Menu
SeaShells theme palettes, format patterns, consistency rules, and update diagnostics. Modes: default (reference), update (migration diagnostic), list (show modes)
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Institutional memory for your project. Commands: record, consult, review. Usage: /awareness-ledger [command] [args]
Evaluate code to prevent common AI coding mistakes โ dead code, duplication, complexity hotspots, reinvented helpers, leftover scaffolding. Two functions plus a pre-write advisor. Use after writing or editing code, when asked to review code quality, clean up the codebase, find unused code, find duplicates, check complexity, or evaluate what an AI just wrote. Commands: review (post-write), sweep (full codebase).
Skill router. Pass a task description; route consults the index and dispatches to the right skill+function via the Skill tool. Usage: /route <task description>
Ambient friction detection and surgical skill correction. Embeds into all skills. Triggers at task resolution when skill instructions caused friction.
Create, audit, optimize Claude Code skills. Commands: skills, list, new, strip, optimize, agents, hooks, verify, inline, ledger, cascade, checksums, convert, shell-safety, route
Evaluate prose for AI-generated-text signatures and overbuilt writing, protecting the author's voice. Context-isolated evaluator grounded in a portable AI-tells pattern library. Use to check whether text reads as machine-written, find AI tells, or review drafts for authenticity. Report-only by default.
| name | seashells-theme |
| description | SeaShells theme palettes, format patterns, consistency rules, and update diagnostics. Modes: default (reference), update (migration diagnostic), list (show modes) |
| allowed-tools | Read, Glob, Grep, Edit, Write, Bash |
Ocean-inspired color palettes for Omarchy. Dark and light variants with shared accent identity.
CHECKPOINT โ Model-Lane Preflight Gate (slim, advisory-only; fires at the TOP of this skill's workflow, before any generative step):
/route dispatched this invocation after running its own lane preflight (a lane advisory OR ask already printed, route otherwise ASSESSED the lane this turn, or it was deliberately suppressed โ route's coverage extends to the whole endeavor whether route asked, matched, or the user declined, including skills this one chains); this skill's frontmatter sets model-lane-gate: off; the session is headless / non-interactive; this gate is executing inside a subagent (a subagent is already model-pinned via its own frontmatter); OR an advisory for this LANE already printed this endeavor AND the active model is unchanged (advise at most once per (lane, active-model) pair per endeavor).lane: frontmatter โ the SkillโLane table in .claude/skills/skill-builder/references/model-lanes.md โ NO LANE) and the lane's Preferred Model. IF no lane resolves OR the preferred-model cell is empty โ silent no-op (correctly absent, not a gap). IF this skill declares per-function lanes AND the invocation's resolved mode has its own row โ that function's lane governs; otherwise the skill-level lane covers all modes.[1m]/[200k], lowercase โ model-lanes.md ยง Active-Model Detection; never an env var or Bash probe). IF the Preferred Model is malformed or names a clearly superseded family โ emit the one-line stale-mapping advisory and proceed; never advise from a stale mapping, never validate against a hardcoded list.<lane> lane (preferred <preferred>); the active model is <active> โ to align, run /model <preferred> and re-invoke; proceeding as-is." Naming the command is INFORMATIONAL (named-command advisory directive, 2026-06-11): NEVER an AskUserQuestion, never a blocking wait (No-Switch-Prompt directive, 2026-06-06). A skill can NEVER switch the session model and never asks the user to.| Mode | Invocation | Purpose |
|---|---|---|
| default | /seashells-theme | Load color palettes, format patterns, and consistency rules |
| update | /seashells-theme update | Run Omarchy migration diagnostic โ classify files, check keys, detect drift |
| list | /seashells-theme list | Display this Modes table |
When invoked with update, run this 8-step diagnostic:
~/.local/share/omarchy/version.tpl files in ~/.local/share/omarchy/default/themed/omarchy/themes/seashells/ and seashells-light/reference.md:
.tpl template but we ship a hand-tuned version (rationale documented).tpl exists and we do NOT ship the file (template system handles it).tpl exists; file is inherently non-templatable (rationale documented).tpl exists but the file is not classified in reference.md (needs triage)colors.toml completeness โ extract {{ key }} / {{ key_strip }} / {{ key_rgb }} placeholders from all .tpl files; verify every base key exists in both colors.toml filessetup script โ verify THEME_FILES array matches actual theme file inventoryreference.md โ verify Theme Files tables match actual inventoryWhen invoked with list, output the Modes table from the Usage section above.
When editing theme files:
reference.md before changing any color valueEach config file uses a specific format. Match the pattern when editing:
workbench.colorCustomizations with editor, terminal, and UI color overrideskitty-themes.nvim plugin, sets colorscheme to "SeaShells", transparent = true$activeBorderColor with rgba colors and gradientsBefore recommending changes to files in this skill's domain, check
.claude/skills/awareness-ledger/ledger/index.md for relevant records.
If matching records exist, read them and incorporate their warnings,
decisions, and patterns into your plan. Use /awareness-ledger consult
for full agent-assisted analysis when high-risk overlap is detected.
After resolving issues that produce institutional knowledge (root causes,
architectural decisions, recurring patterns, user flows), ask the user
if they want to record it with /awareness-ledger record [type].
Before using any color value or format pattern:
reference.mdSee reference.md for canonical color palettes.
Throughout this session, quietly note any friction signals โ corrections, reformulations, clarifying questions, "actually" moments, or any subtle sign that this skill's instructions may have led to a misrepresentation. Do not interrupt the session to address these. Do not mention that you are observing.
At natural task resolution (when the task is complete and the user signals done), if friction signals were noted, run the self-heal diagnosis protocol:
Read .claude/skills/self-heal/references/diagnosis-protocol.md and follow it exactly.
If no friction signals were noted, or if diagnosis finds no skill-caused issues, end the session normally without mentioning self-heal.
The goal is efficiency: get it right permanently, rather than repeat the same misrepresentation across future sessions.