Slim down skill.md into components to improve performance under 40k claude limit#48
Open
itsdevlin wants to merge 3 commits into
Open
Slim down skill.md into components to improve performance under 40k claude limit#48itsdevlin wants to merge 3 commits into
itsdevlin wants to merge 3 commits into
Conversation
… → 15.3k chars) Resolves the "Large CLAUDE.md will impact performance" warning by extracting 7 situationally-loaded sections into dedicated reference files. The coaching state schema, migration rules, mode detection, voice standard, and other blocks are now loaded on-demand — matching the existing references/ pattern. Co-Authored-By: Claude Opus 4.6 <[email protected]>
Co-Authored-By: Claude Opus 4.6 <[email protected]>
Brings in Lenny's archive integrations across 16 command reference files. Co-Authored-By: Claude Opus 4.6 <[email protected]>
Author
|
Realized my fork was a few commits behind, updated and reopened. |
dbhat93
added a commit
to dbhat93/job-search-os
that referenced
this pull request
Apr 15, 2026
New command: `apply [company]` drafts written answers to job application screening questions. 7-step workflow with story selection, domain match flag, gap check, Writing Quality Gate integration, Proof Bank enrichment, and character limit enforcement (LinkedIn 300 / Greenhouse 500). Adopted from upstream PR noamseg#39 (saurabhsudhir15), enhanced with cross-cutting hooks. Extracted 4 sections from COACH.md into reference files to reduce main file size (adopted pattern from upstream PR noamseg#48 by itsdevlin): coaching-state-schema.md, schema-migration.md, archival-rules.md, state-update-triggers.md. COACH.md now uses pointer references. Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
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.
Summary
references/files, reducing size from 47.5k → 15.3k chars (68% reduction)references/pattern — content is loaded on-demand when commands need it, not on every conversation turnWhat was extracted
references/coaching-state-schema.mdreferences/mode-detection.mdreferences/schema-migration.mdreferences/state-update-triggers.mdreferences/coaching-voice.mdreferences/evidence-sourcing.mdreferences/archival-rules.mdWhat stays in SKILL.md
Priority Hierarchy, Session protocols (brief, with pointers), Non-Negotiable Rules, Command Registry, File Routing, Core Rubric summary, Response Blueprints — everything needed on every turn.
Test plan
kickoff— confirm schema file is read and state is created correctlyhelp— confirm command registry still worksanalyzewith a transcript — confirm mode detection routes correctly🤖 Generated with Claude Code