Skip to content
SkillCheatSheet Sign in

work-unit-commits

An AI agent skill from Gentleman-Programming/gentle-ai, scored 71 out of 100 by code.

71/ 100B

Code score by group

  • Spec20/20
  • Description9/20
  • Procedure7/15
  • Done criteria11/15
  • Resources10/10
  • Scripts2/8
  • Safety7/7
  • Upkeep5/5

It loses the most points in Description (11), the group that checks whether the description says what the skill does and when to use it.

What the author says it does

Plan commits as reviewable work units. Trigger: commit splitting, chained PRs, or keeping tests and docs with code.

This is the description in the skill's own SKILL.md, written by its author, not by SkillCheatSheet.

Repository
Gentleman-Programming/gentle-ai
Folder
skills/work-unit-commits
License
MIT
GitHub stars
8,818
SKILL.md lines
99
Other files
0

Add work-unit-commits to your agent

npx skills add Gentleman-Programming/gentle-ai --skill work-unit-commits

The command uses the open skills CLI. A skill is instructions and scripts your agent will follow, so read it first: open the folder on GitHub at the commit that was scored.

Labelled for

More skills from Gentleman-Programming/gentle-ai

  1. gentle-ai-collab-perfect

    Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR st…

    Verified88A
  2. issue-creation

    Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.

    75B
  3. skill-creator

    Trigger: new skills, agent instructions, documenting AI usage patterns. Create LLM-first skills with valid frontmatter.

    70B
  4. issue-root-resolution

    Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue cluste…

    65C
  5. rdd-defect-workflow

    Trigger: fixing RDD defects (review authority, receipts/lineage, correction/recovery, delivery gate). Not for using or toggling RDD.

    65C
  6. skill-registry

    Trigger: update skills, skill registry, actualizar skills, after skill changes. Index available skills by trigger and path.

    64C
  7. cognitive-doc-design

    Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.

    63C
  8. chained-pr

    Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

    62C

All skills in Gentleman-Programming/gentle-ai

Scores come from a snapshot of 300 public GitHub repositories taken on 12 November 2026. Every score is the result of fixed checks run by code; no AI is involved. How scoring works.