agentleFS
DesquaredDesquared/agents-rules-skills/skills/shared-task-workflow/SKILL.md

shared-task-workflow

Skill4 starsChanged 3 months agoMITView on GitHub

Generic, project-abstract task workflow orchestrator. Automatically leverages all existing skills, agents, and rules from this repository. Includes built-in AI safeguards and educational explanations for every implementation, change, or suggestion.

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 9 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never hallucinate, invent code, libraries, files, or facts.

    line 14
  2. Distinctive:

    Never force changes: Always ask for explicit confirmation before modifying code.

    line 15
  3. Distinctive:

    Create a clear step-by-step plan.

    line 31
  4. Distinctive:

    After the user has confirmed the plan, perform the work using the delegated skill(s)/agent(s).

    line 37
  5. Distinctive:

    Verify correctness, consistency with project conventions, and absence of hallucinations.

    line 42
  6. Distinctive:

    If anything is unclear → ask the user immediately.

    line 84
  7. Distinctive:

    If context is missing → request it before proceeding.

    line 85
  8. Distinctive:

    Never output final code changes without user confirmation when modifications are involved.

    line 86
  9. Distinctive:

    Always include the Educational Note section.

    line 87

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Shared Task Workflow

Purpose:
Provide a consistent, high-quality, educational workflow for any development task while remaining completely project-abstract. The AI will adapt to the user's specific tech stack, architecture, naming conventions, and preferences.

Core Principles (always enforce)

  • Stay 100% project-abstract: Never assume any specific framework, language, or architecture. Ask for clarification when needed.
  • Leverage all existing skills, agents, and rules from this repository when they fit the task.
  • Never hallucinate, invent code, libraries, files, or facts.
  • Never force changes: Always ask for explicit confirmation before modifying code.
  • Turn every interaction into a learning opportunity for the software engineer.

Mandatory Workflow (follow exactly)

Phase 0: Safeguards & Context Gathering

  1. Activate shared-ai-safeguards rules.
  2. Collect and summarize project context (language, frameworks, architecture, key conventions, existing patterns).
  3. Output a short context line:
    Context: [Primary language/framework] | [Architecture style] | [Key conventions]

Phase 1: Task Analysis

  • Break down the requested task into clear, actionable requirements.
  • Identify which existing skills/agents from the repository should be used (or adapt the closest one if no exact match exists).

Phase 2: Planning & Delegation

  • Create a clear step-by-step plan.
  • Delegate subtasks to the appropriate skill(s) or agent(s).
  • Present the full plan to the user before any execution.
  • Explicitly ask the user to confirm or adjust the plan before proceeding to execution.

Phase 3: Execution

  • After the user has confirmed the plan, perform the work using the delegated skill(s)/agent(s).
  • Apply all safeguards at every step.

Phase 4: Review & Validation

  • Conduct a thorough review using relevant review skills or rules.
  • Verify correctness, consistency with project conventions, and absence of hallucinations.

Phase 5: Educational Explanation (always include)

Educational Note:
Provide clear, concise education for the software engineer covering:

  • Why this approach was chosen
  • Which rule or skill from the repository was referenced
  • Key software engineering principle being applied
  • One or two practical takeaways
  • Optional: link to official documentation or relevant section in RULES.md

Output Format (strictly follow)

Task: [Clear short title]

Context

[One-line project context summary]

Plan

... ... ...

Execution

[Code changes, files created/updated, etc.]

Review

[Summary of validation results]

Educational Note

  • Why this solution: [explanation]
  • Referenced from: [skill/rule name]
  • Learning takeaway: [1-2 sentences]
  • Further reading: [official docs or RULES.md section if applicable]

Next Steps

[Optional non-forced suggestions. Always ask for confirmation before proceeding.]


Critical Safeguards (never violate)

  • If anything is unclear → ask the user immediately.
  • If context is missing → request it before proceeding.
  • Never output final code changes without user confirmation when modifications are involved.
  • Always include the Educational Note section.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.