Claude Skills by kbichave

github.com/kbichave

4 skillsA× 43 installs28 views

DeepADiscovery, planning, and implementation pipeline. Modes — intent: capture the problem; discovery: system audit → phase specs; plan: implementation blueprint; implement: execute sections; auto: autonomous end-to-end from a phase list; goalloop: loop toward a stated end state, carving increments as it goes, until every acceptance line is evidenced. Accepts @path, inline text, or no argument.developmentpythongoVotes: 0GitHub stars: 2
HumanizerARemove signs of AI-generated writing from text. TRIGGER when user says "humanize", "make this sound human", "remove AI writing", "de-slop", or asks to edit/review text to sound more natural. Also triggers on slide decks, roadmap docs, card headers and chart labels, blog posts and landing pages, not only prose. Other skills call it as an embedded step (review comments, PR text). Based on Wikipedia's "Signs of AI writing" plus the stylometric findings in Reinhart et al. (PNAS 2025). Detects and...ai-agentsgoreactVotes: 0GitHub stars: 2
No Op RemoverAFind and remove no-ops from instruction and prompt files — lines a model already obeys by default, so they burn context to say nothing. TRIGGER when the user says "remove no-ops", "strip no-ops", "hunt no-ops", "kill filler instructions", "tighten this prompt/skill", or asks to cut instructions that change no behavior. Scans SKILL.md, agent definitions, CLAUDE.md/AGENTS.md, prompt templates, and docs; proposes delete/strengthen fixes; applies only what the user approves. NOT for humanizing pr...ai-agentsbashgitVotes: 0GitHub stars: 2
Review PanelAStandalone multi-expert code review, outside of /deep implement. Routes the diff to a panel of specialist reviewer subagents (core packs, logic, architecture, ML, stats, MLOps, data engineering, prompt engineering), verifies claims against current docs, gates everything through a final review-verifier, and writes a dated report under ~/.claude/code-reviews/ (never inside the repo). Detects whose code it is: on the user's own work it offers fixes and inserts inline CODECHANGE/RECOMMENDATION ma...ai-agentspythongoVotes: 0GitHub stars: 2