rtk-optimizer
Wrap high-verbosity shell commands with RTK to reduce token consumption. Use when running git log, git diff, cargo test, pytest, or other verbose CLI output that wastes context window tokens.
79
75%
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 ./examples/skills/rtk-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, well-crafted description that clearly communicates what the skill does (wrapping verbose CLI commands with RTK), why (to reduce token consumption), and when to use it (with specific command examples). It uses third person voice, includes natural trigger terms, and occupies a distinct niche that minimizes conflict risk.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists a specific concrete action ('Wrap high-verbosity shell commands with RTK to reduce token consumption') and names specific commands (git log, git diff, cargo test, pytest). The description clearly states what the skill does. | 3 / 3 |
Completeness | Clearly answers both 'what' (wrap high-verbosity shell commands with RTK to reduce token consumption) and 'when' (explicit 'Use when' clause listing specific triggers: git log, git diff, cargo test, pytest, or other verbose CLI output). | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would encounter: 'git log', 'git diff', 'cargo test', 'pytest', 'verbose CLI output', 'context window tokens', 'token consumption'. These are terms a user or Claude would naturally associate with this need. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche — wrapping verbose shell commands with RTK for token reduction is a very specific use case unlikely to conflict with other skills. The mention of RTK and token consumption clearly differentiates it. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
50%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill provides a useful and well-organized reference for RTK command mappings with concrete reduction percentages, but suffers from moderate verbosity through duplicated information (metrics repeating the supported commands section) and meta-descriptions of how the skill itself works. The workflow lacks validation steps for verifying compressed output completeness, and the 'Usage Pattern' section reads more like a behavioral template than actionable guidance.
Suggestions
Remove the 'How It Works' and 'Activation Examples' sections — Claude doesn't need meta-instructions about detecting user intent; just provide the command mappings and let Claude use them.
Consolidate the 'Supported Commands' and 'Metrics' sections into a single table to eliminate duplication of the same commands and percentages.
Add a validation/fallback step to the workflow: 'If RTK output seems incomplete or truncated, re-run without RTK wrapper to get full output.'
Remove time-sensitive information like '446 stars on GitHub' and '30 releases in 23 days' from Limitations, as these will quickly become stale.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill includes some unnecessary content like the 'Activation Examples' section (Claude doesn't need to be shown how to detect user intent), the 'How It Works' meta-description of the skill itself, and the GitHub stars mention in Limitations. The metrics table partially duplicates the supported commands section. However, the core command mappings are efficiently presented. | 2 / 3 |
Actionability | The command mappings are concrete and useful (e.g., `git log` → `rtk git log`), and installation commands are copy-paste ready. However, the 'Usage Pattern' section is written in pseudocode/markdown template format rather than executable guidance, and the 'Session Tracking' section is thin. The skill describes a behavioral pattern more than providing executable code. | 2 / 3 |
Workflow Clarity | The usage pattern provides a basic sequence (detect → suggest → execute → track), but there's no validation checkpoint for verifying RTK actually produced correct/complete output. For a tool that compresses output by 90%, there should be guidance on when to fall back to the uncompressed command if information is lost. The installation check is a good step but the overall workflow lacks error recovery. | 2 / 3 |
Progressive Disclosure | The skill references external files (docs/resource-evaluations/rtk-evaluation.md, examples/claude-md/rtk-optimized.md) which is good, but the main file itself is quite long with sections that could be split out (e.g., the full metrics table, the configuration template). The structure is reasonable with clear headers, but the content is somewhat monolithic for its length. | 2 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Commit
746adc8
- 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.