implement-universal
implement-universal is a Multi-stage workflow orchestration skill for AI agents, published by Arindam200 in the awesome-ai-apps repository on GitHub. Skillspace rates implement-universal C (74/100) and it passed the safety scan; a judge model has also reviewed it.
Harness-agnostic version of `/implement`. Drives a single workshop ticket through the SWE→Tester loop in ONE conversation, with the role prompts bundled as `agents/software-engineer.md` and `agents/tester.md` instead of being launched as subagents. Resolves the ticket from `implement_yourself/tasks/`, creates an `implementing/from-scratch` branch (a fixed default — not derived from the ticket; subsequent tickets stack on top), adopts the software-engineer role to implement, then switches to the tester role to verify (logic tickets only). Loops on FAIL up to 3 times, moves the file to `tasks/done/`, then commits directly with `git commit -m`. Stops after one ticket. Trigger when the user types `/implement-universal`, asks to "implement task NNN without subagents", or is running in a harness (Cursor, Windsurf, plain Claude API client, etc.) that doesn't support Claude Code's `Task` tool.
- Grade
- C
- Quality
- 74 / 100
- Safety
- Passed
- GitHub stars
- 13,166
Placed #2 of 6 in the judged category final for Multi-stage workflow orchestration.
Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: a model that read it found it written only for the repository it lives in. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided
Our two independent classifiers differ on this skill's category, so treat the placement as provisional.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 100 / 100
- Maturity
- Structured: ships references or scripts
- Security scan
- No issues found
- License
- MIT
- Adoption
- Adopted by 2 other repositories, in 1 collections
- Scope
- Repo-internal: written for the repository it lives in. Drives tickets from this repo's implement_yourself workshop layout
Judge review
Placed #2 of 6 in the judged category final for Multi-stage workflow orchestration.
- Trigger
85 85 - Instructions
88 88 - Specificity
92 92 - Safety
85 85 - Disclosure
85 85 - Maintenance
80 80
Explicit about the bias risk of sharing context between its own two phases and names a banned eval target, though scoped tightly to one workshop's ticket system.
Not checked yet
- No blind task eval yet
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.