CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

52

Quality

56%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/incremental-implementation/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

62%

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

This is a well-structured process skill with clear workflow sequencing and practical checklists. Its main weakness is verbosity — it over-explains principles that Claude already understands (why incremental development is better, why small commits help) and includes overlapping sections (Red Flags and Common Rationalizations cover similar ground). The actionability is moderate: while it provides good illustrative examples and specific verification commands, much of the content is philosophical guidance rather than directly executable instructions.

Suggestions

Cut the 'Common Rationalizations' table — Claude already understands why incremental development is beneficial; the Red Flags section covers the same ground more concisely.

Trim the 'Simplicity First' and 'Scope Discipline' sections significantly — these are general engineering principles Claude knows; keep only the concrete check patterns (the ✗/✓ examples).

Consider splitting Slicing Strategies into a referenced file (e.g., SLICING_STRATEGIES.md) to reduce the main skill's token footprint for simple use cases.

DimensionReasoningScore

Conciseness

The skill is well-written but verbose for its target audience. Sections like 'Common Rationalizations' and 'Red Flags' overlap significantly. The simplicity check examples and scope discipline sections, while useful, add bulk. Some content (e.g., explaining why small commits are good, why testing each slice matters) is knowledge Claude already possesses. However, the concrete examples and checklists do earn their place.

2 / 3

Actionability

The skill provides concrete examples (TypeScript feature flags, slicing strategies with specific scenarios) and checklists with specific commands (npm test, npm run build, npx tsc --noEmit). However, much of the guidance is philosophical/principled rather than executable — it describes an approach rather than giving copy-paste-ready implementation steps. The code examples are illustrative rather than directly executable in a real project.

2 / 3

Workflow Clarity

The increment cycle is clearly sequenced (Implement → Test → Verify → Commit → Next slice) with an explicit diagram. Validation checkpoints are well-defined in the Increment Checklist with specific commands. The feedback loop is implicit but clear — if tests fail, you fix before moving on. The note about not re-running unchanged commands adds practical nuance.

3 / 3

Progressive Disclosure

The content is well-organized with clear section headers and logical flow from overview to details. However, at ~200 lines, some sections (Common Rationalizations, Red Flags, Slicing Strategies) could be split into referenced files. The single cross-reference to 'git-workflow-and-versioning' is appropriate, but the monolithic structure means Claude loads all content even when only part is needed.

2 / 3

Total

9

/

12

Passed

Description

49%

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 has good structural completeness with explicit 'Use when' clauses, but suffers from vagueness in what it actually does and overly broad trigger conditions. The triggers are so generic ('more than one file', 'large amount of code') that this skill would conflict with nearly any coding skill, and the core capability ('delivers changes incrementally') lacks concrete actions explaining the methodology.

Suggestions

Specify concrete actions the skill performs, e.g., 'Breaks large changes into sequential, independently-reviewable commits/PRs, ensuring each step compiles and passes tests.'

Narrow the trigger conditions to reduce conflict risk—instead of 'more than one file', use more specific triggers like 'when the user asks to split a PR, break up a large change, or deliver work incrementally.'

Add natural trigger terms users would actually say, such as 'split commits', 'incremental PRs', 'stacked changes', 'break up this change', 'step by step implementation'.

DimensionReasoningScore

Specificity

The description uses vague language like 'delivers changes incrementally' without specifying concrete actions. It doesn't explain what 'delivering changes incrementally' actually entails—no mention of specific techniques like creating branches, splitting commits, breaking PRs into smaller pieces, etc.

1 / 3

Completeness

The description answers both 'what' (delivers changes incrementally) and 'when' (implementing features touching more than one file, writing large amounts of code, tasks too big for one step) with explicit 'Use when' clauses.

3 / 3

Trigger Term Quality

It includes some relevant trigger phrases like 'more than one file', 'large amount of code', and 'too big to land in one step', which are somewhat natural. However, it lacks specific keywords users would say like 'split PR', 'incremental commits', 'break up changes', 'refactor step by step', etc.

2 / 3

Distinctiveness Conflict Risk

This description is extremely generic—almost any non-trivial coding task touches more than one file or involves a 'large amount of code.' It would conflict with virtually every coding-related skill and trigger far too broadly.

1 / 3

Total

7

/

12

Passed

Validation

100%

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

Validation11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository
addyosmani/agent-skills
Reviewed

Table of Contents

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.