docs: improve develop skill structure + add skill-review-and-optimize CI#77
Closed
fernandezbaptiste wants to merge 1 commit intoTheBushidoCollective:mainfrom
Closed
Conversation
- sharpen frontmatter description with trigger terms like add a feature, implement a capability - remove duplicate sections (Name, Synopsis, Description repeated same sentence) - replace pseudocode with executable TypeScript test examples + real bash commands - consolidate DO/DON'T best practices into inline phase guidance - convert agent list from verbose bullets to compact table - net reduction from 446 to 274 lines - add .github/workflows/skill-review.yml for automated skill review + optimize on PRs - add .github/workflows/skill-apply-optimize.yml for /apply-optimize command
Collaborator
|
Thanks for the contribution and the kind words about Han, @fernandezbaptiste. After reviewing, we're going to close this PR. The skill text edits have some good ideas (removing duplicate boilerplate, tighter phrasing), but the two GitHub Actions workflows ( If you'd like to submit the SKILL.md text improvements as a standalone PR without the tessl workflows, we'd be happy to review that separately. |
jwaldrip
added a commit
that referenced
this pull request
Mar 27, 2026
- Enrich description with trigger terms for better skill matching - Remove 4 redundant sections (Name, Synopsis, Description, Implementation) that repeated 'Comprehensive 8-phase workflow' verbatim - Remove stale Usage section referencing non-existent /feature-dev command - Update See Also to reference current skill names Inspired by observations in #77 (without the third-party CI dependency). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
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 @TheBushidoCollective, thanks for building han. really like the Bushido philosophy applied to agent orchestration. Kudos on passing
100stars mark! I've just starred it.ran your develop skill through agent evals and spotted a few quick wins that took it from
~42%to~100%performance:sharpened description with trigger terms like add a feature, implement a capability + removed duplicate sections that repeated the same sentence
replaced pseudocode with executable TypeScript test examples + real bash commands, net reduction from 446 to 274 lines
consolidated DO/DON'T best practices into inline phase guidance + converted agent list to compact table
also added a GitHub Action (
skill-review.yml) that freely reviews anyskill.mdchanged in a PR. review mode works out of the box with no auth and posts a score comment.these were easy changes to bring the skill in line with what performs well against Anthropic's best practices. honest disclosure, I work at tessl.io where we build tooling around this. not a pitch, just fixes that were straightforward to make.
optionally, you can enable optimize mode by adding a token as
TESSL_API_TOKENin your repo secrets. when enabled, the action suggests improvements you can accept by commenting/apply-optimize. this means that it gives you and your contributors an instant quality signal before you have to review yourself.happy to answer any questions on the changes.