feat: jira - fullsend skill#41
Draft
durandom wants to merge 5 commits into
Draft
Conversation
Conversational grooming skill that scores Jira tickets against a 6-dimension agent-readiness rubric (problem clarity, repo identification, file hints, acceptance criteria, scope, type clarity). Three modes: interactive grooming, quick score, and batch scoring via JQL. Inspired by Rehor's (platform-frontend-ai-dev) grooming workflow, adapted for general use with any autonomous agent. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Creates GitHub Issues from groomed Jira tickets so fullsend agents can pick them up. Validates agent-readiness score before bridging, maps Jira components to target repos, handles duplicate detection, and links both sides (Jira comment + GitHub body). Three modes: single ticket bridge, dry-run preview, and batch bridging via JQL. Designed to pair with jira-groom as a two-step workflow: groom → bridge → fullsend picks up. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
…4.0) Merge two separate skills into a single unified `fullsend` skill with `groom` and `bridge` subcommands. This better reflects the workflow: groom a Jira ticket for agent-readiness, then bridge it to GitHub. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Surface cross-skill dependencies (rhdh-repos, jira fields, JQL patterns, acli commands) at the routing level so Claude loads the right context before dispatching to groom or bridge sub-commands. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Credit the ConsoleDot Rehor bot as the inspiration for the grooming rubric, investigation workflow, and repo-mapping pattern. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
durandom
changed the title
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
fullsendskill for the agent-readiness workflow: groom Jira tickets so autonomous agents can implement them, then bridge groomed tickets to GitHub Issuesgroom(score + improve tickets against a 6-dimension readiness rubric) andbridge(create GitHub Issues with fullsend-compatible formatting, link both sides)Attribution
The grooming workflow and agent-readiness rubric are derived from
platform-frontend-ai-dev(Rehor), the autonomous dev bot built by the ConsoleDot Platform Experience team.Key inspirations:
prompts/groom.md— conversational grooming prompt. Our 6-dimension scoring rubric formalizes the same checks Rehor performs implicitly.needs-investigationworkflow — investigation tickets produce reports, not code. Our groom workflow adopts this distinction.project-repos.json— repo-to-persona mapping. Ourrepo-mapping.mdfollows the same pattern but uses the existingrhdh-jiracomponent catalog as source of truth.fullsendlabel.Architectural difference: Rehor is a monolith (groom + execute + triage in one agent), while fullsend separates preparation (this skill) from execution (the fullsend agent on GitHub).
What's in the skill
/fullsend groom <KEY>/fullsend groom <KEY> --quick/fullsend groom --batch <JQL>/fullsend bridge <KEY>/fullsend bridge <KEY> --dry-runFiles added
skills/fullsend/README.md— skill overview with attribution to platform-frontend-ai-devskills/fullsend/SKILL.md— router with command table, shared context references, cross-skill dependenciesskills/fullsend/references/groom.md— agent-readiness rubric, grooming workflow, question guide, description template, investigation checkskills/fullsend/references/bridge.md— Jira-to-GitHub bridging workflow, issue template, field mapping, batch modeskills/fullsend/references/repo-mapping.md— Jira component → GitHub repo mapping, referencesrhdh-repos.mdandrhdh-jirafieldsTest plan
/fullsendshows command table/fullsend groom <KEY>fetches ticket and scores it/fullsend groom <KEY> --quickreturns score without conversation/fullsend bridge <KEY>creates GitHub Issue and links back to Jira/fullsend bridge <KEY> --dry-runpreviews without creating🤖 Generated with Claude Code