modify template
This commit is contained in:
김경종
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"project": "{보고서 프로젝트명}",
|
||||
"phase": "0-report-generation",
|
||||
"steps": [
|
||||
{
|
||||
"step": 0,
|
||||
"name": "brief-audit",
|
||||
"status": "pending"
|
||||
},
|
||||
{
|
||||
"step": 1,
|
||||
"name": "source-discovery",
|
||||
"status": "pending"
|
||||
},
|
||||
{
|
||||
"step": 2,
|
||||
"name": "deep-research",
|
||||
"status": "pending"
|
||||
},
|
||||
{
|
||||
"step": 3,
|
||||
"name": "source-review-outline",
|
||||
"status": "pending"
|
||||
},
|
||||
{
|
||||
"step": 4,
|
||||
"name": "draft-report",
|
||||
"status": "pending"
|
||||
},
|
||||
{
|
||||
"step": 5,
|
||||
"name": "feedback-setup",
|
||||
"status": "pending"
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,34 @@
|
||||
# Step 0: brief-audit
|
||||
|
||||
## Read First
|
||||
- /AGENTS.md
|
||||
- /docs/PRD.md
|
||||
- /docs/ARCHITECTURE.md
|
||||
- /docs/ADR.md
|
||||
- /docs/UI_GUIDE.md
|
||||
- /docs/RESEARCH_LOG.md
|
||||
- /docs/REPORT_DRAFT.md
|
||||
- /docs/FEEDBACK.md
|
||||
|
||||
## Task
|
||||
Audit `docs/PRD.md` for the minimum report inputs: topic, purpose, keywords, direction, audience, output format, required questions, exclusions, and success criteria.
|
||||
|
||||
If the brief is usable, update `docs/RESEARCH_LOG.md` with a concrete research question list derived from the brief. If a critical input is still a placeholder or empty, update this step in `phases/0-report-generation/index.json` as `blocked` with a concise `blocked_reason` and stop.
|
||||
|
||||
## Acceptance Criteria
|
||||
```bash
|
||||
python scripts/validate_workspace.py
|
||||
```
|
||||
|
||||
## Verification
|
||||
1. Run the acceptance command.
|
||||
2. Confirm the report brief has enough information to guide research.
|
||||
3. Confirm `docs/RESEARCH_LOG.md` contains research questions aligned with the brief.
|
||||
4. Update this step in `phases/0-report-generation/index.json`:
|
||||
- `completed` + `summary`
|
||||
- `blocked` + `blocked_reason`
|
||||
- `error` + `error_message`
|
||||
|
||||
## Do Not
|
||||
- Do not invent missing report intent because later research will follow the wrong direction.
|
||||
- Do not start drafting the report in this step.
|
||||
@@ -0,0 +1,33 @@
|
||||
# Step 1: source-discovery
|
||||
|
||||
## Read First
|
||||
- /AGENTS.md
|
||||
- /docs/PRD.md
|
||||
- /docs/ARCHITECTURE.md
|
||||
- /docs/ADR.md
|
||||
- /docs/UI_GUIDE.md
|
||||
- /docs/RESEARCH_LOG.md
|
||||
- /phases/0-report-generation/index.json
|
||||
|
||||
## Task
|
||||
Perform broad web search for the report topic, purpose, and keywords in `docs/PRD.md`.
|
||||
|
||||
Update `docs/RESEARCH_LOG.md` with candidate sources. Prioritize official documents, primary sources, public data, academic or government sources, credible industry research, and reputable journalism. Record each source with title, publisher, URL, publication date or access date, key content, reliability note, and likely report section.
|
||||
|
||||
Aim for enough source diversity to cover the main claims, counterarguments, and uncertainty. If web access is unavailable or a required source is behind authentication/paywall, mark the step `blocked` with the reason.
|
||||
|
||||
## Acceptance Criteria
|
||||
```bash
|
||||
python scripts/validate_workspace.py
|
||||
```
|
||||
|
||||
## Verification
|
||||
1. Run the acceptance command.
|
||||
2. Confirm `docs/RESEARCH_LOG.md` contains source entries with URLs and reliability notes.
|
||||
3. Confirm weak or unverified claims are listed under `검증 필요`.
|
||||
4. Update this step in `phases/0-report-generation/index.json`.
|
||||
|
||||
## Do Not
|
||||
- Do not use model memory as a substitute for web search.
|
||||
- Do not copy long source text into the repository; summarize only what is needed.
|
||||
- Do not add unsupported claims to `docs/REPORT_DRAFT.md` in this step.
|
||||
@@ -0,0 +1,36 @@
|
||||
# Step 2: deep-research
|
||||
|
||||
## Read First
|
||||
- /AGENTS.md
|
||||
- /docs/PRD.md
|
||||
- /docs/ARCHITECTURE.md
|
||||
- /docs/ADR.md
|
||||
- /docs/UI_GUIDE.md
|
||||
- /docs/RESEARCH_LOG.md
|
||||
- /phases/0-report-generation/index.json
|
||||
|
||||
## Task
|
||||
Deepen the research around the most important keywords, stakeholders, time periods, regions, and required questions from `docs/PRD.md`.
|
||||
|
||||
Use web search to fill evidence gaps, find current data, and look for conflicting viewpoints. Update:
|
||||
|
||||
- `docs/RESEARCH_LOG.md` source list with additional source entries.
|
||||
- `docs/RESEARCH_LOG.md` `상충 근거` table when sources disagree.
|
||||
- `docs/RESEARCH_LOG.md` `검증 필요` for claims that still lack enough support.
|
||||
- `docs/RESEARCH_LOG.md` `폐기한 주장` for claims excluded because the evidence is weak, outdated, or outside scope.
|
||||
|
||||
## Acceptance Criteria
|
||||
```bash
|
||||
python scripts/validate_workspace.py
|
||||
```
|
||||
|
||||
## Verification
|
||||
1. Run the acceptance command.
|
||||
2. Confirm the required questions in `docs/PRD.md` have research coverage or explicit gaps.
|
||||
3. Confirm conflicts and uncertainty are visible in `docs/RESEARCH_LOG.md`.
|
||||
4. Update this step in `phases/0-report-generation/index.json`.
|
||||
|
||||
## Do Not
|
||||
- Do not resolve conflicting evidence by ignoring one side.
|
||||
- Do not overfit research to a predetermined conclusion.
|
||||
- Do not write the final report body before the source review and outline step.
|
||||
@@ -0,0 +1,32 @@
|
||||
# Step 3: source-review-outline
|
||||
|
||||
## Read First
|
||||
- /AGENTS.md
|
||||
- /docs/PRD.md
|
||||
- /docs/ARCHITECTURE.md
|
||||
- /docs/ADR.md
|
||||
- /docs/UI_GUIDE.md
|
||||
- /docs/RESEARCH_LOG.md
|
||||
- /docs/REPORT_DRAFT.md
|
||||
- /phases/0-report-generation/index.json
|
||||
|
||||
## Task
|
||||
Review `docs/RESEARCH_LOG.md` for source quality, source freshness, conflicts, weak claims, and missing evidence. Then create or refine the report outline in `docs/REPORT_DRAFT.md`.
|
||||
|
||||
The outline must reflect the report purpose, keywords, direction, audience, and output format from `docs/PRD.md`. Include placeholders for key claims, supporting sources, risks, uncertainty, and feedback questions.
|
||||
|
||||
## Acceptance Criteria
|
||||
```bash
|
||||
python scripts/validate_workspace.py
|
||||
```
|
||||
|
||||
## Verification
|
||||
1. Run the acceptance command.
|
||||
2. Confirm the outline follows `docs/UI_GUIDE.md`.
|
||||
3. Confirm major sections have evidence sources or explicit evidence gaps.
|
||||
4. Update this step in `phases/0-report-generation/index.json`.
|
||||
|
||||
## Do Not
|
||||
- Do not hide source weaknesses because they are inconvenient.
|
||||
- Do not delete useful research history from `docs/RESEARCH_LOG.md`.
|
||||
- Do not write polished conclusions that are not supported by the reviewed sources.
|
||||
@@ -0,0 +1,32 @@
|
||||
# Step 4: draft-report
|
||||
|
||||
## Read First
|
||||
- /AGENTS.md
|
||||
- /docs/PRD.md
|
||||
- /docs/ARCHITECTURE.md
|
||||
- /docs/ADR.md
|
||||
- /docs/UI_GUIDE.md
|
||||
- /docs/RESEARCH_LOG.md
|
||||
- /docs/REPORT_DRAFT.md
|
||||
- /phases/0-report-generation/index.json
|
||||
|
||||
## Task
|
||||
Write or revise `docs/REPORT_DRAFT.md` into a coherent report draft.
|
||||
|
||||
Use only claims supported by `docs/RESEARCH_LOG.md` or clearly label unresolved claims as uncertain. Follow the target format, audience, direction, and success criteria in `docs/PRD.md`. Include executive summary, background, core findings, detailed analysis, risks and uncertainty, options or scenarios, recommendations, references, and user feedback questions unless the brief specifies a different structure.
|
||||
|
||||
## Acceptance Criteria
|
||||
```bash
|
||||
python scripts/validate_workspace.py
|
||||
```
|
||||
|
||||
## Verification
|
||||
1. Run the acceptance command.
|
||||
2. Confirm every core claim in the draft maps to a source or a `검증 필요` note.
|
||||
3. Confirm the draft includes risks, uncertainty, and next-decision guidance.
|
||||
4. Update this step in `phases/0-report-generation/index.json`.
|
||||
|
||||
## Do Not
|
||||
- Do not include source-free statistics or current claims.
|
||||
- Do not use persuasive language that exceeds the evidence.
|
||||
- Do not remove feedback questions from the end of the draft.
|
||||
@@ -0,0 +1,35 @@
|
||||
# Step 5: feedback-setup
|
||||
|
||||
## Read First
|
||||
- /AGENTS.md
|
||||
- /docs/PRD.md
|
||||
- /docs/ARCHITECTURE.md
|
||||
- /docs/ADR.md
|
||||
- /docs/UI_GUIDE.md
|
||||
- /docs/RESEARCH_LOG.md
|
||||
- /docs/REPORT_DRAFT.md
|
||||
- /docs/FEEDBACK.md
|
||||
- /phases/0-report-generation/index.json
|
||||
|
||||
## Task
|
||||
Prepare the report for user review.
|
||||
|
||||
Update `docs/REPORT_DRAFT.md` with focused feedback questions that help the user decide the next iteration. Update `docs/FEEDBACK.md` with a new pending feedback entry that names the draft version, review focus, and next questions.
|
||||
|
||||
If the report still has material evidence gaps, list them clearly in both `docs/REPORT_DRAFT.md` and `docs/FEEDBACK.md`.
|
||||
|
||||
## Acceptance Criteria
|
||||
```bash
|
||||
python scripts/validate_workspace.py
|
||||
```
|
||||
|
||||
## Verification
|
||||
1. Run the acceptance command.
|
||||
2. Confirm `docs/REPORT_DRAFT.md` is ready for user review.
|
||||
3. Confirm `docs/FEEDBACK.md` has a pending entry for the next iteration.
|
||||
4. Update this step in `phases/0-report-generation/index.json`.
|
||||
|
||||
## Do Not
|
||||
- Do not mark unresolved evidence gaps as finished.
|
||||
- Do not ask generic feedback questions that do not help revise the report.
|
||||
- Do not start a second revision phase in this step.
|
||||
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"phases": [
|
||||
{
|
||||
"dir": "0-report-generation",
|
||||
"status": "pending"
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user