feat: improve blazemeter-administration skill score (82% → 93%)#77
Draft
yogesh-tessl wants to merge 1 commit into
Draft
feat: improve blazemeter-administration skill score (82% → 93%)#77yogesh-tessl wants to merge 1 commit into
yogesh-tessl wants to merge 1 commit into
Conversation
Hey @Baraujo25 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for `blazemeter-administration`. Here's the before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | blazemeter-administration | 82% | 93% | +11% | The other 14 skills were already solid — baselines ranged from 70% to 82% across the board. I focused on `blazemeter-administration` since it's the account-level entry point and had the clearest path to improvement. Changes made: - MCP tools table: Replaced verbose bullet-list of tools with a compact reference table showing tool name, action, required args, and purpose - Concrete invocation examples: Added actual argument formats (e.g., {"account_id": 12345}) to example workflows so they're copy-paste ready - Validation checkpoints: Added verification steps to workflows — check for valid account IDs before proceeding, verify responses have no error field, handle AI consent errors gracefully - New workflow: Added "Listing Available Test Locations" example showing read_locations with purpose filtering - Removed redundancy: Eliminated the duplicate "When to Use Each Reference" section and the generic "Overview" section - Flattened references: Collapsed per-reference sub-headers into a single clean list with richer inline descriptions Honest disclosure — I work at @tesslio where we build tooling around skills like these. Not a pitch — just saw room for improvement and wanted to contribute.
Author
|
hey @Baraujo25, just checking in on this one, happy to make any changes if something needs tweaking! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hey @Baraujo25 👋
truly impressive work. 15 skills that map the entire BlazeMeter platform, from getting started guides through performance testing, API monitoring, service virtualisation, and scripting. The troubleshooting skill alongside the detailed private locations and network security skills shows you're covering the real-world complexity that teams actually hit when running load tests at scale.
ran your skills through
tessl skill reviewat work and found some targeted improvements forblazemeter-administration. Here's the before/after:the other 14 skills were already solid, baselines ranged from 70% to 82% across the board. I focused on
blazemeter-administrationsince it's the account-level entry point and had the clearest path to improvement.Changes made
Content improvements (biggest impact):
{"account_id": 12345}) to example workflows so they're copy-paste readyerrorfield, handle AI consent errors gracefullyread_locationswith purpose filteringUnchanged:
also stress-tested your
blazemeter-administrationskill against a few real-world task evals and it held up really well on multi-workspace account discovery with AI consent validation chains. Kudos for that.quick honest disclosure. I work at https://github.com/tesslio where we build tooling around skills like these. Not a pitch, just saw room for improvement and wanted to contribute.
If you want to self-improve your skills, or define your own scenarios to pressure test, just ask your agent (Claude Code, Codex, etc.) to evaluate and optimize your skill with Tessl. Ping me @yogesh-tessl, if you hit any snags.