메뉴
Create and manage YAMLGraph feature requests. Use when: writing a feature request, planning a feature, following the plan-judge-enforce workflow, submitting a proposal to the chaplain inbox, understanding the FR lifecycle, or writing acceptance criteria.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | feature-request |
| description | Create and manage YAMLGraph feature requests. Use when: writing a feature request, planning a feature, following the plan-judge-enforce workflow, submitting a proposal to the chaplain inbox, understanding the FR lifecycle, or writing acceptance criteria. |
| argument-hint | 'new', 'template', or FR-XXX number |
Create, judge, and enforce feature requests. Sources: feature-requests/TEMPLATE.md, the Scripture (copilot-instructions.md).
feature-requests/FR-XXX-name.md. Define objectives, constraints, acceptance criteria.docs/diary/. Name the trap or insight. Plant a Seed.# Feature Request: [Title]
**Priority:** LOW | MEDIUM | HIGH
**Type:** Feature | Bug | Enhancement
**Status:** Proposed
**Effort:** X days
**Requested:** YYYY-MM-DD
## Summary
Brief description.
## Value Statement
Who benefits and how (one sentence).
## Problem
What problem does this solve?
## Proposed Solution
How should it work? Include code examples.
## Acceptance Criteria
- [ ] Criterion 1
- [ ] Tests added
- [ ] Documentation updated
## Alternatives Considered
What other approaches were considered?
## Related
- Links to issues, PRs, files
Proposed → Judged → In Progress → Completed (or Rejected)
Write to .chaplain/inbox/:
cat > .chaplain/inbox/refactor-state-builder.md << 'EOF'
Problem: State builder has grown to 450 lines.
Task: Split into state_builder.py and state_reducer.py.
EOF
Open a GitHub Issue with the chaplain label. The runtime imports it automatically.
FR-XXX-kebab-case-name.md in feature-requests/feat(scope): FR-XXX summary (Conventional Commits)changelog/unreleased/ for feat/fix PRstmp/msg.txt, use git commit -F tmp/msg.txtGood criteria are:
- [ ] `yamlgraph graph lint` detects missing edges (E301)
- [ ] Unit test covers empty graph case
- [ ] Changelog fragment in `changelog/unreleased/`
Every test must link to a requirement:
@pytest.mark.req("REQ-YG-XXX")
def test_feature():
...
When adding a new capability: add requirement to ARCHITECTURE.md, extend scripts/req_coverage.py, tag tests.
python scripts/req_coverage.py --strict # Verify coverage
| File | Purpose |
|---|---|
feature-requests/TEMPLATE.md | FR template |
feature-requests/FR-*.md | All feature requests |
ARCHITECTURE.md | Requirements registry |
capabilities/CAP-*.yaml | Capability specs |
scripts/req_coverage.py | Requirement coverage checker |
.chaplain/inbox/ | Chaplain proposal inbox |
Author YAMLGraph prompt YAML files. Use when: writing prompt templates, configuring inline schemas or output_schema, using Jinja2 templates, adding system/user messages, defining structured output fields, or using system_segments for prompt caching.
Author YAMLGraph graph YAML files. Use when: creating or editing graph YAML, adding nodes or edges, configuring routing and conditions, setting up state keys, variables, data_files, tools, loop limits, error handling, or verification gates.
Operate the Chaplain automation system. Use when: starting the chaplain, checking pipeline status, submitting proposals to inbox, debugging pipeline failures, retrying failed topics, cleaning worktrees, running the philosopher or inquisitor.
Release a new YAMLGraph version. Use when: bumping version, creating a release, tagging, pushing a release, freezing changelog, or handling pre-commit hook cascades during release.
Run code quality analysis on YAMLGraph. Use when: running ruff, bandit, radon, vulture, pytest coverage, checking code quality, finding dead code, security scanning, or generating improvement recommendations. For autonomous analysis, use the code-analysis agent instead.
Check LangSmith traces for YAMLGraph runs. Use when: debugging graph execution, reviewing LLM latency or token usage, investigating failed runs, verifying tracing config, querying recent traces, troubleshooting LangSmith connectivity.