Agent Skills catalog · page 168
Standard HTML pagination keeps the complete catalog discoverable. Use the main directory for search, filtering, and comparison.
- Current page
- 168/209
- Entries on page
- 24
- URL status
- Self-canonical
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-create-benchmark
Author MCP-promotion, behavior, skill-benchmark, and model-benchmark artifacts; route the Lane A authoring guide.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-create-manual-testing-playbook
Author manual testing playbook packages with deterministic scenarios, evidence collection, and multi-agent execution planning.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
system-spec-kit
Unified spec-folder workflow + context preservation: Levels 1-3+, validation, Spec Kit Memory. Required for file modifications.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
cli-cursor
Cursor CLI executor for cursor-agent-backed coding, plan/ask read-only modes, native git worktree isolation, and a cloud worker — a shared-editor-config CLI dispatch.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
mcp-notion
Operates a Notion workspace through the official Notion MCP (@notionhq/notion-mcp-server, 24 tools) over Code Mode, fills 5 API gaps with direct Notion API calls, and routes between the headless local-stdio backend and the interactive remote OAuth backend. Carries a Notion knowledge layer (data-source model, 22 property types, relations, rollups, Formulas 2.0). Embedded registration and agent safety invariants.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-code-review
Stack-agnostic code-review for sk-code: findings-first severity, security/correctness minimums, and surface evidence.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-create-quality-control
Validate, score, and optionally improve existing markdown via structure extraction, DQI scoring, HVR review, and validation gates.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
cli-claude-code
Claude Code CLI executor for Anthropic-backed reasoning, edits, reviews, and structured cross-AI handoff.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
cli-devin
Devin CLI executor for Cognition-backed coding, cloud handoff, subagent delegation, and cross-AI validation.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
cli-opencode
OpenCode CLI orchestrator: external dispatch, in-OpenCode parallel sessions, cross-AI handback with full runtime context.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
deep-ai-council
AI Council: multi-seat planning, artifact persistence, convergence checks, packet-local ai-council outputs.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
deep-research
Autonomous deep-research loop: iterative investigation, externalized state, convergence detection, fresh context per pass.
brianwestphal/glassbox
kerf-app
Build UIs in the kerf reactive framework (https://github.com/brianwestphal/kerf). Use this skill whenever the user is writing or modifying code that imports `kerfjs`, asks to add a feature to a kerf app, or asks "how do I do X in kerf?". Use it proactively the moment you spot a kerf import in the file you're editing.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
mcp-click-up
Routes ClickUp between cupt CLI (daily ops) and official MCP (docs, goals, bulk). Embedded install and agent safety invariants.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-create-command
Scaffold OpenCode slash commands with explicit argument hints, allowed tools, and router/presentation separation.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-create-feature-catalog
Create sk-doc feature-catalog packages with a root catalog, category folders, per-feature files, and auditable source anchors.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-vision
Local vision for text-only models: OCR, inspect, detect and pixel analysis on screenshots via a private Moondream runtime.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
system-deep-loop
Routes research, review, AI Council, and improvement modes through registry-selected packets.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
system-skill-advisor
Routes non-trivial requests to matching skills through standalone MCP metadata and stable advisor tool ids.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
deep-improvement
Evaluator-first bounded agent improvement: 5-dim scoring, dynamic profiling, packet-local candidates, guarded promotion.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
diagram-design
Create technical and product diagrams — architecture, IT current-state, flowchart, sequence, state machine, ER / data model, timeline, swimlane, quadrant, radar / spider, loop / flywheel, nested, tree, org chart, layer stack, venn, pyramid / funnel, bar chart, line chart, Gantt, scatter plot, high-level, process, medallion, data flow, DP integration, DP security matrix — as standalone HTML files with inline SVG. Also imports existing draw.io / diagrams.net files (.drawio, .drawio.png, .drawio.sv
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-code
Unified two-axis code skill: routes to two WORKFLOW modes (sk-code-quality, sk-code-review) and bundles two read-only SURFACE evidence packets (sk-code-webflow, sk-code-opencode) — each surface carrying the implement/debug/verify workflow doctrine plus its stack knowledge — over shared surface-detection; holds no per-mode logic; dispatches by workflowMode through mode-registry.json.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-code-mobile-cli
Read-only Svelte design-system and source-convention evidence for the Pi Remote Mobile-CLI app.
MichelKerkmeester/opencode--skilled-agent-loops-with-spec-kit-memory
sk-create-diff
Local, Git-free before/after review of an edited document (text, Markdown, HTML, DOCX, text PDF) as a self-contained HTML report.