Cheggin/slack-course-correction
skills/slack-course-correction/SKILL.md
Detect user feedback in Slack threads, classify intent, and propagate direction changes to specs, Issues, and agents.
data-ai
Updated Apr 25, 2026
$ install --global
skillsauthnpx skillsauth add Cheggin/skill-chain slack-course-correctionInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 25, 2026, 8:37 PM11.0s1 file scanned
SKILL.md
- name:
- slack-course-correction
- description:
- Detect user feedback in Slack threads, classify intent, and propagate direction changes to specs, Issues, and agents.
- user-invocable:
- true
- group:
- comms
- prerequisites:
- [investor-updates]
- next:
- [plan, issue-creator]
- workflows:
- [incident-response]
Slack Course Correction
When a user replies to an investor update in Slack, detect the reply, classify intent, propagate changes atomically across specs and Issues, and confirm back in the thread.
Steps
- Listen for replies to investor update messages in Slack via the Slack plugin or webhook.
- Classify intent into one of: pivot, feature request, bug report, priority change, general feedback. If ambiguous, post a clarifying question before acting.
- Handle each intent type:
- Pivot: require explicit user confirmation, then rewrite the spec and reprioritize all Issues.
- Feature request: create a new feature checklist in
features/and corresponding GitHub Issues with labels. - Bug report: create a GitHub Issue with the
buglabel and route to the appropriate agent. - Priority change: reorder the Project board and update agent task queues.
- General feedback: append context to the relevant spec sections or feature files.
- Sync GitHub Issues to match the new direction: create new Issues, close obsolete ones, reprioritize remaining ones.
- Notify active agents whose task context changed so they can adapt or restart with updated information.
- Post a confirmation message back to the Slack thread summarizing what was understood and what actions were taken.
- Log every course correction with before/after state as a GitHub Issue comment for audit.
Anti-Patterns
- Executing a full pivot on vague feedback like "maybe we should rethink the approach" without asking for clarification
- Updating the spec but not reconciling GitHub Issues, leaving stale Issues on the board
- Not notifying agents of priority changes, so they continue working on deprioritized tasks
- No confirmation posted to Slack, leaving the user unsure if feedback was received
Validation
- Every user reply is classified and acted on or clarified within the thread
- Spec changes and Issue changes are atomic -- neither happens without the other
- Active agents are notified when their task context changes
- Confirmation message in the Slack thread matches the actions actually taken
Related Skills
Cheggin/make-interfaces-feel-better
development
VerifiedTrustedCommunity
Design engineering principles for making interfaces feel polished. Use when building UI components, reviewing frontend code, implementing animations, hover states, shadows, borders, typography, micro-interactions, enter/exit animations, or any visual detail work. Triggers on UI polish, design details, "make it feel better", "feels off", stagger animations, border radius, optical alignment, font smoothing, tabular numbers, image outlines, box shadows.
1SKILL.mdUpdated Apr 29, 2026
Cheggin/writer-memory
documentation
VerifiedTrustedCommunity
Agentic memory system for writers - track characters, relationships, scenes, and themes
SKILL.mdUpdated Apr 25, 2026
Cheggin/wiki
documentation
VerifiedTrustedCommunity
LLM Wiki — persistent markdown knowledge base that compounds across sessions (Karpathy model)
SKILL.mdUpdated Apr 25, 2026
Cheggin/website-creation
development
VerifiedTrustedCommunity
Build production-quality SaaS websites with opinionated design presets. Use when creating any startup website. The user MUST pick a design style before building. Enforces shadcn/ui, Figma design principles, specific CSS values per style, and anti-AI-writing. Load alongside anti-ai-writing skill. LIGHT MODE ONLY.
SKILL.mdUpdated Apr 25, 2026