kate-career-coach: v0.4.0 — skill-based invocation architecture#153
Open
cbellbell-spin wants to merge 5 commits intoanthropics:mainfrom
Open
kate-career-coach: v0.4.0 — skill-based invocation architecture#153cbellbell-spin wants to merge 5 commits intoanthropics:mainfrom
cbellbell-spin wants to merge 5 commits intoanthropics:mainfrom
Conversation
Kate is a senior career coaching assistant for executive job seekers (VP+). Includes skills for fit assessment, interview prep, post-interview debrief, and ongoing job market monitoring via Indeed.
Internal efficiency improvements: commands are now thin dispatchers that defer to flows.md, reducing redundant context load. flows.md is read once at session init rather than per command. setup-monitoring generates a standalone scheduled task prompt file instead of embedding flow steps inline. Three standing coaching rules trimmed from execution-detail to principle statements. No behavior changes.
- Add homepage and license fields to plugin.json - Add .mcp.json connector config - Add Configuration section to README clarifying that user settings are captured interactively, not via settings.local.json Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…on narrative, and show-don't-tell probe Adds Step 2B (Intelligence Diagnostic), Step 5B (Vision Narrative), and Pre-Interview Step 2B (Show Don't Tell Probe) to the onboarding and prep flows. Also restructures formatting for consistency. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Adds five individual skills (fit-assessment, interview-prep, debrief, run-monitoring, setup-monitoring) as the primary invocation path. Each loads only its relevant flow section on demand, eliminating the ~385-line flows.md preload that fired on every session start. kate-coach SKILL.md trimmed; flows.md corrected (Intelligence Diagnostic and Vision Narrative moved to Pre-Interview Prep where they belong); all command files stripped to stubs; README updated. Co-Authored-By: Claude Sonnet 4.6 <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
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
fit-assessment,interview-prep,debrief,run-monitoring,setup-monitoring) — each with proper trigger phrases and lazy-load flow references, now the primary invocation pathflows.mdpreload from session init; watchlist structure moved into monitoring skills; flow references updated to lazy-load modelTest plan
flows.mdis not pre-loaded on session start — only loads when a specific workflow is invoked🤖 Generated with Claude Code