feat: improve skill score for using-glean-productivity#33
Open
rohan-tessl wants to merge 1 commit into
Open
Conversation
Hey @steve-calvert-glean 👋 really like how you've structured this plugin ecosystem, 9 plugins each with clean skill boundaries and cross-references back to glean-core for shared tool docs. The "Which Plugin Do I Need?" table in the README is a nice touch for discoverability. I ran your skills through `tessl skill review` at work and found some targeted improvements for `using-glean-productivity`. Here's the full before/after: | Skill | Before | After | Change | |-------|--------|-------|--------| | using-glean-productivity | 70% | 90% | +20% | | using-glean-code | 85% | 85% | 0 | | using-glean | 84% | 84% | 0 | | dev-docs-guide | 84% | 84% | 0 | | project-awareness | 69% | 69% | 0 | | skill-creation-guide | 62% | 62% | 0 | Description improvement: - replaced the vague verb "synthesize" with concrete actions "retrieve, filter, and summarize" so the skill triggers more reliably on user queries about their own activity Content improvements (biggest impact): - added a concrete 6-step workflow (load personalization, pull activity, supplement with meetings/docs, filter and classify, validate, group and format) with explicit tool calls and parameters - added a worked example showing the full call sequence for "summarize my week" with real tool invocations and grouped output - added a validation checkpoint (step 5) that handles sparse results honestly instead of padding - trimmed meta-commentary to keep the skill lean Unchanged: - reference files (activity.md, priorities.md) left as-is since they were already well-structured - cross-cutting rules preserved verbatim - all other skills left untouched I also stress-tested the using-glean-productivity skill against a few real-world task evals and it held up really well on weekly status update generation with themed grouping by ActiveProjects. 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 @rohan-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 @steve-calvert-glean 👋
really like how you've structured this plugin ecosystem, 9 plugins each with clean skill boundaries and cross-references back to glean-core for shared tool docs. The "Which Plugin Do I Need?" table in the README is a nice touch for discoverability.
I ran your skills through
tessl skill reviewat work and found some targeted improvements forusing-glean-productivity. Here's the full before/after:I also stress-tested the using-glean-productivity skill against a few real-world task evals and it held up really well on weekly status update generation with themed grouping by ActiveProjects.
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 @rohan-tessl, if you hit any snags.
Thanks in advance 🙏