Loading...
Loading...
Found 39 Skills
Prompt engineering standards and context engineering principles for AI agents based on Anthropic best practices. Covers clarity, structure, progressive discovery, and optimization for signal-to-noise ratio.
Goal-persistence execution wrapper for autonomous work that must continue across turns until the stated objective is actually satisfied.
Create new narrative summaries from content. Formats: 3-part story, n-length with inline links, abridged 5-line, or comprehensive. Uses UltraThink for creative framing. USE WHEN: "explain as a story", "narrative summary", "story-format explanation". NOT for editing existing text — use humaniser to remove AI patterns from written text.
Automated UI development loop: dev server + browser + implement + verify + fix. Launches dev server, implements via frontend-design skill, checks for errors (console, TypeScript, network), and iterates up to 5 times. USE WHEN: "implement next feature", "implement [description]", "verify the UI". NOT for one-off design/code tasks — use frontend-design directly for those. 6. Reports completion or escalates with detailed report **Triggers:** - "implement next feature", "implement the hero section" - "verify this implementation", "check the UI" - "fix the errors", "iterate on this" - "start dev server", "manage server"
Owner-scoped task decomposition with gates, rollback, verification commands, and smoke tests.
Horizontal session personality overlay — auto-detects conversation mode from density signals, defaults casual, upgrades to structured only on sustained signal. Includes CommitMono aesthetic preference and MoE/thinking-chain runtime awareness.
Web research, content extraction, and deep analysis. Multi-source parallel search with extended thinking. Supports Fabric pattern selection (242+ prompts). USE WHEN: "research X", "extract wisdom from", "analyze this content", "find info about".
Root-cause investigation for bugs, regressions, suspicious runtime behavior, failed automations, and unexpected outcomes.
Findings-first review discipline for code, diffs, task plans, live workflow changes, and implementation evidence.
Frontend and visual QA for responsive surfaces, screenshots, text fit, hierarchy, and interaction states.
Source-first, self-loop resistant guardrails for Capy GitHub dialogue responders before any write-capable PR, issue, or review action.
Capability discovery and current-state verification for Heavy Path, ambiguous repo/runtime ownership, and runtime-dependent Standard Path work.