Enforce the design token layer — block raw hex values, hardcoded font sizes, and magic spacing numbers in component files. All visual values must reference semantic tokens.
Skills in this repository
andrem-sec/psc-comet - Page 2
SkillsMP has collected 66 skills from andrem-sec/psc-comet. Open a skill to review its source and details.
andrem-sec/psc-cometShowing 26 of 66 collected skills.
Memory consolidation — distills session learnings and transcripts into persistent memory files
Bug fix workflow — debug-session → tdd → refactor (optional) → code-review
Commit with decision context trailers — encodes the why, not just the what
File a structured GitHub issue — reads the actual template at runtime, auto-gathers context, enforces one concept per issue
Open or update a GitHub PR — reads the actual template at runtime, auto-detects create vs update mode, reconstructs body section-by-section
Gate before any UI implementation — requires confirmed inspiration references, color intent, typography direction, visual storytelling concept, and product-type design system. No HTML/CSS written until brief is confirmed.
Classify ambiguous requests and route to the correct skill or agent before any execution begins
Systematic root-cause debugging — no fixes before root cause is confirmed
Autonomous loop management with safety defaults and escalation gates
Schedule a prompt or skill to run on a recurring interval using CronCreate
YC-style product idea validation — forces specificity on demand, problem, and approach before any code is written
Product Requirements Document — specify and verify before implementing
Activates clean-output constraints when working on public repos — no internal tool names, no AI attribution in commits
Safe refactoring protocol — behavior-preserving restructuring with test coverage gate
Enforce mobile-first responsive design — breakpoint definition, content reflow audit, touch target validation, and layout stress testing at each tier.
Engineering retrospective from git history — velocity, quality, patterns, and team breakdown
Three-mode safety guardrail for autonomous operations with action logging
Visual QA loop for UI development — build, screenshot, compare to reference, identify delta, prompt correction, repeat. Formalizes the self-review cycle and defines when to disable it.
3-agent parallel code review — reuse, quality, and efficiency — fixes issues found
Fetch and analyze the full HTML, CSS, and JavaScript of a reference website — not a WebFetch summary. Identifies techniques, effects, and patterns powering the design for cloning or inspiration extraction.
Automated compliance measurement for skills, rules, and agent definitions
Quality audit of installed skills with portfolio health dashboard
Test-driven development — Red, Green, Refactor with explicit phase gates
Audit UI code for AI slop patterns — generic color palettes, missing interaction states, cookie-cutter gradients, and template-clone layouts. Returns SLOP/RISK/CLEAN verdicts with specific remediation.
6-phase pre-PR verification sweep with structured PASS/FAIL reporting