The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands to manage repository state and validate builds.
Evidence: git status --short, npm run lint, npm run build in SKILL.md.
Use of advanced git operations involving temporary index files: GIT_INDEX_FILE=/tmp/<task>-index git read-tree HEAD.
[DYNAMIC_EXECUTION]: The skill injects and executes JavaScript code within a browser context to collect animation and memory metrics.
Evidence: Multiple calls to tab.playwright.evaluate() in references/browser-profiling.md to scan DOM elements and computed styles.
Use of dynamic imports to load browser client modules: await import('<path-to-browser-plugin>/scripts/browser-client.mjs').
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted data from repository files.
Ingestion points: Reads repository context, specifically AGENTS.md and local instructions (documented in SKILL.md workflow).
Boundary markers: No explicit boundary markers or "ignore instructions" warnings are defined for the file reading process.
Capability inventory: The skill has the ability to execute shell commands (git, npm) and run JavaScript in a browser session.
Sanitization: No evidence of sanitization or filtering of the content read from repository files before it is processed by the agent.

optimize-web-animations