agentleFS
MarcusJellinghausMarcusJellinghaus/mcp-workspace/.claude/skills/implementation_finalise/SKILL.md

implementation_finalise

Skill49 starsChanged 2 days agoMITView on GitHub

Complete remaining unchecked tasks in the task tracker

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

Show its rules and text

We split this skill into the rules it gives an agent

14 rules. About 0 are common, 9 are distinctive, and 5 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.

  • 5

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read pr_info/TASK_TRACKER.md and identify all unchecked tasks (- [ ]).

    line 14
  2. Very specific:

    If all tasks are already checked (- [x]), report that no finalisation is needed and exit.

    line 16
  3. Distinctive:

    If the task contains "commit message" (case-insensitive):

    line 24
  4. Very specific:

    if the tasks before are already done, ignore this task by marking it as done [x]

    line 26
  5. Very specific:

    Check pr_info/steps/ for related step files that provide context

    line 30
  6. Distinctive:

    If step files don't exist, analyse based on task name and codebase

    line 31
  7. Distinctive:

    Verify if the task is already complete

    line 32
  8. Distinctive:

    If not complete: implement the required work

    line 33
  9. Very specific:

    If complete or successfully implemented: mark as [x]

    line 34
  10. Distinctive:

    If unable to complete: DO NOT mark as done - explain the issue

    line 35
  11. Distinctive:

    If any code changes were made during this process:

    line 39
  12. Distinctive:

    Run pylint checks using the MCP server (fix all errors)

    line 41
  13. Distinctive:

    Run pytest checks using the MCP server (fix all failures)

    line 42
  14. Distinctive:

    Run mypy checks using the MCP server (fix all type errors)

    line 43

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Implementation Finalise

Complete any remaining unchecked tasks in the task tracker before transitioning to code review.

Process

1. Read Task Tracker

Read pr_info/TASK_TRACKER.md and identify all unchecked tasks (- [ ]).

If all tasks are already checked (- [x]), report that no finalisation is needed and exit.

2. Process Each Unchecked Task

For each unchecked task:

Commit Message Tasks

If the task contains "commit message" (case-insensitive):

  • if the tasks before are already done, ignore this task by marking it as done [x]

Other Tasks

  • Check pr_info/steps/ for related step files that provide context
  • If step files don't exist, analyse based on task name and codebase
  • Verify if the task is already complete
  • If not complete: implement the required work
  • If complete or successfully implemented: mark as [x]
  • If unable to complete: DO NOT mark as done - explain the issue

3. Quality Checks (If Code Changed)

If any code changes were made during this process:

  • Run pylint checks using the MCP server (fix all errors)
  • Run pytest checks using the MCP server (fix all failures)
  • Run mypy checks using the MCP server (fix all type errors)

Output

Report:

  1. Which tasks were processed
  2. Which tasks were marked complete
  3. Any issues encountered
  4. Summarize the changes in a commit message and report it

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.