agentleFS
Sign inStart free
GstMirabalGstMirabal/Token-Optimized-Agent-Pipeline/skills/sprint-architect/SKILL.md

sprint-architect

Skill1 starsChanged 10 days agoMITView on GitHub

Breaks a strategic Roadmap into a Work Breakdown Structure (components, dependencies, verification gates) and drafts the Implementation Plan before any code changes. Also runs the Legacy Onboarding Protocol for mature projects that predate this framework.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    When a mature project without this framework's roadmap hierarchy is detected, the agent MUST:

    line 32
  2. Very specific:

    Compliance Rule: Every implementation_plan.md generated by the pipeline must follow this standard.

    line 38
  3. Distinctive:

    Language Guard: All project management artifacts MUST be in Technical English (except human-agent chat and explicit plan debate loops).

    line 39

≈ “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

🛠️ Local Skill: Sprint Architect (v2.0.0)

Domain

  • Category: Project Management / Workflow Orchestration
  • Origin: Custom synthesis from skills.sh planning standards.
  • Status: ACTIVE_LOCAL
  • Sovereignty: local (Project-Specific)

Technical Logic

This skill provides the reasoning engine for the deconstruction of strategic Roadmaps. It implements the "Planning-before-execution" pattern, forcing the agent to perform a technical breakdown before proposing code changes. It also holds the core logic for the Legacy Onboarding Protocol.

Procedures

1. WBS (Work Breakdown Structure)

  • The agent must segment each Roadmap Phase into:
    • Components: Physical areas of code affected.
    • Dependencies: Logical execution order (what must exist before what).
    • Verification Gates: Technical acceptance criteria for each task.

2. Implementation Plan Drafting

  • Mandatory plan structure:
    1. Goal: Brief description of the change.
    2. Proposed Changes: Grouped by component.
    3. Verification Plan: Specific commands and tests.

3. Legacy Onboarding Protocol

  • When a mature project without this framework's roadmap hierarchy is detected, the agent MUST:
    1. Audit via Omni-Minimizer: Invoke skills/omni-context-minimizer/scripts/omni_minimizer.py to extract the full AST structural skeleton of the legacy code.
    2. Retroactive Mapping: Draft retrospective Roadmaps and Implementation Plans that reverse-engineer the legacy architecture into the [Stack]/[Layer]/[Sprint_ID] taxonomy.
    3. Physical Relocation: Invoke topology-scaffolder to physically nest the legacy artifacts into sprint_00_legacy_import/ or appropriate new folders without breaking functional dependencies.

Governance Audit

  • Compliance Rule: Every implementation_plan.md generated by the pipeline must follow this standard.
  • Language Guard: All project management artifacts MUST be in Technical English (except human-agent chat and explicit plan debate loops).

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.

Check your setup, free