saeedkolivand/ai-job-hunter-app
Command Claude Code
Run a WebGL landing review -- scrub-safety, resource disposal, per-frame allocation, post pipeline correctness, budget, semantic-layer parity, and gate integrity.
saeedkolivand/ai-job-hunter-app
Command Claude Code
Strict pre-PR review of the diff — risk-tiered ensemble (1-4 pr-reviewer passes by size/risk), security gate first on risky diffs, per-finding verifier fan-out, deterministic verdict from parsed schema-1 findings.
saeedkolivand/ai-job-hunter-app
Command Claude Code
Sync docs/knowledge with current code via project-steward (+ graphify update).
saeedkolivand/ai-job-hunter-app
Agent Claude Code
Cross-cutting rendered-output auditor for the apps/landing WebGL milestones - drives the dev server via Chrome DevTools MCP to exact playhead positions, screenshots, records performance traces, reads the console, and runs the scrub-determinism, draw-call, strobe-budget, copy-parity, and gate-fallback checks. Never…
saeedkolivand/ai-job-hunter-app
Agent Claude Code
WRITE-access owner of all GLSL in apps/landing - material shaders, the post-processing chain, procedural textures, and vertex shaders. Implements shaders to spec; never approves its own work - webgl-reviewer audits the diff. NOT for scene layout / engine wiring (webgl-author).
saeedkolivand/ai-job-hunter-app
Agent Claude Code
WRITE-access implementer for the apps/landing WebGL experience - scenes, engine, scroll rig, a11y overlay, semantic layer, content, and fallback (apps/landing/src/, GLSL/post excluded). Implements the R3F/three scroll-driven landing to spec; never approves its own work - webgl-reviewer (code/scrub-safety) and…
saeedkolivand/ai-job-hunter-app
Agent Claude Code
Cross-cutting GL frame-rate profiler for apps/landing - measures the worst t-segment via a Chrome DevTools performance trace, then applies the landing degradation ladder IN ORDER, stopping at the first rung that passes. Has write access to apply rungs. GL frame-rate only - distinct from performance-profiler (desktop…
saeedkolivand/ai-job-hunter-app
Agent Claude Code
Independent last-line critic for the apps/landing WebGL experience - audits BOTH GL authors' diffs (webgl-author scenes/engine, shader-engineer GLSL/post). Reviews scrub-safety, resource disposal, per-frame allocation, uniform-update vs recompile correctness, draw-call budget, ASCII compliance, semantic-layer parity…
saeedkolivand/ai-job-hunter-app
Skill Claude CodeCodex
Procedures for auditing apps/landing TERMINAL VELOCITY WebGL phase gates - driving the browser to exact playhead positions across the 9 scenes, screenshot discipline, scrub + VAT determinism (scrub down THEN rewind to the same playhead -> identical frame), FPS sampling at the risk scenes, draw-call + bundle-size…
saeedkolivand/ai-job-hunter-app
Skill Claude CodeCodex
DORMANT (ADR-0017, 2026-07-20) - the TERMINAL VELOCITY scroll-film was retired and apps/landing is a static site with no GL surface; this skill is preserved for any future WebGL rebuild (conventions, verified version pins, playhead/scroll-rig/VAT/Gerstner/post-chain patterns, budgets, gate + semantic-layer machinery).…
saeedkolivand/ai-job-hunter-app
Hook Claude Code
Runs before the agent uses a tool for Bash, Edit and Write tool calls, executing graphify-hint.mjs and guard-protected-files.mjs via node (2 commands). From saeedkolivand/ai-job-hunter-app.
saeedkolivand/ai-job-hunter-app
Hook Claude Code
Runs after a tool call finishes for Edit and Write tool calls, executing format-on-edit.mjs via node. From saeedkolivand/ai-job-hunter-app.
saeedkolivand/ai-job-hunter-app
Hook Claude Code
Runs when the agent finishes a response, executing review-gate.mjs via node. From saeedkolivand/ai-job-hunter-app.
saeedkolivand/ai-job-hunter-app
Hook Claude Code
Runs when a session starts, executing style-policy.mjs via node. From saeedkolivand/ai-job-hunter-app.
saeedkolivand/ai-job-hunter-app
Settings file Claude Code
Agent settings declaring 4 hook events (PreToolUse, PostToolUse, Stop, SessionStart) and 1 allowed tools.
saeedkolivand/ai-job-hunter-app
Skill Claude CodeCodex
Shared write-side contract every domain AUTHOR imports — smallest-diff implementation, ground-first, validation gates, tests-are-blocking, and never-approve-your-own-work. The write-side mirror of token-efficiency. Load at the start of any implementation task.