feat: improve report skill score from 44% to 95%#4
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
Hey @sjarmak 👋 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 | |-------|--------|-------|--------| | report | 44% | 95% | **+51%** | | audit | 69% | — | — | | evaluate | 59% | — | — | | infra | 54% | — | — | | next | 56% | — | — | | run | 71% | — | — | | scaffold | 59% | — | — | | status | 73% | — | — | | triage | 62% | — | — | The `report` skill had the most headroom — it was missing explicit trigger guidance and a structured workflow, which dragged its score down despite having solid domain content underneath. <details> <summary>Changes made to <code>report</code> skill</summary> - **Expanded frontmatter description** with domain context (CodeScaleBench, baseline vs MCP) and an explicit "Use when..." clause with natural trigger terms (`benchmark results`, `cost breakdowns`, `config comparisons`, `MCP impact analysis`, `pass-rate summaries`) - **Added a 4-step reporting workflow** — verify run completion → generate report → compare configs → review for anomalies — so the agent follows a sensible sequence instead of picking commands at random - **Replaced flat command list with a decision table** mapping each reporting goal to the right command, making it easy to pick the correct script - **Tightened scope bullets** to be more specific about what this skill handles (benchmark runs, token spending by model/suite, baseline vs MCP comparisons) - **Preserved all domain terminology** — MCP, Sourcegraph, oracle, baseline, IR, dual verification — untouched </details> I also stress-tested your `run` skill against a few real-world task evals and it held up really well on paired baseline+MCP execution with multi-account orchestration guardrails. Kudos for that. 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. 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 @sjarmak 👋
this is really impressive work. The 20 skills cover the full benchmarking lifecycle in a very practical way, from task mining to trace evaluation and cost reporting. The
ir-analysisandmcp-auditskills especially stand out as thoughtful additions. Having a skillsREADME.mdalongside.claude/commandsalso shows real commitment to making the repo easy for agents to discover, understand, and use.ran your skills through
tessl skill reviewat work and found some targeted improvements. Here's the full before/after:The
reportskill had the most headroom. It was missing explicit trigger guidance and a structured workflow, which dragged its score down despite having solid domain content underneath.Changes made to
reportskillbenchmark results,cost breakdowns,config comparisons,MCP impact analysis,pass-rate summaries)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.