Skip to content
SkillModel-led2,010 tokens in use

incremental-implementation

Build features in thin vertical slices, testing, verifying and committing each increment before the next.

119,377 stars on the repository MIT Licenseaddyosmani/agent-skills · skills/incremental-implementation
npx skills add addyosmani/agent-skills --skill incremental-implementation
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing incremental-implementation costs

80tokens idle
2,010tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter12/15
  • Structure19/25
  • Examples12/15
  • Output15/15
  • Size13/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community76
  • Maturity32
  • Momentum40

Incremental Implementation is the execution discipline for any change that touches more than one file. The agent implements the smallest complete piece, runs the tests, verifies the result, commits it and only then moves to the next slice.

The skill describes vertical, contract-first and risk-first slicing, and sets rules for simplicity, scope discipline, one change at a time, a compilable build after every step, feature flags, safe defaults and rollback-friendly increments.

What You Get

  • The implement, test, verify and commit cycle
  • Slicing strategies with examples
  • Rules from simplicity to rollback-friendly changes
  • A per-increment checklist and a prompt pattern for directing an agent

Common Use Cases

  • Implementing a feature from a task breakdown
  • Making a multi-file change
  • Merging unfinished work behind a feature flag
  • Refactoring in small steps

What Makes It Unique

The skill pairs slicing strategies with explicit scope control and a rule against re-running a verification command when the code has not changed. It also gives a short prompt that tells an agent what is in and out of scope for each increment.

Under The Hood

The skill is a single SKILL.md of instructions. It runs no scripts of its own. The agent runs the repository’s own test, build, type check and lint commands and makes git commits after each slice, and it points to the git-workflow-and-versioning skill and a definition-of-done reference.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers