
Research Outline
- 39 installs
- 6 repo stars
- Updated July 22, 2026
- julianobarbosa/claude-code-skills
Bootstrap structured research project on any topic - generate initial items list and research-field schema from model knowledge, supplement with web search.
About
Bootstrap structured research project on any topic - generate items list and schema from model knowledge, supplement with web search, emit outline.yaml and fields.yaml.. Use for academic research, benchmarks, tech selection, competitive analysis, market scans.
- intermediate skill
- core: ai & agent building
Research Outline by the numbers
- 39 all-time installs (skills.sh)
- +2 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #8,347 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 3, 2026 (Skillselion catalog sync)
npx skills add https://github.com/julianobarbosa/claude-code-skills --skill research-outlineAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 39 |
|---|---|
| repo stars | ★ 6 |
| Last updated | July 22, 2026 |
| Repository | julianobarbosa/claude-code-skills ↗ |
What it does
Bootstrap structured research project on any topic - generate initial items list and research-field schema from model knowledge, supplement with web search.
Files
Research — Preliminary Research
Bootstraps a research project. Produces the outline (items + execution config) and field schema (the research dimensions) that /research-deep and /research-report consume.
Trigger
/research-outline <topic>
Pipeline contract
This skill is the entry point of a four-step pipeline:
/research-outline <topic> # this skill — produces outline.yaml + fields.yaml
├─ /research-add-items # optional — append more research objects
├─ /research-add-fields # optional — append more research dimensions
├─ /research-deep # fan-out per-item deep research → results/*.json
└─ /research-report # summarise results into a markdown reportOutput layout:
{current_working_directory}/{topic_slug}/
├── outline.yaml # items list + execution config
└── fields.yaml # field definitionsWorkflow
Step 1 — Generate initial framework from model knowledge
Based on the topic, use the model's existing knowledge to draft:
- a main research-objects (items) list in the domain
- a suggested research-field framework
Show the draft as {step1_output}, then AskUserQuestion to confirm:
- Need to add or remove items?
- Does the field framework match what they want to learn?
Step 2 — Web-search supplement
AskUserQuestion for the time range (e.g. last 6 months, since 2024, unlimited).
Parameters captured at this point:
{topic}— the user's research topic{YYYY-MM-DD}— today's date{step1_output}— full output from Step 1{time_range}— user's chosen window
Launch one background research agent via the Task tool with subagent_type: general-purpose (or your project's research subagent if one is registered).
Why the prompt below is templated literally: the subagent runs in isolation without the conversation's context. Its prompt has to carry every parameter explicitly, and small wording changes ("supplement" vs "add") subtly change how aggressively it searches. Treat the template as a stable contract — replace {xxx} variables and keep the rest as-is so results stay comparable across runs.
Prompt template (replace variables, preserve structure):
## Task
Research topic: {topic}
Current date: {YYYY-MM-DD}
Based on the following initial framework, supplement latest items and recommended research fields.
## Existing Framework
{step1_output}
## Goals
1. Verify if existing items are missing important objects
2. Supplement items based on missing objects
3. Continue searching for {topic} related items within {time_range} and supplement
4. Supplement new fields
## Output Requirements
Return structured results directly (do not write files):
### Supplementary Items
- item_name: Brief explanation (why it should be added)
...
### Recommended Supplementary Fields
- field_name: Field description (why this dimension is needed)
...
### Sources
- [Source1](url1)
- [Source2](url2)Worked example (topic = "AI Coding History"):
## Task
Research topic: AI Coding History
Current date: 2025-12-30
Based on the following initial framework, supplement latest items and recommended research fields.
## Existing Framework
### Items List
1. GitHub Copilot: Developed by Microsoft/GitHub, first mainstream AI coding assistant
2. Cursor: AI-first IDE, based on VSCode
...
### Field Framework
- Basic Info: name, release_date, company
- Technical Features: underlying_model, context_window
...
## Goals
1. Verify if existing items are missing important objects
2. Supplement items based on missing objects
3. Continue searching for AI Coding History related items within since 2024 and supplement
4. Supplement new fields
## Output Requirements
[as above]Step 3 — Ask user for existing fields
AskUserQuestion: do you have an existing field-definitions file we should merge with? If yes, Read it and fold it into the field set.
Step 4 — Generate outline (two files)
Merge {step1_output}, the subagent's {step2_output}, and any user-supplied fields. Write two files:
`outline.yaml` — items + execution config:
topic: <research topic>
items:
- name: <item>
category: <optional>
description: <optional>
execution:
batch_size: <parallel agents — confirm with AskUserQuestion>
items_per_agent: <items per agent — confirm with AskUserQuestion>
output_dir: ./results # default`fields.yaml` — field definitions:
field_categories:
- category: <name>
fields:
- name: <field_name>
description: <what to capture>
detail_level: brief | moderate | detailed
required: false # optional; validator checks required fields are present
uncertain: [] # reserved — auto-filled during /research-deepdetail_level runs brief → moderate → detailed. The uncertain array is populated by /research-deep; leave it empty here.
Step 5 — Save and confirm
- Create
./{topic_slug}/ - Save
outline.yamlandfields.yaml - Show both to the user for confirmation before they move on
Follow-up commands
/research-add-items— append more research objects/research-add-fields— append more field definitions/research-deep— start parallel deep research/research-report— summarise results
Gotchas
- `{topic_slug}` is conventionally a kebab-case slug of the topic (e.g.
AI Coding History→ai-coding-history). The follow-up skills auto-locate*/outline.yaml, so the directory name only needs to be filesystem-safe and unique. - The subagent prompt template in Step 2 is a contract, not a suggestion.
/research-deepand/research-reportboth assume the schema produced here is stable. If you reword the template ad-hoc, downstream skills may receive fields they don't know how to render. - `required: true` on a field is enforced at deep-phase validation (
validate_json.py) — missing required fields fail the validator. Use sparingly; over-marking creates noise in the report. - The `uncertain` array in `fields.yaml` is reserved for downstream use. Don't put anything in it during this skill;
/research-deeppopulates it per-item.
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
import json
import sys
from collections import defaultdict
from pathlib import Path
import yaml
CATEGORY_MAPPING = {
"basic_info": ["basic_info", "Basic Info"],
"technical_features": ["technical_features", "technical_characteristics", "Technical Features"],
"performance_metrics": ["performance_metrics", "performance", "Performance Metrics"],
"milestone_significance": ["milestone_significance", "milestones", "Milestone Significance"],
"business_info": ["business_info", "commercial_info", "Business Info"],
"competition_ecosystem": ["competition_ecosystem", "competition", "Competition Ecosystem"],
"history": ["history", "History"],
"market_positioning": ["market_positioning", "market", "Market Positioning"],
}
_SKIP_KEYS = {"_source_file", "uncertain"}
def load_fields_yaml(fields_path):
with fields_path.open(encoding="utf-8") as f:
data = yaml.safe_load(f)
items = [
(field["name"], category["category"], field.get("required", False))
for category in data.get("field_categories", [])
for field in category.get("fields", [])
]
all_fields = {name for name, _, _ in items}
required_fields = {name for name, _, required in items if required}
field_categories = {name: category for name, category, _ in items}
return all_fields, required_fields, field_categories
def extract_json_fields(data, category_mapping=None):
category_mapping = CATEGORY_MAPPING if category_mapping is None else category_mapping
nested_keys = {k for keys in category_mapping.values() for k in keys}
fields = set()
stack = [(data, True)]
while stack:
obj, is_category_level = stack.pop()
if isinstance(obj, dict):
for k, v in obj.items():
if k in _SKIP_KEYS:
continue
if is_category_level and k in nested_keys:
if isinstance(v, dict):
stack.append((v, True))
continue
fields.add(k)
elif isinstance(obj, list):
stack.extend((item, is_category_level) for item in obj if isinstance(item, dict))
return fields
def validate_json(json_path, all_fields, required_fields, field_categories):
with json_path.open(encoding="utf-8") as f:
data = json.load(f)
json_fields = extract_json_fields(data)
covered = all_fields & json_fields
missing = all_fields - json_fields
extra = json_fields - all_fields
missing_required = missing & required_fields
missing_by_category = defaultdict(list)
for field in missing:
missing_by_category[field_categories.get(field, "Unknown")].append(field)
return {
"file": json_path.name,
"total_defined": len(all_fields),
"covered": len(covered),
"missing": len(missing),
"extra": len(extra),
"coverage_rate": len(covered) / len(all_fields) * 100 if all_fields else 100,
"missing_required": sorted(missing_required),
"missing_optional": sorted(missing - required_fields),
"missing_by_category": {k: sorted(v) for k, v in missing_by_category.items()},
"extra_fields": sorted(extra),
"valid": len(missing_required) == 0,
}
def print_result(result, verbose=True):
status = "PASS" if result["valid"] else "FAIL"
line = "=" * 60
print(f"\n{line}")
print(f"[{status}] {result['file']}")
print(line)
print(f"Coverage: {result['coverage_rate']:.1f}% ({result['covered']}/{result['total_defined']})")
if result["missing_required"]:
print(f"\n[ERROR] Missing required fields ({len(result['missing_required'])}):")
print("\n".join(f" - {f}" for f in result["missing_required"]))
if verbose and result["missing_optional"]:
missing_required = set(result["missing_required"])
print(f"\n[WARN] Missing optional fields ({len(result['missing_optional'])}):")
for cat in sorted(result["missing_by_category"]):
optional = [f for f in result["missing_by_category"][cat] if f not in missing_required]
if optional:
print(f" [{cat}]: {', '.join(optional)}")
if verbose and result["extra_fields"]:
extra = result["extra_fields"]
print(f"\n[INFO] Extra fields ({len(extra)}):")
print(f" {', '.join(extra[:10])}")
if len(extra) > 10:
print(f" ... and {len(extra) - 10} more")
def main():
import argparse
parser = argparse.ArgumentParser(description="Validate whether JSON files cover all fields defined in fields.yaml")
parser.add_argument("--fields", "-f", type=str, help="Path to fields.yaml", default="fields.yaml")
parser.add_argument("--json", "-j", type=str, nargs="*", help="JSON file paths to validate")
parser.add_argument("--dir", "-d", type=str, help="Directory containing JSON files", default="results")
parser.add_argument("--quiet", "-q", action="store_true", help="Show summary only")
args = parser.parse_args()
fields_path = Path(args.fields)
if not fields_path.exists():
for p in (Path.cwd() / "fields.yaml", Path.cwd().parent / "fields.yaml"):
if p.exists():
fields_path = p
break
if not fields_path.exists():
print(f"[ERROR] fields.yaml not found: {fields_path}")
sys.exit(1)
print(f"Field definition file: {fields_path}")
all_fields, required_fields, field_categories = load_fields_yaml(fields_path)
print(f"Total fields: {len(all_fields)} (required: {len(required_fields)}, optional: {len(all_fields) - len(required_fields)})")
json_files = (
[Path(p) for p in args.json]
if args.json
else sorted(Path(args.dir).glob("*.json")) if Path(args.dir).exists() else []
)
if not json_files:
print("[WARN] No JSON files found")
sys.exit(0)
results = []
for json_path in json_files:
if not json_path.exists():
print(f"[WARN] File not found: {json_path}")
continue
result = validate_json(json_path, all_fields, required_fields, field_categories)
results.append(result)
print_result(result, verbose=not args.quiet)
line = "=" * 60
print(f"\n{line}")
print("Summary")
print(line)
passed = sum(1 for r in results if r["valid"])
avg_coverage = sum(r["coverage_rate"] for r in results) / len(results) if results else 0
print(f"Validation passed: {passed}/{len(results)}")
print(f"Average coverage: {avg_coverage:.1f}%")
if passed < len(results):
sys.exit(1)
if __name__ == "__main__":
main()