incremental-implementation

Delivers changes incrementally. Use when implementing any feature or change that touches more than one file. Use when you're about to write a large amount of code at once, or when a task feels too big to land in one step.

Quality

83%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

88%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a strong, actionable guide: it sequences a clear increment cycle with validation checkpoints, supplies executable code and commands, and largely avoids over-explaining concepts Claude already knows. Progressive disclosure is good but slightly undermined by a non-resolving external reference and a modest amount of repeated guidance.

Suggestions

Verify or fix the See Also path '../../references/definition-of-done.md' so it resolves to a real bundled file, or rephrase it as a sibling-skill pointer like the other references.

Consolidate the overlapping guidance between 'Common Rationalizations' and 'Red Flags' to trim tokens while keeping the actionable signal.

Consider moving the longer worked slicing examples (Vertical/Contract-First/Risk-First) into a short reference or tightening them, since the core pattern is already conveyed by the Increment Cycle.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with concrete slices and rules rather than padded explanation; a few sections (e.g., the Rationalizations table and Red Flags list) restate the same guidance multiple ways, keeping it just short of a lean 5.	4 / 5
Actionability	It provides copy-paste-ready code (feature flag, safe-defaults function), concrete slicing templates, and explicit verification commands like 'npm test', 'npx tsc --noEmit', matching the fully-executable anchor covering common cases.	5 / 5
Workflow Clarity	The Increment Cycle is an explicit Implement→Test→Verify→Commit sequence with validation checkpoints, the checklist enforces per-slice verification, and the Rationalizations/Red Flags sections supply feedback-loop guidance for error recovery.	5 / 5
Progressive Disclosure	Structure is well organized with one-level-deep references to sibling skills (git-workflow-and-versioning, test-driven-development) and a See Also pointer; not a 5 because the external reference '../../references/definition-of-done.md' does not resolve to an actual bundled file, and some inline material could be split out.	4 / 5
	Total	18 / 20 Passed

Description

78%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is concise, uses third person, and pairs a clear capability statement with explicit 'Use when' triggers covering multiple realistic scenarios. Specificity is slightly limited because it names only one concrete action, but trigger quality and completeness are strong.

Dimension	Reasoning	Score
Specificity	Quotes 'Delivers changes incrementally' — names the domain and one concrete action, but the rest of the description is trigger phrasing rather than a list of specific capabilities, matching the 'names domain and 1-2 concrete actions' anchor; not a 4 because it does not list several distinct actions.	3 / 5
Completeness	It explicitly states the 'what' ('Delivers changes incrementally') and follows with multiple concrete 'Use when...' trigger clauses, satisfying the anchor for clearly and explicitly answering both what and when.	5 / 5
Trigger Term Quality	Phrases like 'touches more than one file', 'about to write a large amount of code at once', and 'too big to land in one step' are natural things a user would say, giving good keyword coverage; not a 5 because common synonyms and explicit scope nouns are limited.	4 / 5
Distinctiveness Conflict Risk	The incremental-delivery niche with concrete multi-file triggers is mostly distinct from adjacent skills, with only minor overlap risk against git-workflow or test-driven-development; not a 5 because the trigger 'more than one file' is broadly applicable.	4 / 5
	Total	16 / 20 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: addyosmani/agent-skills
Path: skills/incremental-implementation/SKILL.md
Commit: df1edb2

Reviewed: about 18 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.