context-optimizer

Optimize token usage and context management. Use when sessions feel slow, context is degraded, or you're running out of budget.

Quality

82%

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

100%Weight 40%Scale 1-3

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

The body is an exemplary lean, actionable operational reference: dense tables and commands, clear conditional workflows with escalation loops, and clean single-file organization that respects the token budget it advocates.

Dimension	Reasoning	Score
Conciseness	The body is lean and table/bullet driven, assumes Claude's competence (no explanations of what compaction, MCPs, or subagents are), and follows its own ASCII-only token-efficiency guidance.	3 / 3
Actionability	Concrete executable commands (/context, /compact, /resume, /mcp), a copy-paste JSON config block, specific thresholds (>70%, <80 tools, 20-80 tool-call budget), and ready-to-use prompt examples make the guidance fully actionable.	3 / 3
Workflow Clarity	Quick Diagnosis gives a sequenced flow with conditional checkpoints (>70%, >90%), and 'When Context Is Degraded' provides an explicit escalation feedback loop (/compact -> if still bad /resume -> if recurring reduce CLAUDE.md).	3 / 3
Progressive Disclosure	A single well-organized file with clearly headed navigable sections and no nested or poorly-signaled references; absence of bundle files is appropriate for this compact operational skill.	3 / 3
	Total	12 / 12 Passed

Description

65%Weight 40%Scale 1-3

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 covers what the skill does and when to invoke it with explicit triggers and low conflict risk, but it is held back by an abstract single verb and second-person voice that costs it specificity.

Suggestions

Replace the abstract 'Optimize' with concrete actions, e.g. 'Diagnose context usage, trigger compaction, and prune MCP overhead'.

Rewrite in third person to avoid the specificity penalty: drop 'you're running out of budget' in favor of 'Use when sessions feel slow, context is degraded, or the token budget is nearly exhausted'.

Add natural trigger variations users actually say, such as 'context is full', 'running out of tokens', or 'session feels sluggish'.

Dimension	Reasoning	Score
Specificity	Names the domains ('token usage', 'context management') with one abstract action ('Optimize'), which is anchor-2 territory, but the second-person phrasing 'you're running out of budget' triggers the mandated -1 voice penalty, dropping it to 1.	1 / 3
Completeness	Clearly answers 'what' ('Optimize token usage and context management') and 'when' with an explicit 'Use when...' trigger clause, matching the anchor for full completeness.	3 / 3
Trigger Term Quality	'sessions feel slow' and 'running out of budget' are natural user phrases, but 'context is degraded' is jargon and common variations like 'context full' or 'out of tokens' are missing.	2 / 3
Distinctiveness Conflict Risk	Context/budget optimization is a clear niche with triggers tied to session performance and budget that are unlikely to fire for unrelated file-format or coding skills.	3 / 3
	Total	9 / 12 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: rohitg00/pro-workflow
Path: skills/context-optimizer/SKILL.md
Commit: 7f7209d

Reviewed: 8 days 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.