[claude] Add research prompt template library (#974) #999

Rockachopa · 2026-03-22T22:43:40Z

Rockachopa commented

2026-03-22 22:43:40 +00:00

Fixes #974

Summary

Creates 6 structured research prompt templates under skills/research/:

Template	Purpose	Cascade Tier
`tool_evaluation.md`	Discover and compare tools in a domain	groq_preferred
`architecture_spike.md`	Investigate system integration approaches	groq_preferred
`game_analysis.md`	Evaluate games for AI agent playability	local_ok
`integration_guide.md`	Step-by-step tool integration with code	groq_preferred
`state_of_art.md`	Landscape survey of a field	groq_preferred
`competitive_scan.md`	Compare a project against alternatives	groq_preferred

Each template has:

Valid YAML frontmatter with name, type, typical_query_count, expected_output_length, and cascade_tier
{slot} placeholders in the body for Timmy to fill from issue descriptions or chat
Clear output format constraints (tables, headers, structured markdown)
Research steps and constraints sections to guide the LLM

Acceptance Criteria

6 template files exist under skills/research/
Each has valid YAML frontmatter with cascade_tier
Each has {slot} placeholders in the body
Templates produce well-structured prompts when filled

Fixes #974 ## Summary Creates 6 structured research prompt templates under `skills/research/`: | Template | Purpose | Cascade Tier | |----------|---------|-------------| | `tool_evaluation.md` | Discover and compare tools in a domain | groq_preferred | | `architecture_spike.md` | Investigate system integration approaches | groq_preferred | | `game_analysis.md` | Evaluate games for AI agent playability | local_ok | | `integration_guide.md` | Step-by-step tool integration with code | groq_preferred | | `state_of_art.md` | Landscape survey of a field | groq_preferred | | `competitive_scan.md` | Compare a project against alternatives | groq_preferred | Each template has: - Valid YAML frontmatter with `name`, `type`, `typical_query_count`, `expected_output_length`, and `cascade_tier` - `{slot}` placeholders in the body for Timmy to fill from issue descriptions or chat - Clear output format constraints (tables, headers, structured markdown) - Research steps and constraints sections to guide the LLM ## Acceptance Criteria - [x] 6 template files exist under `skills/research/` - [x] Each has valid YAML frontmatter with cascade_tier - [x] Each has `{slot}` placeholders in the body - [x] Templates produce well-structured prompts when filled

Rockachopa added 1 commit 2026-03-22 22:43:40 +00:00

feat: add research prompt template library (skills/research/)

Tests / lint (pull_request) Failing after 5s

Details

Tests / test (pull_request) Has been skipped

Details

2889b34958

Create 6 structured research prompt templates with YAML frontmatter,
cascade_tier hints, and {slot} placeholders:

- tool_evaluation.md — discover and compare tools in a domain
- architecture_spike.md — investigate system integration approaches
- game_analysis.md — evaluate games for AI agent playability
- integration_guide.md — step-by-step tool integration with code
- state_of_art.md — landscape survey of a field at a point in time
- competitive_scan.md — compare a project against alternatives

Each template has valid YAML frontmatter (name, type, query count,
output length, cascade_tier) and produces well-structured prompts
when slots are filled.

Fixes #974

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Rockachopa referenced this pull request

2026-03-22 22:43:47 +00:00

[P0] Create research prompt template library (skills/research/) #974

Rockachopa merged commit e35a23cefa into main

2026-03-22 22:44:02 +00:00

Rockachopa deleted branch claude/issue-974

2026-03-22 22:44:03 +00:00

Rockachopa referenced this issue from a commit

2026-03-22 22:44:04 +00:00

[claude] Add research prompt template library (#974) (#999)

Sign in to join this conversation.