Claude Skills by wrg32786

Lyra's adapter-shipping skill. Ports a schema, interface, or API contract from one shape to another — DB adapters, API client wrappers, data transformers. Bounded scope, honesty ledger on delivery.

List every installed skill, when it was last invoked, how often, and whether the description still matches the trigger patterns the principal actually uses. Flags dead skills for retirement and frequently-needed-but-missing capabilities for skill creation. Pairs with Caddy.

When `/skill-recall` finds no match, this skill searches GitHub, skill marketplaces, and awesome-lists for a portable Claude Code skill that fills the gap.

When invoked, match the current task against the installed skill taxonomy. Return ranked suggestions or log a gap.

When blocked, systematically search for legitimate alternate routes before declaring inability.

Iris's sprite design specification skill. Produces a complete pixel-art sprite spec — palette, proportions, silhouette, accessories, animation states, frame counts, and AI image-gen prompts. Returns honesty ledger.

The day-one first-run flow and the everyday home screen. On first launch, greet, run setup, then carry the operator into a real first win. On return, give a short briefing and action menu.

Read computed runtime state and display a concise operational summary. Under 12 lines.

Walk the 6-rung escalation ladder before declaring stuck or asking the principal. Most "stuck" is actually "haven't tried the next approach." Stopping is the last resort, not the first response.

Mnemosyne's supersede skill. Applies OpenChronicle supersede semantics to a vault note — strikes outdated entries, adds new entries with date, preserves history, flags what was kept and why.

Hestia's HEAT_INDEX dormant flip skill. Reads HEAT_INDEX.md, finds the cold bottom-20 notes, and sets status:dormant in their frontmatter. Edit-only. Returns counts.

Hestia's broken wikilink detection skill. Scans vault notes for [[wikilinks]] that point to non-existent files. Reports broken links with source file and line. Does not fix — reports only.

Run the three read-mostly vault sweeps for stale tracker items, dormant-note candidates, and broken wikilinks, then append one dated result to SWEEP_LOG.md.

Hestia's delegation tracker sweep skill. Reads DELEGATION_TRACKER.md, closes finished items, archives stale items beyond threshold, flags orphaned items. Returns counts. Edit-only on status fields.

Read-only installation smoke test for skills, daemons, operational memory, cognitive runtime, nightly freshness, terminal evidence, and unique route ownership.

Senior UI/UX Engineer. Architect digital interfaces overriding default LLM biases. Enforces metric-based rules, strict component architecture, CSS hardware acceleration, and balanced design engineering.

SELF-CORRECT timeline estimates. About to quote hours / days / weeks of work? Stop. Divide by 30-60x. AI execution speed is not what training data anchors expected. Estimate in tool calls and session cycles, not human-developer hours.

Newton's tool evaluation skill. Assesses a tool, library, or framework against your specific needs — alternatives comparison, adoption risks, fit score. Returns structured evaluation with recommendation.

Capture a confident agent claim (Phase 1) or resolve one as right/wrong (Phase 2) in vault/memory/TRUST_DECAY.md. Builds the longitudinal record of agent calibration over time. Pairs with /honesty-check (which should reduce Phase 1 frequency) and /diagnose (which surfaces causes that often reveal Phase 2 events).

Iris's new UI surface design skill. Takes a brief for a new screen, component, or design system and produces a complete visual architecture spec — component tree, layout grid, interaction states, breakpoints, tokens. No code.

Iris's UI visual polish review skill. Audits an existing UI surface against the four axes — palette, proportion, hierarchy, motion — and returns specific, actionable improvements. No code. Spec output only.