New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Gsd Phase Researcher

by allgpt-co in allgpt-co/QuickVoice

Researches phase implementation for planning. An agent skill from allgpt-co/QuickVoice.

MITAuto-check passedAgent Workflows

Install Gsd Phase Researcher

skills CLI
$ npx skills add allgpt-co/QuickVoice --skill gsd-phase-researcher -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install allgpt-co/QuickVoice gsd-phase-researcher --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/allgpt-co/QuickVoice.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/gsd/agents/phase-researcher .claude/skills/gsd-phase-researcher && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
gsd-phase-researcher
GitHub stars
488
Token cost
~1.9k tokens
SKILL.md length
621 words
Files
1
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

Researches phase implementation for planning. An agent skill from allgpt-co/QuickVoice.

  • Works in 8 steps: Receive Context → Analyze Phase Requirements → Identify Research Areas → …
  • Agent Workflows work in your project
  • SKILL.md covers When to Use, Core Responsibilities, Philosophy and Process, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Gsd Phase Researcher is an agent skill from allgpt-co/QuickVoice. Researches phase implementation for planning. Spawned by /gsd:plan-phase or /gsd:research-phase orchestrators.

Its SKILL.md is about 1.9k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. The repository describes itself as: Open-source, self-hostable platform for building and operating AI phone agents. The licence is MIT.

When your agent uses it

  • Agent Workflows work in your project

Example prompts

  • “Use the gsd-phase-researcher skill to research phase implementation for planning. An agent skill from allgpt-co/QuickVoice”
  • “/gsd-phase-researcher”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Receive Context
  2. Analyze Phase Requirements
  3. Identify Research Areas
  4. Explore Codebase Context
  5. Research Domain Knowledge
  6. Synthesize Findings
  7. Write DISCOVERY.md
  8. Return Confirmation

What it can do on your machine

Read from SKILL.md and the folder at commit 89fa8ff. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Gsd Phase Researcher loads about 1.9k tokens when it runs. Until then it costs about 33 tokens; SKILL.md has 621 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~33
When it runs · the whole SKILL.md, loaded when a task matches
~1.9k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from allgpt-co/QuickVoice at commit 89fa8ff, republished under its MIT licence (© allgpt-co). 621 words, ~1,860 tokens.

Download SKILL.mdSave it as .claude/skills/gsd-phase-researcher/SKILL.md (or your agent's skills folder).
name
gsd-phase-researcher
description
Researches phase implementation for planning. Spawned by /gsd:plan-phase or /gsd:research-phase orchestrators.
version
1.0.0
author
GSD Project
tags
research, phase-planning, domain-knowledge
triggers
research phase, investigate phase implementation
tools
Read, Write, Bash, WebFetch, mcp__context7__*

GSD Phase Researcher

Researches how to implement a specific phase by exploring domain knowledge, existing patterns, and codebase context.

When to Use

Use this agent when:

  • A phase needs to be planned but requires research first
  • You need to understand what technologies, patterns, or approaches are standard for implementing the phase
  • You are spawned by /gsd:plan-phase (standard planning) or /gsd:research-phase (explicit research)
  • The phase involves new domains, unfamiliar libraries, or architectural decisions

Core Responsibilities

  1. Research the domain - Understand standard approaches, libraries, and patterns
  2. Explore existing codebase - Find relevant implementations and patterns
  3. Identify key decisions - What choices need to be made during planning
  4. Document findings - Create DISCOVERY.md with actionable recommendations
  5. Provide rationale - Explain why certain approaches are recommended

Philosophy

Research for Planning, Not Implementation

Your goal is NOT to implement the phase. Your goal is to provide the planner with enough context to create good plans.

Focus areas:

  • Technology choices (which libraries, frameworks)
  • Architectural patterns (how to structure the code)
  • Integration approaches (how to connect with external services)
  • Common pitfalls (what to avoid)

Be specific: "Use React" is not helpful. "Use React with shadcn/ui for components and Tailwind for styling" is actionable.

Be opinionated: The planner needs clear recommendations, not a list of options. Say "Use X because Y" not "Consider X or Y."

Codebase Context

Always explore the existing codebase to understand:

  • Established patterns and conventions
  • Existing implementations that can be referenced
  • Technology choices already made
  • File structure and organization

Process

Step 1: Receive Context

Read the research prompt provided by the orchestrator:

markdown
<objective>
Research how to implement Phase {phase_number}: {phase_name}
</objective>

<context>
**Phase description:**
{phase_description}

**Requirements (if any):**
{requirements}

**Prior decisions:**
{decisions}

**Phase context (if any):**
{phase_context}
</context>

<output>
Write research findings to: {phase_dir}/{phase}-RESEARCH.md
</output>
Step 2: Analyze Phase Requirements

Extract key requirements from the phase description:

  • What functionality needs to be implemented?
  • What are the key constraints or requirements?
  • What are the success criteria?
Step 3: Identify Research Areas

Based on phase requirements, determine what needs to be researched:

Common research areas:

  • Technology stack (libraries, frameworks, tools)
  • Architecture patterns (how to structure components)
  • Integration approaches (APIs, databases, external services)
  • Security considerations (auth, data protection)
  • Performance considerations (optimization strategies)
  • Testing approaches (how to test this functionality)

Niche domains:

  • 3D graphics (WebGL, Three.js, shaders)
  • Games (physics engines, game loops)
  • Audio (Web Audio API, DSP, streaming)
  • ML/AI (TensorFlow, PyTorch, model serving)

For niche domains, recommend /gsd:research-phase instead of relying on this agent's research.

Show full SKILL.md (247 more words)Show less
Step 4: Explore Codebase Context

Check for existing implementations and patterns:

bash
# Find relevant files by keywords
grep -r "auth\|login\|user" src/ --include="*.ts" --include="*.tsx" | head -20

# Check existing patterns
find . -name "*.ts" -o -name "*.tsx" | head -20

# Look for similar functionality
grep -r "similar.*pattern\|existing.*implementation" .planning/ --include="*.md" | head -10
Step 5: Research Domain Knowledge

Use Context7 MCP or WebSearch to research:

  • Standard libraries and frameworks for this type of work
  • Best practices and patterns
  • Common pitfalls and how to avoid them
  • Security considerations
  • Performance optimization techniques

For technology research:

  • Check official documentation
  • Look for recent blog posts and articles
  • Compare multiple options
  • Identify version requirements and compatibility issues
Step 6: Synthesize Findings

Combine research from:

  • Domain knowledge research
  • Codebase context exploration
  • Existing patterns and implementations
Step 7: Write DISCOVERY.md

Create a comprehensive research document with:

markdown
---
phase: XX-name
researched: YYYY-MM-DDTHH:MM:SSZ

## Research Summary

[Brief 2-3 paragraph summary of findings]

## Technology Recommendations

[Specific technology choices with rationale]

## Architecture Recommendations

[Structural patterns and organization]

## Implementation Considerations

[Key decisions and trade-offs]

## Codebase Patterns

[Existing patterns to follow or extend]

## Potential Pitfalls

[Common mistakes and how to avoid them]

## Integration Notes

[Any external service considerations]

## Open Questions

[Any areas that need clarification during planning]

---
_Phase {XX} Research_
Step 8: Return Confirmation

Return brief confirmation without including document contents:

markdown
## RESEARCH COMPLETE

**Phase:** {phase_number}
**Research written:** .planning/phases/{phase_dir}/{phase}-RESEARCH.md

**Key findings:**
- [Finding 1]
- [Finding 2]
- [Finding 3]

**Ready for planning.**

Structured Returns

Research Complete
markdown
## RESEARCH COMPLETE

**Phase:** {phase_number}
**Research written:** .planning/phases/{phase_dir}/{phase}-RESEARCH.md

**Key findings:**
- [Finding 1]
- [Finding 2]
- [Finding 3]

**Ready for planning.**
Research Blocked
markdown
## RESEARCH BLOCKED

**Blocked by:** [issue]

**Missing context:**
- [list what's needed]

**Awaiting:**
[What input is needed to continue]

Critical Rules

  • Be specific and actionable - Provide concrete recommendations, not vague suggestions
  • Document rationale - Explain WHY certain approaches are recommended
  • Explore codebase - Always check for existing patterns and implementations
  • Identify key decisions - Highlight choices the planner must make
  • Write DISCOVERY.md - Create the research document for planning reference
  • Return confirmation only - Don't include document contents in your response
  • Flag niche domains - For 3D, games, audio, ML, recommend dedicated research phase

Success Criteria

  • Phase requirements analyzed and understood
  • Research areas identified based on requirements
  • Codebase context explored for relevant patterns
  • Domain knowledge researched (Context7/WebSearch)
  • Findings synthesized into actionable recommendations
  • Key decisions identified
  • DISCOVERY.md created with complete content
  • Confirmation returned (not document contents)
  • @skills/gsd/agents/planner - Agent that will use your DISCOVERY.md to create plans
  • @skills/gsd/agents/codebase-mapper - For understanding existing codebase patterns
  • @skills/gsd/references/git-integration - For checking existing implementations

© allgpt-co, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/gsd/agents/phase-researcher of allgpt-co/QuickVoice.

Open the folder on GitHubat commit 89fa8ff

Compare with similar skills

Gsd Phase Researcher next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Gsd Phase Researcher compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Gsd Phase Researcher this skillallgpt-co/QuickVoice488—~1.9kAutomated safety check: PassMIT
Journal AdaptWantongC/journal-adapt-writing-skill7961 repos~5.2kAutomated safety check: PassMIT
Business Brainstormcoreyhaines31/makerskills851—~1.7kAutomated safety check: PassMIT
Proposal AgentOpenRSI-Foundation/OpenRSI-Index207—~5.1kAutomated safety check: PassApache-2.0
Research Junshijunshi-research/research-junshi126—~2.1kAutomated safety check: PassApache-2.0
Open-Science Host Inspectionaipoch/open-science5.5k—~3.8kAutomated safety check: PassApache-2.0

Similar skills

  • Journal Adapt

    WantongC/journal-adapt-writing-skill

    Dynamic academic writing skill generator. An agent skill from WantongC/journal-adapt-writing-skill.

    796 GitHub starsUsed in 1 repo~5.2k tokens
    Agent WorkflowsAuto-check passed

  • Business Brainstorm

    coreyhaines31/makerskills

    When you want to pressure-test a potential new business, product, or side project against the serial-founder filter.

    851 GitHub stars~1.7k tokensUpdated 3 days ago
    Agent WorkflowsAuto-check passed

  • Proposal Agent

    OpenRSI-Foundation/OpenRSI-Index

    A skill your agent uses when a contributor wants to create, repair, or complete an OpenRSI-Index AutoResearch task proposal grounded in a remote model-development repository, including…

    207 GitHub stars~5.1k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed

  • Research Junshi

    junshi-research/research-junshi

    Personalized academic literature digests and ranked research ideas grounded in the researcher's papers and persistent memory.

    126 GitHub stars~2.1k tokensUpdated 25 days ago
    Agent WorkflowsAuto-check passed

  • Open-Science Host Inspection

    aipoch/open-science

    Teaches an agent to inspect Open-Science's JavaScript control REPL, check which host.* calls are allowed, and find project files, sessions and agent frames.

    5.5k GitHub stars~3.8k tokensUpdated today
    Agent WorkflowsAuto-check passed

  • Audit

    leanEthereum/leanSpec

    Read-only, multi-agent audit of the leanSpec codebase. An agent skill from leanEthereum/leanSpec.

    143 GitHub stars~2.5k tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed

More from allgpt-co/QuickVoice

All 12 skills in this repo

  • Livekit Agents

    allgpt-co/QuickVoice

    Build voice AI agents with LiveKit Cloud and the Agents SDK.

    488 GitHub stars~3.3k tokensUpdated 6 days ago
    Auto-check: notes

  • Gsd

    allgpt-co/QuickVoice

    Get Shit Done (GSD) - A comprehensive project management system for solo developers using Claude agents

    488 GitHub stars~2k tokensUpdated 6 days ago
    Auto-check passed

  • Gsd Codebase Mapper

    allgpt-co/QuickVoice

    Explores codebase and writes structured analysis documents. An agent skill from allgpt-co/QuickVoice.

    488 GitHub stars~3.5k tokensUpdated 6 days ago
    Auto-check: notes

  • Gsd Integration Checker

    allgpt-co/QuickVoice

    Verifies that integrations work correctly by checking endpoints, responses, and data flow.

    488 GitHub stars~2.8k tokensUpdated 6 days ago
    Auto-check passed

  • Gsd Plan Checker

    allgpt-co/QuickVoice

    Validates plan quality by checking task completeness, dependency correctness, and scope sanity.

    488 GitHub stars~2.5k tokensUpdated 6 days ago
    Auto-check passed

  • Gsd Executor

    allgpt-co/QuickVoice

    Executes GSD plans with atomic commits, deviation handling, checkpoint protocols, and state management.

    488 GitHub stars~4.7k tokensUpdated 6 days ago
    Auto-check: warnings

Categories

Questions about Gsd Phase Researcher

What does Gsd Phase Researcher do?

Researches phase implementation for planning. An agent skill from allgpt-co/QuickVoice. Gsd Phase Researcher is an agent skill from allgpt-co/QuickVoice. Researches phase implementation for planning.

When should I use Gsd Phase Researcher?

Gsd Phase Researcher fits situations like: agent Workflows work in your project.

How do I install Gsd Phase Researcher in Claude Code?

Run `npx skills add allgpt-co/QuickVoice --skill gsd-phase-researcher -a claude-code`. Or copy the skill folder (.claude/skills/gsd/agents/phase-researcher in allgpt-co/QuickVoice) into .claude/skills/gsd-phase-researcher in your project. Claude Code loads it when a task matches its description.

How do I install Gsd Phase Researcher in Codex?

Run `npx skills add allgpt-co/QuickVoice --skill gsd-phase-researcher -a codex`. Or copy the skill folder (.claude/skills/gsd/agents/phase-researcher in allgpt-co/QuickVoice) into .agents/skills/gsd-phase-researcher in your project. Codex loads it when a task matches its description.

Can I use Gsd Phase Researcher in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add allgpt-co/QuickVoice --skill gsd-phase-researcher -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/gsd-phase-researcher, .gemini/skills/gsd-phase-researcher, .github/skills/gsd-phase-researcher and .opencode/skills/gsd-phase-researcher in your project.

What does Gsd Phase Researcher need to run?

SKILL.md names no scripts, command-line tools or credentials: Gsd Phase Researcher is instructions for the agent only.

Does Gsd Phase Researcher access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Gsd Phase Researcher safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Gsd Phase Researcher use?

Gsd Phase Researcher is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Gsd Phase Researcher use?

About 1.9k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Gsd Phase Researcher?

Skills that share tags, products or a category with Gsd Phase Researcher: Journal Adapt (WantongC/journal-adapt-writing-skill, 796 stars), Business Brainstorm (coreyhaines31/makerskills, 851 stars), Proposal Agent (OpenRSI-Foundation/OpenRSI-Index, 207 stars) and Research Junshi (junshi-research/research-junshi, 126 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Gsd Phase Researcher?

allgpt-co (a GitHub organization) maintains it in allgpt-co/QuickVoice, which has 488 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on October 5, 2026.

Source: allgpt-co/QuickVoice on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.