context-optimizer

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

Quality

58%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./skills/context-optimizer/SKILL.md

Quality

Content

77%

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

This is a solid, actionable skill with clear decision points and concrete commands/thresholds. Its main strength is the combination of diagnostic steps, specific configuration, and escalation workflows. The primary weakness is some unnecessary verbosity in sections that explain behaviors Claude already understands (like avoiding sycophantic openers), and the content could benefit from splitting detailed reference material into separate files.

Suggestions

Move the detailed 'Token Efficiency' subsections (Output Reduction, Behavioral Efficiency, Task Profiles) into a separate REFERENCE.md file, keeping only a summary line and link in the main SKILL.md

Remove items that instruct Claude on its own behavior patterns it already knows (e.g., 'No sycophantic openers', 'No prompt restatement') — these are better placed in CLAUDE.md as behavioral directives rather than in a skill document

Dimension	Reasoning	Score
Conciseness	Generally efficient with good use of tables and bullets, but some sections explain things Claude already knows (e.g., 'No sycophantic openers', 'No closing fluff' are behavioral instructions Claude can follow without examples). The prompt engineering tips and some behavioral efficiency items are somewhat obvious to Claude. However, the overall structure is reasonably tight.	2 / 3
Actionability	Provides concrete commands (/compact, /context, /resume, /mcp), specific configuration JSON for auto-compaction, clear thresholds (70%, 90%), specific tool-call budgets (20-80), and actionable tables with specific actions and triggers. The guidance is immediately executable.	3 / 3
Workflow Clarity	The Quick Diagnosis section provides a clear decision tree (check → threshold → action). The Context Budget Planning table gives explicit phase-based thresholds with escalation actions. The 'When Context Is Degraded' section provides a clear escalation sequence (compact → resume → reduce). For a non-destructive optimization skill, this level of workflow clarity is excellent.	3 / 3
Progressive Disclosure	The content is well-organized with clear headers and sections, but it's all inline in a single file with no references to supporting documents. Some sections like 'Token Efficiency' and 'CLAUDE.md Optimization' could be split into separate reference files. For a skill of this length (~100 lines of content), it's borderline but leans toward needing better separation.	2 / 3
	Total	10 / 12 Passed

Description

40%

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 too vague about what concrete actions the skill performs—it says 'optimize' without specifying how (e.g., summarize context, prune messages, compress prompts). While it includes a 'Use when' clause, the triggers are subjective ('feel slow', 'degraded') rather than concrete. The use of second person ('you're') violates the voice guidelines.

Suggestions

Replace the vague 'optimize token usage and context management' with specific actions like 'Summarizes conversation history, prunes redundant context, and compresses prompts to reduce token consumption.'

Expand trigger terms to include common user phrases like 'token limit', 'context window full', 'too expensive', 'cost reduction', 'rate limit', 'running out of tokens'.

Rewrite in third person voice—change 'you're running out of budget' to 'the user is approaching token budget limits' or similar phrasing.

Dimension	Reasoning	Score
Specificity	The description uses vague language like 'optimize token usage and context management' without listing any concrete actions. What specific steps does this skill perform? There are no actionable capabilities described.	1 / 3
Completeness	Has a weak 'what' (optimize token usage and context management) and does include a 'Use when' clause with triggers ('sessions feel slow, context is degraded, running out of budget'), but the 'what' is too vague to fully satisfy completeness. The 'when' clause is present but the triggers are somewhat subjective and imprecise.	2 / 3
Trigger Term Quality	Includes some relevant terms like 'token usage', 'context', 'budget', and 'slow' that users might mention, but misses common variations like 'rate limit', 'cost', 'tokens', 'context window', 'context length', or 'performance'. Also uses second person 'you're' which is a voice issue.	2 / 3
Distinctiveness Conflict Risk	The domain of token/context optimization is somewhat specific, but 'sessions feel slow' could overlap with performance optimization skills, and 'context management' is broad enough to conflict with various other skills related to conversation management or memory.	2 / 3
	Total	7 / 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 — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: rohitg00/pro-workflow
Commit: 5c313e2

Reviewed: 12 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.