feat(han-communication): add the han-readability output style - #174
Merged
Conversation
Distill the readability rule and the writing-voice profile that readability-guidance surfaces into a single output style, so the standard applies to every turn instead of only to skills that invoke the guidance. The style lives in the default auto-discovered output-styles/ directory, so plugin.json needs no outputStyles field. It sets keep-coding-instructions so Claude keeps its software engineering behavior. The config-driven writing-voice override does not port: an output style is static system-prompt text loaded at session start and cannot probe .han/config.md, so the built-in Han voice is hardcoded.
Output styles are a new component kind for this repo, so the surfaces that describe what han-communication ships had no entry for one. - han-communication/README.md gains an Output styles section - docs/readability.md gains a session-wide section naming the three limits (no subagent reach, built-in voice only, derived copy) - docs/choosing-a-han-plugin.md and CONTRIBUTING.md name it in the han-communication scent - CLAUDE.md gains the output-styles/ layout line and a doc-map entry warning that the style is derived from the canonical rule and voice files
…ability The coverage rule bound long-form docs to skills and agents only, so the han-readability output style had no doc and no rule requiring one. Extend the rule to output styles and add an output-style variant section, following the precedent the inline-guidance variant set: describe the heading deviations in the rule itself rather than adding a fourth template file. The variant renames the two invocation headings (a style is selected once, not called), replaces "What you get back" with "What it changes" (no artifact), and adds "What it does not reach" for the boundaries that surprise people. It drops "How to get the most out of it", "YAGNI", and "Sources". Point the plugin README scent line and the readability page at the new long-form doc rather than at the style file, per the canonical-source convention.
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.
Distill the readability rule and the writing-voice profile that readability-guidance surfaces into a single output style, so the standard applies to every turn instead of only to skills that invoke the guidance.
The style lives in the default auto-discovered output-styles/ directory, so plugin.json needs no outputStyles field. It sets keep-coding-instructions so Claude keeps its software engineering behavior.
The config-driven writing-voice override does not port: an output style is static system-prompt text loaded at session start and cannot probe .han/config.md, so the built-in Han voice is hardcoded.