Skip to content
Skills Library
Programming · Building & coding

morphsaver-execute

/morphsaver-execute

Execute one MorphSaver task file (a behaviour-preserving refactor to classes, a dispatch table or a dataclass). Use when handed a task from .morphsaver/runs/<run>/tasks/.

Repository
MorphSaver ↗
Licence
MIT
Last repository change
04.11.2026

Assessment and security

86/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content21 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
1
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 04.11.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Execute one MorphSaver task file (a behaviour-preserving refactor to classes, a dispatch table or a dataclass). Use when handed a task from .morphsaver/runs/<run>/tasks/.

Original author description

Execute one MorphSaver task file (a behaviour-preserving refactor to classes, a dispatch table or a dataclass). Use when handed a task from .morphsaver/runs/<run>/tasks/.

How it works

SKILL.md has no level-two headings · 13 lines, 159 words

SKILL.md preview
---
name: morphsaver-execute
description: Execute one MorphSaver task file (a behaviour-preserving refactor to classes, a dispatch table or a dataclass). Use when handed a task from .morphsaver/runs/<run>/tasks/.
---

# MorphSaver execute

One task file, one branch. The task names the sites, the target shape, the tests that must stay green and the acceptance criteria.

1. Run the listed tests first. If any is red before you change anything, stop and report.
2. Build the new shape beside the old code (base class and registry, or the table). Move one site at a time; run the tests after each.
3. One site per commit when the task lists more than 3 sites.
4. Remove the old arms only when every site goes through the new shape.
5. Keep public names. Add no feature. Do not widen the task.
6. Report the signed line delta (`git diff --shortstat`) in the commit message or pull request body, with the task id.
7. If the refactor turns out to grow the code or the tests do not cover a site, stop and report `reject` with the reason rather than forcing it.

Versions

The database has no other skills named morphsaver-execute.

Database snapshot: 13.11.2026 · package version a64a8ce7f17c (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100st-execute-task
    Use when the user asks to run, execute, or implement one specific task ID within a Strikethroo plan in this repository — triggers include execute task, run task, implement task, do task N. Do not use to execute a whole plan or blueprint, to generate tasks, or for generic…
  • 100arn-code-execute-task
    This skill should be used when the user says "execute task N", "run task N", "implement task N", "re-run task N", "retry task N", "run single task", or wants to execute a single specific task from the task list with optional review. This is for ONE task only — for executing the…
  • 100arn-code-execute-plan
    This skill should be used when the user says "execute plan", "run the plan", "execute project", "execute all tasks", "run all tasks", "run plan in parallel", "execute with review gates", or wants to execute a full structured project plan after tasks have been created via…
  • 100execute-plan
    Execute structured task plans with status tracking. Use when the user provides a plan file path in the format `plans/{current-date}-{task-name}-{version}.md` or explicitly asks you to execute a plan file.
  • 95execute-tdd-tasks
    Execute TDD task pairs autonomously with RED-GREEN-REFACTOR verification. Orchestrates wave-based execution with strategic parallelism, routing TDD tasks to tdd-executor agents and non-TDD tasks to standard task-executor. Use when user says "execute tdd tasks", "run tdd tasks",…
  • 92plan-execute
    Execute the user's plan that has been iteratively refined, step by step, with resume on failure. Use when the user runs /plan-execute or asks to execute an existing plan.

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.