TrimVis

9 mods across 1 repository, 2 stars between them.

comment-cleanup

01

TrimVis/skills

Skill Claude CodeCodex

Strip low-value comments and docstrings from code, fit what survives to the file's existing comment style, then rewrite the surviving text with the ste-writing skill. Loops until a pass changes nothing. Use when the user says "clean up the comments", "this is over-commented", "remove the AI comments", "trim the…

2 18d ago A 81 tokens original MIT

commit

02

TrimVis/skills

Skill Claude CodeCodex

Create one or more focused commits from the current working tree. Groups changes by logical concern, writes terse category-prefixed headlines and short high-level descriptions. Authored as the user (no Claude co-author). Use when the user says "commit this", "make a commit", "commit my changes", or invokes /commit.

2 18d ago A 67 tokens original MIT

difit-open

03

TrimVis/skills

Skill Claude CodeCodex

Open a REVIEW.md (written by /difit-review) in difit's browser UI for interactive review. Starts a difit instance (or pushes to one the user already has running on a given port), populates it with the unresolved threads from REVIEW.md. Optional — REVIEW.md is the source of truth; this skill just provides a nicer way…

2 18d ago A 83 tokens original MIT

difit-resolve

04

TrimVis/skills

Skill Claude CodeCodex

Apply the fixes proposed in a REVIEW.md (written by /difit-review), merge any new user replies from a running difit instance, write Claude's replies back into REVIEW.md, and best-effort echo them to difit if it's running. REVIEW.md is the source of truth; difit is an optional UI we sync to when available.

2 18d ago A 75 tokens original MIT

difit-review

05

TrimVis/skills

Skill Claude CodeCodex

Parallel multi-model code review. Spawns Opus, Sonnet, Fable, and Haiku reviewers in parallel — each specialised for the analysis dimensions that model is strongest at — then writes the merged findings to REVIEW.md under the Claude project dir. REVIEW.md is the authoritative review state; difit is a separate, optional…

2 18d ago A 78 tokens original MIT

refactor-prose

06

TrimVis/skills

Skill Claude CodeCodex

Iteratively refactor existing prose — privacy policies, marketing copy, web content, docs — based on user requirements or feedback. Reads surrounding pages for voice, asks clarifying questions before drafting, edits in place, and expects multi-turn revision. Use when the user says "update the privacy policy", "reword…

2 18d ago A 91 tokens original MIT

refine-skills

07

TrimVis/skills

Skill Claude CodeCodex

Mine Claude Code transcripts for how your installed skills actually behaved, find recurring corrections, and propose SKILL.md edits one finding at a time. Use when the user says "refine my skills", "improve my skills from usage", "what keeps going wrong with skill X", or invokes /refine-skills.

2 18d ago A 69 tokens original MIT

squash

08

TrimVis/skills

Skill Claude CodeCodex

Rebase the current branch against its fork point (master/main) and squash the branch commits into a small, sensibly-grouped set. Larger restructuring is welcome — drop work that was later reverted, fold fixups into their parent. Commit messages follow the same category-prefixed terse style as /commit, authored as the…

2 18d ago A 101 tokens original MIT

ste-writing

09

TrimVis/skills

Skill Claude CodeCodex

Rewrite prose (docs, READMEs, PR descriptions, error messages, release notes, comments, tool descriptions, system prompts — never code) into ASD-STE100 Simplified Technical English to remove "AI slop". Use when asked to make writing not sound like AI, make docs clear or plain, enforce a controlled writing style…

2 18d ago A 103 tokens original MIT