sharp-coder
Two-layer performance skill combining disciplined THINK layer (surgical edits, simplicity) and terse SPEAK layer (caveman compression). Triggers on requests for brevity, token efficiency, or disciplined coding.
Sharp Coder
Two orthogonal layers. Both always active. Neither overrides the other.
| Layer | Governs | When active |
|---|---|---|
| THINK | Reasoning & coding behavior | Before/during any code task |
| SPEAK | Prose output style | Every response |
Shared philosophy: no bloat. Not in code. Not in words.
When to Use
Use when the user explicitly requests brevity ("caveman mode", "less tokens", "be brief") OR requests disciplined coding ("karpathy guidelines", "think before coding"). This skill combines extreme token efficiency in prose with rigorous engineering discipline in code generation.
SPEAK Layer — Caveman Compression
Default: full mode. Switch: /caveman lite|full|ultra. Off: stop caveman / normal mode.
Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Pattern: [thing] [action] [reason]. [next step].
Keep exact: technical terms, code blocks, error strings, API names, function names, symbols.
Intensity levels
| Level | Rules |
|---|---|
| lite | Drop filler/hedging. Keep articles + full sentences. Tight but professional. |
| full | Drop articles, fragments OK, short synonyms. Classic caveman. |
| ultra | Abbreviate prose words (DB/aut |
Subscribers only
The full skill, its 1 bundled files and every download is included with every paid Complete AI plan.
Details
| Source | self |
|---|---|
| License | — |
| Risk label | safe ("critical" means the skill may run commands or touch files — read before use) |
| Files | SKILL.md |
| Added | 2026-09-04 |
Related skills
accesslint-diff
Diff a live page's accessibility violations against a baseline — by default compares uncommitted changes (stash-based), or pass --branch [<name>] to diff against a branch. Reports only new violations introduced, violations fixed, and pre-existing count. Use `scan` for a full audit with no diffing.
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.
accint-commitments
Triage acc's open promises and close them with honest real-world verdicts via acc_act(runtime="outcome").
accint-frames
Drain acc's deliberation queue — open/waiting brain_frames checkpointed by headless runs — via acc_act(runtime="continue").
accint-solve
Route a goal through acc's scored-memory loop via acc_act(runtime="solve"); deliberate any returned brain_frame and submit via continue.
ad-creative
Create, iterate, and scale paid ad creative for Google Ads, Meta, LinkedIn, TikTok, and similar platforms. Use when generating headlines, descriptions, primary text, or large sets of ad variations for testing and performance optimization.