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

75%

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

71%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 thorough, actionable instruction skill whose templates and sequenced workflows are its main strength. The main weaknesses are padding (rationalizations/red flags) and the absence of any progressive disclosure via references or split files.

Suggestions

Trim or remove the 'Common Rationalizations' and 'Red Flags' sections, which restate conventions Claude already knows and overlap with 'When to Use'.

Split the CLAUDE.md template and the MCP integrations table into separate reference files (e.g. references/claude-md-template.md, references/mcp.md) and link to them from the body to improve progressive disclosure.

Tighten the Overview to a single sentence and move the philosophy into a one-level-deep reference so the body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	The body is largely actionable, but the Common Rationalizations table, Red Flags list, and overview prose restate ideas Claude already knows and could be trimmed, matching the 'mostly efficient with some unnecessary explanation' anchor.	3 / 5
Actionability	It provides copy-paste-ready templates (CLAUDE.md, Brain Dump, Selective Include, Hierarchical Summary, confusion blocks) that cover the common context-setup cases with concrete, specific guidance.	5 / 5
Workflow Clarity	Pre-task context loading is a clear numbered sequence and the Verification section provides an explicit checklist, but there is no strict validate-then-retry feedback loop (the skill is advisory rather than destructive, so no cap applies).	4 / 5
Progressive Disclosure	The document has strong section structure, but it is a ~290-line monolith with no bundle files and no references; content such as the CLAUDE.md template or MCP table that could live in separate files is fully inlined.	3 / 5
	Total	15 / 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 well-constructed description that pairs a clear purpose statement with an explicit, multi-trigger 'Use when' clause. It is strong on completeness and trigger quality, slightly less so on enumerating concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain ('agent context setup') and one concrete action ('configure rules files and context for a project'), but does not enumerate several specific operations, so it falls short of the multi-action anchor 4.	3 / 5
Completeness	It states what the skill does and provides an explicit 'Use when' clause with multiple concrete trigger phrases, satisfying both halves of the anchor 5.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('starting a new session', 'switching between tasks', 'agent output quality degrades'), giving good keyword coverage, though a few synonyms or extension-style terms are missing.	4 / 5
Distinctiveness Conflict Risk	The rules-files/context-configuration niche is mostly distinct, but generic triggers like 'starting a new session' create minor overlap risk with project-setup 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/context-engineering/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.