constraint-driven-development

Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says "set up constraints" or "define our standards", when an agent keeps silencing checks or skipping tests to get to green, when you need a coverage or performance threshold and don't know what number to pick, or when an agent writes more code than anyone will read.

Quality

87%

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

75%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.

A richly actionable, well-sequenced skill body grounded in concrete commands, defaults with rationale, and verification checkpoints. Its weakness is conciseness — opinionated prose and philosophical asides pad an otherwise dense guide.

Suggestions

Trim the framing/philosophical prose in Overview and the end of Step 7 ("This also answers a fair objection to training...") to lift conciseness without losing the actionable tables.

Consider moving the large Step 4 tool-install table or the Sane Defaults table into a reference file so SKILL.md reads more as an overview, improving progressive disclosure.

Add an explicit validate-fix-retry loop note for the guard-check step (e.g., run floor-guard, address findings, re-run) to push workflow_clarity to the 5 anchor.

Dimension	Reasoning	Score
Conciseness	Dense, actionable tables earn their place, but framing prose ("Spec-driven development says what to build. Test-driven development proves it works...") and philosophical asides ("This also answers a fair objection to training. Models are rewarded for passing tests...") could be trimmed without losing utility.	3 / 5
Actionability	Provides a complete CONSTRAINTS.md template, executable npm scripts, and a tool table with real copy-paste commands and gate conditions covering the common cases across stacks.	5 / 5
Workflow Clarity	A clear seven-step sequence is reinforced by a Verification checklist, a Red Flags self-check, and a non-interactive guard; it stops just short of the 5 anchor because there is no explicit validate-fix-retry feedback loop (the skill is a setup/interview process, not a destructive op).	4 / 5
Progressive Disclosure	Well-sectioned body with one clearly-signaled, one-level-deep reference (references/floor-guard.md, confirmed to exist); the main file is long and a few inlined tables could arguably factor out, leaving minor organization gaps below the 5 anchor.	4 / 5
	Total	16 / 20 Passed

Description

100%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.

An exemplary description: third-person voice, concrete actions, explicit "Use when" triggers with natural phrasing, and a clear niche that separates it from sibling skills. No padding or over-claims.

Dimension	Reasoning	Score
Specificity	Names five concrete actions ("Establishes a project's quality bar as a written contract", "Interviews the user", "supplies sane default thresholds", "records everything in CONSTRAINTS.md", "watches the diff for a weakened bar") with specific violation patterns listed — comprehensive coverage.	5 / 5
Completeness	Explicitly answers both what (five concrete actions) and when (a full "Use when..." clause with multiple concrete trigger conditions), matching the anchor for clearly answering both.	5 / 5
Trigger Term Quality	Covers natural user phrases including "set up constraints", "define our standards", "an agent keeps silencing checks or skipping tests to get to green", and "need a coverage or performance threshold and don't know what number to pick", with synonyms and variations.	5 / 5
Distinctiveness Conflict Risk	The CONSTRAINTS.md contract / diff-guard niche is distinct from the related code-review, test-driven, and security skills named in the pack, with triggers unlikely to fire for the wrong skill.	5 / 5
	Total	20 / 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/constraint-driven-development/SKILL.md
Commit: 48cb116

Reviewed: ~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.