Agent skill
sc-skill
Capture deterministic macOS screenshots for testing, docs, release notes, and marketing assets. Use when asked to automate app screenshots, batch-generate screenshot sets, standardize window sizing/composition, or choose between Peekaboo and native macOS screenshot tooling.
Install this agent skill to your Project
npx add-skill https://github.com/jazzyalex/agent-sessions/tree/main/skills/sc-skill
SKILL.md
SC Skill
Overview
Use this skill to produce repeatable screenshots for two modes:
testing: stable evidence screenshots for QA/regression workflows.marketing: polished, consistently framed screenshots for docs/site/release assets.
This skill is macOS-first and uses Peekaboo as primary automation with native screencapture fallback.
Quick Start
- Normalize window size and position:
skills/sc-skill/scripts/sc_window_preset.sh --app "AgentSessions" --preset marketing
- Capture one screenshot (auto-select tool):
skills/sc-skill/scripts/sc_capture.sh \
--app "AgentSessions" \
--mode marketing \
--delay 0.25 \
--max-edge auto \
--window-preset auto \
--output artifacts/screenshots/agent-sessions-main.png
- Run a manifest batch:
skills/sc-skill/scripts/sc_capture_suite.sh \
--manifest skills/sc-skill/references/examples/agent-sessions.tsv \
--outdir artifacts/screenshots
Workflow
- Choose mode:
testing: prioritize determinism and speed.marketing: prioritize composition consistency.
- Choose tool:
- Start with
--tool auto(defaults to Peekaboo when available and permitted). - Use
--tool nativewhen you need zero external dependency and simple window-region capture.
- Enforce layout before capture:
- Always run
sc_window_preset.shfirst. - Use consistent presets across runs to reduce visual drift.
- Capture and archive:
- Save to
artifacts/screenshots/.... - Sidecar metadata (
.json) is opt-in via--metadata; default runs keep artifacts cleaner. - Default output uses mode-based max edge (
--max-edge auto):testing=1800,marketing=2560, optimized/compressed for sharing/upload. - AgentSessions windows are normalized to a realistic working preset before capture (mode-based
testing/marketing) to avoid distorted/compressed UI composition. - Single capture closes the target app window by default (
--no-close-windowto keep it open). - Suite runs close captured app windows after all requested screenshots by default (
--no-close-after-suiteto keep them open). - For
AgentSessions, transcript readiness retry includes a built-in selection nudge (key down +0.5spause) to force transcript loading before capture. - Default transcript readiness remains fast-fail if loading still does not occur after nudge attempts.
- If transcript readiness times out, capture fails fast by default; pass
--allow-blank-transcriptonly when blank transcript output is acceptable.
Guardrails
- Never run captures from XCTest-driven launches when validating user-visible UI behavior; use a normal app launch.
- Keep screenshot naming stable and descriptive (
screen-purpose-state.png). - Avoid manual resize/drag between shots; use presets.
- For multi-shot runs, use the suite manifest instead of ad-hoc commands.
Resources
scripts/sc_window_preset.sh: deterministic window sizing/placement.scripts/sc_capture.sh: single-shot capture with Peekaboo/native fallback.scripts/sc_capture_suite.sh: manifest-driven batch capture.references/tool-matrix.md: tooling decision matrix and tradeoffs.references/workflow-checklist.md: repeatable QA/marketing checklist.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
deploy
Use when shipping a release of Agent Sessions — bumping version, updating CHANGELOG, building, signing, notarizing, publishing appcast, and creating a GitHub release.
agent-session-format-check
Verify agent session format compatibility for Agent Sessions. Use when any agent CLI updates, when monitoring flags drift, or when bumping max verified versions (fixtures + docs + tests). Covers session schema, usage/limits tracking, storage backends, and discovery path contracts for all supported agents.
agent-support-matrix
Maintain Agent Sessions agent support matrix and JSON/JSONL parsing compatibility. Use when checking upstream agent releases for session format changes, updating max verified versions in docs/agent-support/agent-support-matrix.yml, or updating docs/agent-json-tracking.md and fixtures/tests.
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Didn't find tool you were looking for?