context-engineering

Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/context-engineering/SKILL.md

Quality

Content

67%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.

This is a well-structured, actionable practices skill with strong templates, clear hierarchy, and useful checklists. Its main weakness is verbosity — conceptual explanation and overlapping tables that restate guidance Claude largely already knows.

Suggestions

Trim conceptual padding: collapse 'Common Rationalizations' into 'Anti-Patterns' (or remove it) and drop the Overview's restatement of why context matters.

Externalize the MCP integrations table and the full CLAUDE.md/PROJECT CONTEXT templates into references/ so the body stays a lean overview.

Convert the 'Context Packing Strategies' prose into one concise decision table (situation → template) to cut tokens while preserving actionability.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient but carries padding — the Overview's 'Context is the single biggest lever...' explainer, plus overlapping 'Common Rationalizations' and 'Anti-Patterns' tables that restate the same guidance. It is not a 4 because several sections re-explain concepts Claude already knows rather than just instructing.	3 / 5
Actionability	Concrete copy-paste-ready templates (CLAUDE.md, PROJECT CONTEXT, TASK, CONFUSION, PLAN) and specific numbered pre-task loading steps give mostly executable guidance. It is not a 5 because some sections (MCP table, Rationalizations) are advisory rather than directly actionable.	4 / 5
Workflow Clarity	Sequences are clear — the 5-level persistent-to-transient hierarchy, numbered pre-task loading steps (1-4), and a final Verification checklist — with feedback patterns (surface confusion → ask → proceed; inline plan → execute unless redirected). It is not a 5 because this is a practices compendium rather than one coherent workflow with explicit validate-fix-retry checkpoints throughout.	4 / 5
Progressive Disclosure	No bundle files exist (references/, scripts/, assets/ absent) and the SKILL.md is self-contained with strong, well-labeled section hierarchy and navigation. It is not a 5 because at ~330 lines some material (MCP integrations table, detailed templates) could be externalized into reference files, though inline placement is defensible for a practices skill.	4 / 5
	Total	15 / 20 Passed

Description

65%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 cleanly pairs a capability statement with an explicit, multi-trigger 'Use when' clause, which is its main strength. Its weakness is a generic 'what' ('optimizes agent context setup') that lacks concrete enumerated actions.

Suggestions

Replace 'Optimizes agent context setup' with concrete actions, e.g. 'Curates rules files, structures context loading, and manages context budget for AI coding agents'.

Add natural keyword synonyms users might say (e.g. 'agent context', 'rules files', 'context window') alongside the scenario triggers.

Tighten the 'what' so it reads as a crisp capability rather than a single generic verb ('optimizes').

Dimension	Reasoning	Score
Specificity	The phrase 'Optimizes agent context setup' names the domain but the action is minimal and generic ('optimizes', 'setup') rather than a list of concrete actions, matching the score-2 anchor 'Names the domain but actions are minimal or generic'. It is not a 3 because no 1-2 concrete actions (e.g. 'curate rules files', 'trim stale context') are explicitly enumerated.	2 / 5
Completeness	Both 'what' ('Optimizes agent context setup') and an explicit 'when' ('Use when...') with multiple concrete triggers are present. It is not a 5 because the 'what' is somewhat generic rather than a crisp capability statement, leaving it slightly below the comprehensive anchor.	4 / 5
Trigger Term Quality	Natural trigger phrases are present — 'starting a new session', 'agent output quality degrades', 'switching between tasks', 'configure rules files' — giving good coverage of scenarios a user would voice. It is not a 5 because there are few synonyms or keyword variations beyond these scenario descriptions.	4 / 5
Distinctiveness Conflict Risk	'Agent context setup' and 'configure rules files and context' carve a fairly distinct niche with specific triggers, giving mostly distinct identity with only minor overlap with general project-setup skills. It is not a 5 because some triggers ('setting up a new project') could overlap with broader scaffolding skills.	4 / 5
	Total	14 / 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/context-engineering/SKILL.md
Commit: 48cb116

Reviewed: ~19 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.