feat: improve 5 lowest-scoring product skills#1
Open
rohan-tessl wants to merge 1 commit into
Open
Conversation
Hey @assimovt 👋 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 | |-------|--------|-------|--------| | jtbd-analysis | 76% | 90% | +14% | | strategy-doc | 76% | 97% | +21% | | bet-sizing | 80% | 97% | +17% | | metrics-framework | 80% | 97% | +17% | | opportunity-mapping | 81% | 97% | +16% | This PR is intentionally scoped to the 5 lowest-scoring skills to keep it reviewable. The remaining 11 skills can be improved in follow-ups or via automated review on future PRs. <details> <summary>Changes summary</summary> All changes follow your CONTRIBUTING.md conventions (50-150 line limit, `name`+`description` only frontmatter, ALWAYS/NEVER/CRITICAL rules, examples over explanations, no role-setting). **jtbd-analysis (+14%)** - Added explicit 6-step workflow with validation checkpoint (verify job statements have all three elements before proceeding) - Added complete worked example with forces table and verdict - Trimmed opening JTBD explanation — jumped straight to actionable content - Improved description specificity (map switching triggers, identify push/pull/anxiety/habit forces) **strategy-doc (+21%)** - Added 7-step workflow combining Strategy Kernel and Playing to Win with validation checkpoints - Improved description with concrete actions (diagnoses challenges, defines guiding policies, creates action plans) - Trimmed redundant "strategy is not X" explanations - Tightened prose throughout **bet-sizing (+17%)** - Added 4-step workflow with decision branching (Type 2 → lightweight, Type 1 → full pitch + EV) - Added complete worked example pitch assessment showing all sections filled out - Removed explanatory phrases Claude already knows - Condensed appetite ranges into single line **metrics-framework (+17%)** - Added 5-step workflow with validation checkpoint (sustainability test for North Star) - Added concrete output template (metric name, formula, data source, counter-metric, baseline, target) - Trimmed redundant guideline items **opportunity-mapping (+16%)** - Added 6-step workflow with validation checkpoint (verify opportunities framed as customer needs) - Added complete example OST with table showing opportunities, solutions, and experiments - Improved description specificity (create tree structures, generate solution hypotheses, define assumption tests) - Consolidated level descriptions to reduce redundancy </details> 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.
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 👋 @VenTheZone
I ran your skills through
tessl skill reviewat work and found some targeted improvements.Here's the full before/after:
This PR is intentionally scoped to 5 skills to keep the contribution focused and reviewable — more skills can be improved in follow-ups.
Changes made
All 5 skills received these improvements:
specialist-security-reviewer (+71%): Restructured into a clear 5-step workflow with automated scan commands, compressed OWASP Top 10 into an actionable checklist, and added BAD/GOOD code patterns for critical vulnerabilities.
specialist-refactor-cleaner (+66%): Added SAFE/CAREFUL/RISKY categorization scheme, structured detection-to-removal workflow with test-after-each-batch checkpoints, and streamlined deletion log format.
specialist-rust-reviewer (+55%): Added diagnostic commands upfront, structured review into a 7-step workflow including clippy and unsafe audit steps, and trimmed textbook ownership examples.
specialist-architect (+48%): Condensed architectural principles and common patterns into scannable lists, added a concrete ADR template, and structured the review into a clear 5-step workflow.
eval-harness (+41%): Restructured eval types and grader types with cleaner formatting, added pass@k metrics table, and streamlined the workflow with explicit iteration criteria.
Want your remaining skills optimised too? 🚀
This PR covers 5 of your 88 skills to keep the contribution focused and reviewable. We have tooling that can go further:
SKILL.mdchanged in future PRs. Review mode works with zero secrets; maintainers can addTESSL_API_TOKENfor AI suggestions and the/apply-optimizecomment flow.Interested? Just tick the box below and we'll raise a follow-up PR:
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 and ask it to optimize your skill. Ping me - @rohan-tessl - if you hit any snags.
Thanks in advance 🙏