common-context-optimization
Maximize context window efficiency, reduce latency, and prevent lost-in-middle issues through strategic masking and compaction. Use when token budgets are tight, tool outputs flood the context, conversations drift from intent, or latency spikes from cache misses. (triggers: *.log, chat-history.json, reduce tokens, optimize context, summarize history, clear output)
73
66%
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/common/common-context-optimization/SKILL.mdQuality
Discovery
89%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 well-structured description with strong completeness and trigger term coverage. It clearly defines when to use the skill with explicit scenarios and trigger terms. The main weakness is that the capability description leans toward abstract goals ('maximize efficiency', 'reduce latency') rather than concrete actions, which slightly reduces specificity.
Suggestions
Replace abstract goals with concrete actions, e.g., 'Summarizes conversation history, truncates verbose tool outputs, masks irrelevant log sections, and compacts repeated content to free token budget.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description names a domain (context window management) and some actions ('strategic masking and compaction'), but the actions are somewhat abstract rather than concrete. Terms like 'maximize efficiency' and 'reduce latency' are more like goals than specific operations. It doesn't list concrete steps like 'summarize conversation history, truncate tool outputs, remove redundant messages.' | 2 / 3 |
Completeness | Clearly answers both 'what' (maximize context window efficiency, reduce latency, prevent lost-in-middle issues through masking and compaction) and 'when' (explicit 'Use when' clause with four specific scenarios plus a parenthetical triggers list). | 3 / 3 |
Trigger Term Quality | Good coverage of natural trigger terms including file patterns (*.log, chat-history.json) and phrases users would actually say ('reduce tokens', 'optimize context', 'summarize history', 'clear output'). The 'when' clause also includes natural scenarios like 'token budgets are tight' and 'tool outputs flood the context.' | 3 / 3 |
Distinctiveness Conflict Risk | This occupies a clear niche around context window optimization and token management. The specific triggers like 'reduce tokens', 'optimize context', and 'lost-in-middle' are distinctive enough to avoid conflicting with general summarization or logging skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
42%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill is well-organized with good progressive disclosure and reasonable structure, but suffers from a lack of concrete, actionable guidance. The core content reads more like an architectural overview than executable instructions—key implementation details are entirely deferred to reference files, leaving the main skill body without any copy-paste-ready examples or specific commands. The anti-patterns section also redundantly restates earlier guidance.
Suggestions
Add at least one concrete, executable example inline (e.g., a before/after showing a raw tool output being masked into a summary placeholder with specific format).
Include a validation step in the observation masking workflow to verify critical data was preserved after masking (e.g., 'Verify extracted data points match expected count before discarding raw output').
Remove the anti-patterns section or merge it into the numbered sections to eliminate redundancy and improve conciseness.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Mostly efficient but includes some unnecessary framing (e.g., 'Manage the Attention Budget. Treat context as a scarce resource.' and the Problem/Solution pattern adds overhead). The anti-patterns section partially duplicates guidance already given in the numbered sections. | 2 / 3 |
Actionability | The guidance is abstract and conceptual rather than concrete. There are no executable code examples, no specific commands, and instructions like 'Mask by rewriting history to replace raw data with a summary placeholder' lack concrete implementation details. The actual actionable content is deferred to reference files. | 1 / 3 |
Workflow Clarity | Steps are listed in a reasonable sequence for each section, but validation checkpoints are absent. There's no feedback loop for verifying that masking preserved critical data or that compaction didn't lose essential state. The trigger conditions (50 lines/1KB, 10 turns/8k tokens) are helpful but lack verification steps. | 2 / 3 |
Progressive Disclosure | Content is well-structured as an overview with clear one-level-deep references to masking.md, compaction.md, and implementation.md. The references section is cleanly organized and navigation is straightforward. | 3 / 3 |
Total | 8 / 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
- HoangNguyen0403/agent-skills-standard
- Commit
19a1140
- 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.