agentleFS
Sign inStart free
dmzoneilldmzoneill/skills/plan-implementation/SKILL.md

plan-implementation

Skill2 starsChanged 19 days agoApache-2.0View on GitHub

Create a structured implementation plan for a feature or change. Analyzes goal, identifies files to modify, checks patterns, identifies risks. Use after researching, before coding.

8 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 0

    Distinctive

    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. Very specific:

    Before: start_work, create_mr, create_jira_issue

    line 64

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “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

Plan Implementation

Creates an actionable checklist-style plan from research and context.

Inputs

InputTypeDefaultPurpose
goalstringrequiredWhat to implement (e.g., "Add Redis caching to billing API")
projectstringautoProject to plan for
issue_keystring-Jira issue key if for specific ticket
constraintsstring-Requirements (e.g., "must be backwards compatible")

Workflow

1. Load Developer Persona

  • persona_load("developer") — for Jira tools

2. Detect Project

  • Infer from cwd; default automation-analytics-backend

3. Get Jira Issue (if issue_key)

  • jira_view_issue(issue_key=issue_key) — summary, acceptance criteria

4. Search Related Code

  • code_search(query=goal, project=project, limit=10)
  • Parse into candidate files with relevance scores

5. Load Project Knowledge

  • knowledge_query(project=project, section="patterns.coding")
  • knowledge_query(project=project, section="architecture.key_modules")
  • knowledge_query(project=project, section="gotchas")

6. Build Implementation Plan

Output markdown with:

  • Goal, Issue, Project, Constraints
  • Issue Context: summary, acceptance criteria (if Jira)
  • Files to Modify: checklist from code search
  • Implementation Steps: Setup, Research, Implement, Test, Document, Review, Submit
  • Patterns to Follow: from knowledge
  • Risks & Gotchas: from knowledge or defaults
  • Unknowns to Resolve: placeholder
  • Ready to Start: persona_load('developer'), skill_run('start_work', '{"issue_key": "..."}')

7. Log

  • memory_session_log("Created implementation plan", "Goal: {goal}, Issue: {issue_key}")

Key MCP Tools

  • persona_load — developer persona
  • jira_view_issue — issue context
  • code_search — related files
  • knowledge_query — patterns, architecture, gotchas
  • memory_session_log — session logging

Chaining

  • After: research_topic, gather_context
  • Before: start_work, create_mr, create_jira_issue

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