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

Workflow Research

by nabeelhyatt in nabeelhyatt/coworkpowers

Research and plan a knowledge work task thoroughly before execution.

MITAuto-check passed

Install Workflow Research

skills CLI
$ npx skills add nabeelhyatt/coworkpowers --skill workflow-research -a claude-code

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

GitHub CLI
$ gh skill install nabeelhyatt/coworkpowers workflow-research --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/nabeelhyatt/coworkpowers.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/workflow-research .claude/skills/workflow-research && 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
workflow-research
GitHub stars
114
Token cost
~2.2k tokens
SKILL.md length
902 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
MIT

At a glance

Research and plan a knowledge work task thoroughly before execution.

  • Works in 8 steps: Discover Available Tools → Understand the Task → 5: Ask Clarifying Questions → …
  • Starting any significant piece of work - drafting important communications
  • SKILL.md covers Process, Important Principles, Next Step and Anti-Patterns to Avoid
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Workflow Research is an agent skill from nabeelhyatt/coworkpowers. Research and plan a knowledge work task thoroughly before execution. Use when starting any significant piece of work - drafting important communications, making strategic decisions, preparing for meetings, or tackling analysis projects. Triggers on requests like 'help me prepare for', 'I need to draft', 'plan out', or any high-stakes knowledge work.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Superpowers for knowledge work in Claude Code. The licence is MIT.

When your agent uses it

  • Starting any significant piece of work - drafting important communications
  • Making strategic decisions
  • Preparing for meetings
  • Tackling analysis projects

Example prompts

  • “help me prepare for”
  • “I need to draft”
  • “plan out”
  • “/workflow-research”

Workflow steps

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

  1. Discover Available Tools
  2. Understand the Task
  3. 5: Ask Clarifying Questions
  4. Search Past Learnings
  5. Parallel Research
  6. Research Decision
  7. Synthesize the Plan
  8. User Approval

What it can do on your machine

Read from SKILL.md and the folder at commit 65a1fb7. 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).

    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

Workflow Research loads about 2.2k tokens when it runs. Until then it costs about 92 tokens; SKILL.md has 902 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~92
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 nabeelhyatt/coworkpowers at commit 65a1fb7, republished under its MIT licence (© nabeelhyatt). 902 words, ~2,227 tokens.

Download SKILL.mdSave it as .claude/skills/workflow-research/SKILL.md (or your agent's skills folder).
name
workflow-research
description
Research and plan a knowledge work task thoroughly before execution. Use when starting any significant piece of work - drafting important communications, making strategic decisions, preparing for meetings, or tackling analysis projects. Triggers on requests like 'help me prepare for', 'I need to draft', 'plan out', or any high-stakes knowledge work.

Research: Knowledge Work Research Workflow

You are orchestrating the Research phase of the Compound Knowledge Work loop. Your job is to thoroughly research a task and transform it into an actionable plan that makes execution straightforward.

80% of compound knowledge work is in research and review. Do not rush this phase.

Process

Phase 0: Discover Available Tools

Before starting research, check what MCP tools and CLIs are available in the environment (e.g., email, calendar, meeting notes, CRM, company intel). Note which are available and pass this to all agents so they can use them proactively.

Phase 1: Understand the Task

  1. Read the task description carefully. If the user provided a document, file, or URL, read it thoroughly.

  2. Classify the work type:

    • Communication (email, memo, announcement, presentation)
    • Decision (strategic choice, vendor selection, resource allocation)
    • Analysis (market research, financial analysis, competitive review)
    • Meeting (preparation, facilitation, follow-up)
    • Coaching (leadership challenge, personal effectiveness)
    • Operations (process design, project planning, documentation)

  3. Determine stakes and complexity:

    • Low stakes: Internal notes, routine updates -> lighter planning
    • Medium stakes: Team communications, standard decisions -> moderate planning
    • High stakes: Board communications, strategic decisions, sensitive topics -> full planning
Phase 1.5: Ask Clarifying Questions

Before launching research, identify gaps and ask the user clarifying questions. This prevents wasted research on the wrong problem.

When to ask questions:

  • Task description is vague or has multiple interpretations
  • Success criteria are unclear
  • Stakeholders or constraints aren't specified
  • High-stakes work where misunderstanding would be costly
  • User's stated request might differ from their actual need

Question patterns (from superpowers):

  • Ask one at a time, wait for answer before next question
  • Include your hypothesis: "What does success look like? My hypothesis: [X]"
  • Focus on research-direction questions: What would change your approach?
  • Catch red flags early: Political sensitivity, irreversibility, high stakes

Hard Gate for high-stakes work - You MUST get answers to:

  1. Who is the audience/stakeholder?
  2. What does success look like?
  3. What constraints exist (political, budget, timing)?
  4. What have you tried before that didn't work?

Example questions:

  • "What does success look like for this communication? My hypothesis: Board approval vs. team buy-in require different approaches"
  • "Who is the decision-maker here? This affects stakeholder mapping"
  • "What's the timeline? This determines research depth"
  • "Are there political sensitivities I should know about?"
  • "What have you already tried? What didn't work?"

When to skip this phase:

  • Low-stakes routine work (internal notes, simple updates)
  • User provided comprehensive brief with explicit success criteria
  • Task is crystal clear and unambiguous
Phase 2: Search Past Learnings

Before any new research, check what we already know. This is where compounding pays off.

In Claude Code (file-based retrieval):

  1. Check the learnings index at .context/learnings/INDEX.md - scan for matching category, type, and tags.
  2. Search by category: Grep .context/learnings/[category]/ for the relevant work type (e.g., communication/, decision/, meeting/).
  3. Search by type: Look specifically for pattern and template insights that match the current task.
  4. Search by keywords: Grep across all learnings for topic-specific terms (stakeholder names, project names, framework names).
  5. Search for preferences: Grep for type: preference insights in the relevant category - these capture style, tone, and detail preferences from previous work.

If past learnings exist, incorporate them into the plan:

  • Reuse patterns (type: pattern) that worked before
  • Avoid failures (type: failure) that were documented
  • Apply templates (type: template) if a relevant one exists
  • Honor preferences (type: preference) from previous work in this category

Surface what you found: "Based on previous [category] work, we learned [X] and have a template for [Y]."

Show full SKILL.md (324 more words)Show less
Phase 3: Parallel Research

Launch research agents in parallel based on the work type. Use the Task tool with appropriate subagents. Pass the stakes level to each agent so they can calibrate depth.

Scale agents to stakes:

StakesAgents to Run
Lowcontext-gatherer only (brief scan, no web search)
Mediumcontext-gatherer + 1-2 agents from the work type table below
HighFull agent roster from the work type table below

Agent roster by work type (for medium/high stakes):

Work TypeAdditional Agents
Communicationstakeholder-mapper, precedent-researcher
Decisionstakeholder-mapper, constraint-analyzer, precedent-researcher
Analysisconstraint-analyzer, precedent-researcher
Meetingstakeholder-mapper, precedent-researcher
Coachingstakeholder-mapper
Operationsconstraint-analyzer, precedent-researcher

For high-stakes work, always add:

  • External research via web search for best practices, frameworks, and examples
Phase 4: Research Decision

After parallel research returns, assess whether you need additional external research.

Always research externally when:

  • The topic involves legal, compliance, or regulatory considerations
  • The decision is irreversible or very high stakes
  • The domain is unfamiliar
  • Best practices or industry standards exist that should be consulted
Phase 5: Synthesize the Plan

Use the plan-synthesizer agent mindset to create the final plan.

Plan Output Format:

markdown
# Plan: [Task Name]

## Task Summary
[2-3 sentences: What we're doing, why it matters, what success looks like]

## Context Brief
[Key context gathered - what we know, what matters, what's sensitive]

## Prior Learnings Applied
[What we found from past compound phases, organized by type:
- **Patterns**: [approaches that worked before]
- **Failures**: [mistakes to avoid]
- **Templates**: [reusable structures available]
- **Preferences**: [style/tone/detail preferences for this category]
If none found, state "No prior learnings found for this work type."]

## Stakeholder Considerations
[Who's affected, their interests, anticipated reactions]

## Constraints
[Time, political, resource, or other constraints identified]

## Relevant Precedents
[What's been done before in similar situations, what worked/didn't]

## Approach
[Step-by-step plan for execution]

### Step 1: [Action]
- **What**: [Specific action]
- **Why**: [Rationale]
- **Agent**: [Which work-phase agent to use]
- **Inputs needed**: [What information is required]

### Step 2: [Action]
[Same structure]

## Review Plan
[Which review agents should evaluate the output, and why]

| Reviewer | Why Needed |
|----------|------------|
| [Agent] | [What they'll catch] |

## Success Criteria
- [ ] [Measurable outcome 1]
- [ ] [Measurable outcome 2]
- [ ] [Measurable outcome 3]

## Risks & Mitigations
| Risk | Likelihood | Mitigation |
|------|------------|------------|
| [Risk] | [H/M/L] | [How to address] |

## Timeline
[Suggested sequencing and any time constraints]
Phase 6: User Approval

Present the plan to the user. Ask if they want to:

  1. Approve and proceed to the Work phase
  2. Modify specific sections
  3. Add context you may have missed
  4. Adjust scope (more or less thorough)

Important Principles

  • Plans are living documents. They will be updated during execution.
  • Front-load the thinking. Every minute spent planning saves ten in execution.
  • Be explicit about assumptions. If you're guessing, say so.
  • Match rigor to stakes. A routine email doesn't need a 20-step plan.
  • Include review in the plan. Every plan should specify which reviewers will check the output.

Next Step

When the plan is approved, move to execution: /coworkpowers:workflow-work

Anti-Patterns to Avoid

  • Planning so long that urgency passes
  • Over-planning low-stakes work
  • Skipping stakeholder analysis on communications
  • Assuming context instead of gathering it
  • Creating plans that are too abstract to execute

© nabeelhyatt, 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 skills/workflow-research of nabeelhyatt/coworkpowers.

Open the folder on GitHubat commit 65a1fb7

Compare with similar skills

Workflow Research 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.

Workflow Research compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Workflow Research this skillnabeelhyatt/coworkpowers114—~2.2kAutomated safety check: PassMIT
Thoroughness Scoringrohitg00/pro-workflow2.9k—~1.3kAutomated safety check: PassNone
Thoroughnesspr-pm/prpm122—~1.1kAutomated safety check: PassMIT
Thorough Code Reviewpretend1111/claude-desktop-app4961 repos~502Automated safety check: PassCustom licence
Repo Research Analystudecode/plate17k—~4.2kAutomated safety check: PassCustom licence
Octopus Researchnyldn/claude-octopus4.2k1 repos~1.9kAutomated safety check: PassMIT

Similar skills

  • Thoroughness Scoring

    rohitg00/pro-workflow

    Score every decision point with a Thoroughness Rating (1-10).

    2.9k GitHub stars~1.3k tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed

  • Thoroughness

    pr-pm/prpm

    A skill your agent uses when implementing complex multi-step tasks, fixing critical bugs, or when quality and completeness matter more than speed - ensures comprehensive implementation without…

    122 GitHub stars~1.1k tokensUpdated 2 days ago
    Testing & QAAuto-check passed

  • Thorough Code Review

    pretend1111/claude-desktop-app

    Reviews code or recent changes for bugs, security issues, performance problems and maintainability, reporting findings by severity with the reason and a fix.

    496 GitHub starsUsed in 1 repo~502 tokens
    DevelopmentAuto-check passed

  • Repo Research Analyst

    udecode/plate

    Conducts thorough research on repository structure, documentation, conventions, and implementation patterns.

    17k GitHub stars~4.2k tokensUpdated today
    Auto-check passed

  • Octopus Research

    nyldn/claude-octopus

    Thorough research across multiple sources — use for complex topics needing broad synthesis

    4.2k GitHub starsUsed in 1 repo~1.9k tokens
    Productivity & AutomationAuto-check passed

  • Skill Code Review

    nyldn/claude-octopus

    Expert multi-AI code review with inline PR comments — use for thorough quality and security analysis

    4.2k GitHub starsUsed in 1 repo~2.8k tokens
    DevelopmentAuto-check: warnings

More from nabeelhyatt/coworkpowers

  • Workflow Compound

    nabeelhyatt/coworkpowers

    Extract and store learnings from completed knowledge work to make the next task easier.

    114 GitHub stars~2.2k tokensUpdated 7 mo ago
    Auto-check passed

  • Workflow Review

    nabeelhyatt/coworkpowers

    Run parallel multi-agent review on completed knowledge work.

    114 GitHub stars~1.3k tokensUpdated 7 mo ago
    Auto-check passed

  • Workflow Work

    nabeelhyatt/coworkpowers

    Execute a knowledge work plan efficiently while maintaining quality.

    114 GitHub stars~1.2k tokensUpdated 7 mo ago
    Auto-check passed

Questions about Workflow Research

What does Workflow Research do?

Research and plan a knowledge work task thoroughly before execution. Workflow Research is an agent skill from nabeelhyatt/coworkpowers. Research and plan a knowledge work task thoroughly before execution.

When should I use Workflow Research?

Workflow Research fits situations like: starting any significant piece of work - drafting important communications; making strategic decisions; preparing for meetings; tackling analysis projects.

How do I install Workflow Research in Claude Code?

Run `npx skills add nabeelhyatt/coworkpowers --skill workflow-research -a claude-code`. Or copy the skill folder (skills/workflow-research in nabeelhyatt/coworkpowers) into .claude/skills/workflow-research in your project. Claude Code loads it when a task matches its description.

How do I install Workflow Research in Codex?

Run `npx skills add nabeelhyatt/coworkpowers --skill workflow-research -a codex`. Or copy the skill folder (skills/workflow-research in nabeelhyatt/coworkpowers) into .agents/skills/workflow-research in your project. Codex loads it when a task matches its description.

Can I use Workflow Research 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 nabeelhyatt/coworkpowers --skill workflow-research -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/workflow-research, .gemini/skills/workflow-research, .github/skills/workflow-research and .opencode/skills/workflow-research in your project.

What does Workflow Research need to run?

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

Does Workflow Research 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 Workflow Research 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 Workflow Research use?

Workflow Research 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 Workflow Research use?

About 2.2k tokens (SKILL.md is roughly 8.9k 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 Workflow Research?

Skills that share tags, products or a category with Workflow Research: Thoroughness Scoring (rohitg00/pro-workflow, 2.9k stars), Thoroughness (pr-pm/prpm, 122 stars), Thorough Code Review (pretend1111/claude-desktop-app, 496 stars) and Repo Research Analyst (udecode/plate, 17k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Workflow Research?

nabeelhyatt (a GitHub user) maintains it in nabeelhyatt/coworkpowers, which has 114 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on February 15, 2026.

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