incremental-implementation

Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when picking up the next task from a plan. Use when rolling a change out behind a feature flag, 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

76%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/incremental-implementation/SKILL.md

Quality

Content

73%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 well-structured, highly actionable discipline skill: a clear increment cycle with validation checkpoints, concrete code and slicing examples, and strong anti-drift guardrails. Its weaknesses are redundancy across the checklist, rationalizations, red flags, and verification sections, and a broken up-level reference path for definition-of-done.md.

Suggestions

Consolidate the thrice-repeated 'don't re-run a command on unchanged code' guidance into one place (e.g., the Increment Checklist note) and trim the Red Flags / Common Rationalizations entries that duplicate it.

Fix the reference 'See ../../references/definition-of-done.md' to point at a real file within the skill bundle (e.g., references/definition-of-done.md), since no such file exists at the current up-level path.

Merge the Verification section into the Increment Checklist or clearly differentiate per-increment vs. end-of-task checks, since they currently repeat the same test/build/commit items.

Dimension	Reasoning	Score
Conciseness	The guidance is mostly lean and opinionated rather than teaching known concepts, but it repeats the 'don't re-run commands on unchanged code' point three times (Increment Checklist note, Common Rationalizations table, Red Flags) and the Verification section largely duplicates the checklist. This matches 'mostly efficient but could be tightened' rather than the clearly padded anchor 2.	3 / 5
Actionability	Concrete, executable material throughout: TypeScript feature-flag and safe-defaults snippets, three copy-paste slicing examples, a ready-to-use agent prompt, and enumerated verification commands (npm test, ./gradlew test, pytest, npx tsc --noEmit, mypy). It stops short of 5 because Rules 2 and 5 remain abstract directives with no supporting example.	4 / 5
Workflow Clarity	The Increment Cycle gives a numbered, looped sequence (Implement, Test, Verify, Commit) with explicit validation checkpoints, two checklists, and a rationalizations table guiding recovery from drift. This matches the anchor for clear sequence, explicit validation steps, and feedback loops.	5 / 5
Progressive Disclosure	A single-file discipline skill with well-signaled sections and no content that clearly belongs in a separate reference file. The gap is that the only external pointer ('../../references/definition-of-done.md') uses an up-level path that resolves to no real file in the bundle, and the cross-skill mentions (git-workflow-and-versioning, test-driven-development) carry no paths, keeping it below 5.	4 / 5
	Total	16 / 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.

A strong description with an explicit, multi-clause trigger set and a clear statement of what the skill does. The 'what' side is thinner than the 'when' side, naming one conceptual action rather than several concrete capabilities, and the multi-file trigger is broad enough to overlap with related engineering-discipline skills.

Dimension	Reasoning	Score
Specificity	The 'what' is a single conceptual action ('Delivers changes incrementally in thin, verifiable slices') rather than a list of several concrete capabilities, matching the anchor for 1-2 concrete actions without comprehensive coverage. It does not reach 4 because no multiple specific actions are enumerated.	3 / 5
Completeness	A clear 'what' ('Delivers changes incrementally in thin, verifiable slices') is paired with three explicit 'Use when...' clauses containing concrete triggers, matching the anchor that clearly answers both what and when. A score of 4 would require the 'when' to be less explicit than it is.	5 / 5
Trigger Term Quality	Natural trigger phrases like 'picking up the next task from a plan', 'rolling a change out behind a feature flag', and 'a task feels too big to land in one step' give good coverage of what users would actually say. It falls short of 5 because common synonyms such as 'step by step' or 'break this down' are absent.	4 / 5
Distinctiveness Conflict Risk	The incremental-delivery niche and scenario-specific triggers (feature flag rollout, next task from a plan) are mostly distinct from other skills. It is not 5 because the broad 'any feature or change that touches more than one file' trigger would fire alongside closely related coding-process skills.	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: 2686b62

Reviewed: 3 days 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.