Refine, analyze, improve, and enrich GitHub Story issues with structured templates, surface-aware quality checks (E/F/S numbering prefix, Surface label, parent Feature), and codebase-aware technical analysis driven by `.claude/architecture/*` + `.claude/rules/*` in the configured repo. Outputs land in the Story issue itself as Title / body / Acceptance criteria edits + change-log comments. Use this skill whenever the user mentions Story refinement, enrichment, analysis, or improvement, acceptance criteria, Story quality, sprint readiness, or commands like /backlog-improve, /backlog-refine, /backlog-analyze, /backlog-enrich. Also trigger when the user references GitHub issue numbers in the context of improving or reviewing Story quality. This skill is never invoked autonomously — it only runs when explicitly requested by a human user.
How this skill is triggered — by the user, by Claude, or both
Slash command
/platform-sdlc-harness:backlog-workflow <command> <issue-number><command> <issue-number>This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
A skill for improving Story quality through structured refinement, readiness analysis,
A skill for improving Story quality through structured refinement, readiness analysis,
and codebase-aware technical enrichment. Integrates with GitHub via the gh CLI to read and
comment on Story issues.
/backlog-workflow <command> [issue-number] [extra-args...]
Examples:
/backlog-workflow improve 242/backlog-workflow improve 242 "Team decided to limit scope to admin users only, defer SSO"/backlog-workflow analyze 242/backlog-workflow refine 242/backlog-workflow enrich 242Parse $ARGUMENTS to extract the command and its arguments:
improve, analyze, refine, enrich.#N, with or without the leading #).improve or refine).If the first token is missing or doesn't match a known command, show the usage line above and list the four commands with one-line descriptions. Do not guess.
Deprecated token — groom: If the first token is groom, do not route. Surface
this warning verbatim and stop, so the user re-invokes with the new name:
⚠️ The
groomcommand has been renamed toenrich. Please re-run as:/backlog-workflow enrich <issue-number>The term "grooming" was retired due to its connotations in modern Agile usage; the command's behaviour is unchanged.
Route to the matching command file based on the first token:
| Command | File | Requires Issue Number |
|---|---|---|
improve | commands/improve.md | Yes |
analyze | commands/analyze.md | Yes |
refine | commands/refine.md | Yes |
enrich | commands/enrich.md | Yes |
Read the command file and follow its instructions. Pass the issue number and any extra arguments to the command.
Validation before routing:
.claude/context/platform-context.md (the Org + Repo fields, recorded by /init-workspace). Never hardcode an owner/repo. If platform-context.md is missing, halt with: "Workspace not initialized — run /init-workspace first." When running gh inside the repo clone, gh auto-detects the repo; otherwise pass --repo <org>/<repo>. Pass the resolved org/repo to the routed command.gh CLI available and authenticated (gh auth status)enrich command)/init-workspace before using backlog commands (one-time setup)Backlog templates and output formats live in templates/. Commands reference them as needed.
Do not modify templates during command execution.
Generated by the standalone /init-workspace skill. Each developer generates their own
set by running /init-workspace. Files live at .claude/context/ (git-ignored):
.claude/context/platform-context.md — single context file with sections:
/init-workspace)dotnet-conventions / react-turbo-conventions / expo-mobile-conventions skillsGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.
npx claudepluginhub ameenaliu/harness-platform --plugin platform-sdlc-harness