context-optimizer
Audits agent context window usage via debug logs, token profiling, and redundancy detection. USE FOR: context optimization, token waste analysis, debug log parsing, hand-off gap analysis. DO NOT USE FOR: Azure infrastructure, Bicep/Terraform code, architecture design, deployments.
83
78%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.github/skills/context-optimizer/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines a specific niche (agent context window auditing), lists concrete actions, provides explicit trigger terms via the USE FOR clause, and proactively reduces conflict risk with a DO NOT USE FOR exclusion list. The description is concise, uses third person voice, and covers all key dimensions effectively.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'audits agent context window usage', 'debug logs', 'token profiling', 'redundancy detection'. These are clear, actionable capabilities. | 3 / 3 |
Completeness | Clearly answers 'what' (audits context window usage via debug logs, token profiling, redundancy detection) and 'when' (USE FOR clause with explicit triggers). The DO NOT USE FOR clause adds further clarity on boundaries. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'context optimization', 'token waste analysis', 'debug log parsing', 'hand-off gap analysis', 'context window'. These are terms a user working with agent context issues would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused on agent context window auditing. The explicit DO NOT USE FOR clause listing Azure infrastructure, Bicep/Terraform, architecture design, and deployments actively reduces conflict risk with related DevOps/infrastructure skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has excellent structure and progressive disclosure, clearly pointing to detailed references with a useful index table. However, it leans too heavily on delegation—the main skill file lacks enough inline actionable content (concrete examples, a summarized workflow with checkpoints) for Claude to begin work without immediately loading references. The conciseness is reasonable but could be tightened by removing the capability table and trimming the 'When to Use' section.
Suggestions
Add a condensed 3-5 step workflow summary with validation checkpoints directly in the skill body (even if the full methodology lives in the reference), so Claude can orient without loading references first.
Include at least one concrete example of parsed log output or a sample analysis finding to make the skill immediately actionable.
Remove or condense the 'Quick Reference' capability table since it largely restates what's described in the methodology reference link just below it.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is mostly efficient but includes some unnecessary sections like the 'When to Use This Skill' list (which overlaps with the description), the 'Quick Reference' capability table that largely restates what's in the methodology reference, and the 'Portability' section with step-by-step copy instructions that add moderate bloat without high value. | 2 / 3 |
Actionability | The skill provides one concrete command (the find command for debug logs) but delegates nearly all substantive methodology to `references/analysis-methodology.md`. The main file itself lacks executable code, specific examples of log parsing output, or concrete steps Claude can immediately follow without loading references. | 2 / 3 |
Workflow Clarity | The multi-step analysis workflow (Steps 1-5) is entirely delegated to the reference file rather than being summarized with clear sequencing and validation checkpoints in the skill itself. The portability section has clear steps but that's a setup workflow, not the core analysis workflow. No validation or feedback loops are present for the analysis process. | 2 / 3 |
Progressive Disclosure | The skill excels at progressive disclosure with a clear overview, well-signaled one-level-deep references (analysis-methodology.md, optimization-report.md, token-estimation.md), a reference index table explaining when to load each file, and appropriate separation of concerns between the overview and detailed materials. | 3 / 3 |
Total | 9 / 12 Passed |
Validation
100%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
- jonathan-vella/azure-agentic-infraops
- Commit
ec7b8ff
- Reviewed
Table of Contents
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.