with one click
init
Initialize project with Digital Service Orchestra config
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
Initialize project with Digital Service Orchestra config
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use when the user wants a comprehensive multi-issue health pass — fix all bugs, resolve broken tests, clear CI failures, fix lint and type errors, restore green builds — not for a single targeted bug fix. Diagnoses and resolves every outstanding open bug ticket plus all validation failures (test, lint, type, format, infrastructure) using orchestrated sub-agents with TDD discipline, in tier order. Trigger phrases include 'debug everything', 'fix all bugs', 'fix the failing tests', 'CI is failing', 'build is broken', 'clean up the codebase', 'restore green', 'project health pass'.
Use when wrapping up a worktree session — closing tasks, finishing work, or merging the branch back to main. Closes completed tickets, sweeps orphaned epics, extracts technical learnings, files bug tickets for unfixed failures, commits remaining changes, syncs the tickets branch, merges to main via merge-to-main.sh, verifies the worktree is merged and clean for claude-safe auto-removal, and prints a task summary. Trigger phrases include 'end session', 'wrap up', 'finish', 'done for now', 'close out', 'merge to main and clean up', 'session complete', 'wrap up this branch'.
Use when the user is stuck in a merge conflict, rebase conflict, failed pull, or any git operation that left conflict markers in the working tree. Dispatches a conflict-analyzer sub-agent that classifies each conflicted hunk by confidence (auto-resolvable vs needs-human-review), auto-resolves high-confidence cases, validates the result, and rolls back if validation fails before falling through to human review. Trigger phrases include 'merge conflict', 'resolve conflicts', 'rebase conflict', 'git conflict', 'conflict markers', 'failed rebase', 'git pull conflict', 'fix the conflicts', 'help with this merge'.
Manual review escalation when CI llm-review blocks a PR on a finding that looks like a false positive. Dispatches dso:code-reviewer-standard at opus tier on the PR's diff, parses the result, and emits a force-merge clearance when zero critical/important/fragile findings remain. Use ONLY when CI llm-review has failed on a suspect FP; not for routine PR shipping. Trigger phrases include 'force merge this PR', 'the CI review is wrong', 'false positive from llm-review', 'manual review override', 'FP recovery'.
Use when the user wants to execute an epic, run a sprint, work through a planned epic's stories and tasks, or coordinate multi-agent task execution end-to-end. Routes the epic by complexity (SIMPLE → direct implementation-plan, MODERATE → lightweight preplanning, COMPLEX → full preplanning), runs an SC-coverage gate at haiku/sonnet/opus tiers to confirm story coverage of epic success criteria, plans the task graph, dispatches sub-agents in batches with file-overlap and semantic-conflict checks, runs per-task review and post-batch validation (test gate, lint, AC verification, visual verification for UI), commits/pushes results, and verifies epic completion via the dso:completion-verifier agent before close. Trigger phrases include 'work the epic', 'execute the sprint', 'run the epic', 'sprint this epic', 'work through the stories', 'implement the planned tasks', 'kick off the sprint'.
Use when breaking down an epic into user stories, story splitting, backlog grooming, defining acceptance criteria, or auditing and reconciling existing epic children before implementation. Dispatches an opus `dso:story-decomposer` sub-agent to draft prioritized vertical-slice user stories with measurable done definitions tied to epic Success Criteria (never inline), identifies dependencies, runs an adversarial red-team review pass, dispatches a UI designer for UI stories, and writes the story tickets to the tracker. Trigger phrases include 'break down this epic', 'split into stories', 'story splitting', 'backlog grooming', 'write user stories', 'define acceptance criteria', 'plan the epic', 'decompose the epic', 'reconcile epic children'.
| name | init |
| description | Initialize project with Digital Service Orchestra config |
| user-invocable | true |
| allowed-tools | Read, Write, Edit, Glob, Grep, Bash |
Set up a new project to use Digital Service Orchestra by auto-detecting the stack and writing a
.claude/dso-config.conf with sensible defaults.
/dso:init # Initialize current directory
/dso:init [project-dir] # Initialize a specific directory
Run detect-stack.sh to identify the project type:
STACK=$(bash ".claude/scripts/dso detect-stack.sh" "${PROJECT_DIR:-.}")
The script inspects marker files and returns one of:
python-poetry — pyproject.toml foundrust-cargo — Cargo.toml foundgolang — go.mod foundnode-npm — package.json foundconvention-based — Makefile with ≥2 standard targetsunknown — no recognized markersUse the detected stack to populate sensible command defaults:
| Stack | test | lint | format | format_check |
|---|---|---|---|---|
python-poetry | make test | make lint | make format | make format-check |
node-npm | npm test | npm run lint | npm run format | — |
rust-cargo | cargo test | cargo clippy | cargo fmt | cargo fmt --check |
golang | go test ./... | golangci-lint run | gofmt -l . | — |
convention-based | make test | make lint | make format | — |
Additional defaults for python-poetry:
validate: .claude/scripts/dso validate.sh --ciBefore proposing, check if .claude/dso-config.conf already exists using read-config.sh:
EXISTING_STACK=$(bash ".claude/scripts/dso read-config.sh" stack "${PROJECT_DIR:-.}/.claude/dso-config.conf")
If the file exists, warn the user and ask for confirmation before overwriting.
Present the proposed .claude/dso-config.conf to the user before writing:
# .claude/dso-config.conf — generated by /dso:init
stack=<detected-stack>
commands.test=<default-test-command>
commands.lint=<default-lint-command>
commands.format=<default-format-command>
# commands.format_check=<default-format-check-command> # if applicable
# commands.validate=<validate-command> # if applicable
Write .claude/dso-config.conf to the .claude/ directory under the project directory.
.claude/ if needed, then write directly..claude/dso-config.conf already exists. Overwrite? (yes/no)
If the user says no, abort and report the existing file path.If detect-stack.sh returns unknown, do not guess. Instead:
No recognized stack found in <project-dir>.
Please provide:
- test command (e.g., 'make test'):
- lint command (e.g., 'make lint'):
- format command (e.g., 'make format', or leave blank):
.claude/dso-config.conf.If project-dir is provided but does not exist, report the error and abort before Step 1.