context-engineering

Optimize Claude Code context usage through monitoring, reduction strategies, progressive disclosure, planning/execution separation, and file-based optimization. Task-based operations for context window management, token efficiency, and maintaining conversation quality. Use when managing token costs, optimizing context usage, preventing context overflow, or improving multi-turn conversation quality.

Quality

72%

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/context-engineering/SKILL.md

Quality

Content

56%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 content is well-structured and actionable with clear workflows, but it is conspicuously verbose for a skill whose purpose is context efficiency, and it self-contradicts by inlining detail while pointing to non-existent reference files. Tightening the body and providing the referenced bundle files would materially improve it.

Suggestions

Collapse the redundant 'Best Practices' and 'Common Mistakes' sections into the Operations they restate, and remove explanations of concepts Claude already knows (auto-compaction thresholds, basic Grep/Glob behavior) to cut the body substantially.

Create the referenced bundle files (references/context-monitoring-guide.md, references/reduction-strategies.md, references/optimization-patterns.md, scripts/analyze-context-usage.py) or remove the dangling references, since currently the 'For More Information' links resolve to nothing.

Move the large Quick Reference tables and per-operation examples into references/ so SKILL.md is a lean overview that practices the progressive disclosure it preaches.

Dimension	Reasoning	Score
Conciseness	The ~757-line body is noticeably verbose, restating the same five operations across 'Overview', 'Operations', 'Best Practices', and 'Common Mistakes' sections, and explaining concepts Claude already knows (auto-compaction thresholds, basic Grep/Glob usage).	2 / 5
Actionability	Provides concrete, mostly executable guidance: the `/context` command, file-externalization bash snippets, a decision tree, and 'Quick Optimization Actions'; minor gaps remain where illustrative command output is not runnable.	4 / 5
Workflow Clarity	Each operation is a clearly numbered process with a 'Validation Checklist' and example, giving good sequencing and checkpoints; the operations are advisory rather than destructive, so the strict validation cap does not apply.	4 / 5
Progressive Disclosure	Sections are headed and references are signaled one level deep at the end, but the referenced bundle files (references/context-monitoring-guide.md, reduction-strategies.md, optimization-patterns.md, scripts/analyze-context-usage.py) do not exist, and much detail that the skill's own doctrine says belongs in references is inlined.	3 / 5
	Total	13 / 20 Passed

Description

88%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 is strong: it lists multiple concrete operations, provides explicit 'Use when' trigger guidance, and occupies a distinct niche. Minor gaps in keyword synonym coverage and slight overlap risk keep trigger quality and distinctiveness at 4 rather than 5.

Dimension	Reasoning	Score
Specificity	Names the domain plus five concrete operations ('monitoring, reduction strategies, progressive disclosure, planning/execution separation, and file-based optimization'), matching the comprehensive-coverage anchor.	5 / 5
Completeness	Explicitly states what it does (five optimization operations) and when to use it ('Use when managing token costs, optimizing context usage, preventing context overflow, or improving multi-turn conversation quality').	5 / 5
Trigger Term Quality	Includes natural phrases users say ('token costs', 'context usage', 'context overflow', 'multi-turn conversation quality') but lacks synonyms or shorthand variations, leaving a few common terms missing.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear context-engineering niche with distinct triggers, though it could overlap slightly with general performance/optimization skills.	4 / 5
	Total	18 / 20 Passed

Validation

81%

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 — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (757 lines); consider splitting into references/ and linking	Warning
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
referenced_paths_exist	Referenced path issues: 5 missing	Warning

	Total	13 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/context-engineering/SKILL.md
Commit: 93ed392

Reviewed: 1 day 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.