Improve/skill review optimization#3
Open
yogesh-tessl wants to merge 2 commits into
Open
Conversation
## What This PR Does Hey @OrcaQubits 👋 Improves 2 skill definitions (`a2a-task-lifecycle` and `mpp-session-flow`) with expanded descriptions, executable code examples, structured verification workflows, and trimmed conceptual padding. I ran your skills through `tessl skill review` at work and found some targeted improvements. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | a2a-task-lifecycle | 67% | 90% | +23% | | mpp-session-flow | 61% | 84% | +23% | I kept this PR focused on the 2 skills with the biggest improvements to keep the diff reviewable. Happy to follow up with the rest in a separate PR if you'd like. ## Why Both skills scored well on description quality but had significant gaps in content — missing executable code examples, no verification workflows, and heavy conceptual explanations that didn't help Claude actually implement anything. The changes replace padding with actionable code and clear validation steps. ## Type of Change - [x] Documentation improvement <details> <summary>Changes summary</summary> ### a2a-task-lifecycle (67% → 90%) - Expanded description with "Agent-to-Agent" expansion and natural trigger terms ("task status tracking", "agent-to-agent workflows") - Added complete TypeScript state machine implementation with transition validation - Added task creation handler (`message/send`) with concrete code - Added 6-step verification workflow with explicit validation checkpoints - Removed "What a Task Is" conceptual section — Claude doesn't need background narration - Streamlined state transition diagram for clarity ### mpp-session-flow (61% → 84%) - Expanded description with natural trigger terms ("pay-per-use", "metered billing", "usage-based pricing") - Added complete server-side implementation with metered endpoint example - Added full client-side implementation (session open, metered requests, balance monitoring, refill, close) - Added cap exhaustion handling with 402 retry pattern - Added 6-step verification workflow - Removed "What Session Intent Is", "Payment Channel", and "Session vs Charge" comparison sections — conceptual padding replaced with executable code </details> ## Checklist - [x] Plugin follows the required directory structure (see CONTRIBUTING.md) - [x] Agent has Live Documentation Rule with official source URLs - [x] `tools` field is a comma-separated string, not a YAML list ## Attribution Skill quality evaluation and optimization performed using Tessl skill review tooling. 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. Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide (https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me - @yogesh-tessl (https://github.com/yogesh-tessl) - if you hit any snags. ## Testing Notes Each skill was reviewed with `tessl skill review` before and after changes to verify score improvements. Changes focus on adding executable code examples and verification workflows while preserving all domain-specific content and terminology. Thanks in advance 🙏
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 @OrcaQubits 👋
1,416 skills mapping the entire agentic commerce stack from UCP and A2A protocol internals to platform-specific integrations across Shopify, Magento 2, BigCommerce, WooCommerce, Salesforce, Saleor, and Medusa, with Stripe payment processing tying it together. The design philosophy of baking in stable conceptual knowledge while fetching implementation details live is the right architecture for protocols that evolve fast. Wanted to suggest a few improvements to the SKILL.md.
I ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:Changes summary
a2a-task-lifecycle (67% → 90%)
message/send) with concrete codempp-session-flow (61% → 84%)
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.
I also added a lightweight GitHub Action that auto-reviews any skill.md changed in a PR (includes min permissions, uses a pinned action version, only posts a review comment).
This means that it gives you and your contributors an instant quality signal before you have to review yourself (no signup, no tokens needed).
Want to self-improve your skills? Just point your agent (Claude Code, Codex, etc.) at this Tessl guide (https://docs.tessl.io/evaluate/optimize-a-skill-using-best-practices) and ask it to optimize your skill. Ping me - @yogesh-tessl (https://github.com/yogesh-tessl) - if you hit any snags.
Thanks in advance 🙏