feat: improve content-editing skill score (56% → 90%)#7207
Open
yogesh-tessl wants to merge 1 commit into
Open
Conversation
## Summary Hey @jstirnaman 👋 I ran your skills through `tessl skill review` at work and found some targeted improvements for the `content-editing` skill. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | content-editing | 56% | 90% | +34% | | docs-cli-workflow | 63% | — | — | | hugo-template-dev | 67% | — | — | | vale-rule-config | 70% | — | — | | influxdb3-test-setup | 73% | — | — | | vale-linting | 77% | — | — | | cypress-e2e-testing | 83% | — | — | I picked `content-editing` because it had the most improvement headroom (56%) and it's arguably the most central skill in a docs repo — creating and editing content is the core workflow. <details> <summary><b>Changes made</b></summary> - **Rewrote frontmatter description** with specific capabilities, natural trigger terms (`markdown`, `.md files`, `InfluxDB`, `Telegraf`, `Flux`, `Hugo`, `Vale`), and an explicit "Use when..." clause — this alone moved Description from 33% to 100% - **Removed redundant "Purpose" section** — Claude infers purpose from the content itself - **Eliminated duplicate Vale section** (old Part 3) that repeated Part 2 Section 6 and the `vale-linting` skill; replaced with a compact quick reference - **Condensed MCP fact-checking section** — kept actionable content (setup, example queries, use/don't-use guidance), removed verbose prose - **Compressed 3 example workflows** into compact versions that preserve the commands without lengthy inline comments - **Converted troubleshooting** from verbose subsections into a single reference table - **Reduced file from 622 to 402 lines** (35% reduction) while preserving all domain-specific content (Hugo shared content patterns, frontmatter handling, sourcing file touch requirement) </details> I also stress-tested your `cypress-e2e-testing` skill against a few real-world task evals and it held up really well on Hugo server lifecycle management during parallel E2E spec runs. 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 🙏 ## Checklist - [ ] Signed the [InfluxData CLA](https://www.influxdata.com/legal/cla/) ([if necessary](https://github.com/influxdata/docs-v2/blob/master/DOCS-CONTRIBUTING.md#sign-the-influxdata-cla)) - [x] Rebased/mergeable - [ ] Local build passes (`npx hugo --quiet`)
jstirnaman
reviewed
May 12, 2026
Contributor
jstirnaman
left a comment
jstirnaman
left a comment
There was a problem hiding this comment.
Thanks for the suggestions! I'm impressed by how much you deleted. I'll give it a try.
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
2 participants
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 @jstirnaman 👋
this is seriously well put together. The 7 skills covering everything from Vale linting to Cypress e2e testing give it a really solid foundation, and the layered instruction setup across AGENTS.md, CLAUDE.md, and Copilot instructions shows a lot of care in how AI is integrated into the workflow. It’s honestly one of the most thoughtfully AI-instrumented docs repos I’ve come across.
ran your skills through
tessl skill reviewat work and found some targeted improvements for thecontent-editingskill. Here's the full before/after:I picked
content-editingbecause it had the most improvement headroom (56%) and it's arguably the most central skill in a docs repo, creating and editing content is the core workflow.Changes made
markdown,.md files,InfluxDB,Telegraf,Flux,Hugo,Vale), and an explicit "Use when..." clause - this alone moved Description from 33% to 100%vale-lintingskill; replaced with a compact quick referencequick 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.