs, state assumptions and edge cases, freeze acceptance criteria…
Find a past Claude Code session to resume — I closed my session, find the session where we…, which session discussed X, which session talked to the other agent.
Commit and optionally push. MANDATORY before any git write — commit, push, merge, rebase, reset, branch -d. Triggers: ship it, commit, push. Do NOT enter here when the request also includes deploying and live-verifying the change ("deploy, push, delete the branch", "deploy and close it out", "run the browser tests and…
Review, audit, or improve ONE existing agent skill: SKILL.md structure against the eight required sections, description quality and routing collisions, allowed-tools scope, the 300-line ceiling, dead files under references/assets/scripts, and eval coverage. Ships scripts/review-skill-structure.sh for one skill and…
Build a NEW agent skill from a real repeated workflow. Use when the user asks to create a skill, scaffold SKILL.md, convert a recurring task into a skill, or decide whether a process deserves a skill. Do NOT use to review or audit an existing skill — use skill-improver for that.
Edit Tally forms via MCP tools — add/remove/reorder blocks and questions, change text, configure visibility/required state, and build conditional logic (applylogic DSL). Use when the user mentions Tally, questionnaires, form building, form blocks, or a Tally form ID/URL, or asks to add a question, hide/show a field…
Compare libraries/frameworks/tools and verify current APIs via live sources before choosing or implementing (X vs Y, latest, deprecated?). Also handles decision-grade questions — pivots, build-vs-buy, stack changes — via a weighted-criteria brief. Not for research already running inside a /design-log Phase B, and not…
Create self-contained HTML visualizations (single .html file) from conversation content, data, or ideas. Trigger on: "visualize this," "make a deck/slide/infographic/dashboard," "build a one-pager / poster / carousel / kanban / mind map / org chart / flowchart," "show me a chart," "render as HTML," or any ask to…