How this skill is triggered — by the user, by Claude, or both
Slash command
/devproc:feature-endThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Mark a feature as complete and bring all documentation up to date.
Mark a feature as complete and bring all documentation up to date.
Before proceeding, check that CLAUDE.md contains a Feature Model section. If it doesn't, tell the user to run /feature-init first and stop.
The feature to end is: $ARGUMENTS (if blank, use whichever feature is currently In Progress in FEATURES.md)
Steps:
Run a full checkpoint first (all steps from /feature-checkpoint): update the plan file sub-task statuses, add any outstanding NOTES.md entries, update CLAUDE.md current status.
Confirm all sub-tasks are complete. If any are not, ask the user whether to defer them, drop them, or keep the feature open.
Call @docs-structure-reviewer to perform a full review that the structure of the documentation is still valid. Apply its feedback, then call it again to confirm. If each call does not have fewer issues than the previous one (i.e. you are converging) ask for user input.
Update FEATURES.md:
## In progress.## Completed with the format:### <Feature title> [tags] — <YYYY-MM-DD>
<Two to four sentences summarising what was built, what data was committed, and any notable decisions. No tables, no sub-task lists.>
The plan file (plans/<slug>.md) can be left as-is to serve as a record of how the feature unfolded.
Report a summary of what was completed and what feature is now next.
npx claudepluginhub plwhite/claudeplugins --plugin devprocProvides behavioral guidelines to reduce common LLM coding mistakes, focusing on simplicity, surgical changes, assumption surfacing, and verifiable success criteria.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.