add 5 step prompt loop for implementation#57
Merged
Merged
Conversation
* Introduce prompts for implementation loop: readiness-check, implementation, self-review, learnings, and human-in-the-loop * Enhance README with new prompt structure and descriptions * Update AGENTS.md to reflect new prompt paths
- Update prompts/ label and Canonical Authority list in README to reflect skills/ and loop/ subfolders - Update AGENTS.md Source Of Truth precedence entry to distinguish prompts/skills/ wrappers from prompts/loop/ steps - Update source_prompt paths in 8 skill SKILL.md files from prompts/ to prompts/skills/ - Make src/tests directory references flexible in readiness-check prompt - Make arc42 skill invocation conditional on skill availability - Defer architecture layer constraint to project AGENTS.md/ADRs in both implementation and self-review prompts; keep Clean Architecture as example Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
…etplace manifests Updated description and added implementation-loop and workflow-prompts keywords to both plugin.json and marketplace.json for better discoverability. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
feat(prompts): add implementation loop prompts
Contributor
There was a problem hiding this comment.
Pull request overview
This PR reorganizes prompt wrappers into a dedicated prompts/skills/ folder and introduces a numbered 5-step “implementation loop” under prompts/loop/, updating skill metadata and repository docs to match the new layout.
Changes:
- Updated
skills/*/SKILL.mdfrontmattermetadata.source_promptpaths to point atprompts/skills/*.prompt.md. - Added new wrapper prompts under
prompts/skills/and added the 5-step implementation loop prompts underprompts/loop/. - Updated
README.md,AGENTS.md, and Claude plugin metadata to reflect the new structure and capabilities.
Reviewed changes
Copilot reviewed 17 out of 27 changed files in this pull request and generated 2 comments.
Show a summary per file
| File | Description |
|---|---|
| skills/validate-usercontext-instructions/SKILL.md | Points source_prompt at the new prompts/skills/ wrapper path. |
| skills/validate-skill/SKILL.md | Points source_prompt at the new prompts/skills/ wrapper path. |
| skills/validate-project-instructions/SKILL.md | Points source_prompt at the new prompts/skills/ wrapper path. |
| skills/validate-agents-md/SKILL.md | Points source_prompt at the new prompts/skills/ wrapper path. |
| skills/create-usercontext-instructions/SKILL.md | Points source_prompt at the new prompts/skills/ wrapper path. |
| skills/create-skill/SKILL.md | Points source_prompt at the new prompts/skills/ wrapper path. |
| skills/create-project-instructions/SKILL.md | Points source_prompt at the new prompts/skills/ wrapper path. |
| skills/create-agents-md/SKILL.md | Points source_prompt at the new prompts/skills/ wrapper path. |
| README.md | Documents the new prompts/skills/ and prompts/loop/ structure and precedence notes. |
| prompts/skills/validate-usercontext-instructions.prompt.md | Adds a thin wrapper that routes to the canonical validation skill. |
| prompts/skills/validate-skill.prompt.md | Adds a thin wrapper that routes to the canonical validation skill. |
| prompts/skills/validate-project-instructions.prompt.md | Adds a thin wrapper that routes to the canonical validation skill. |
| prompts/skills/validate-agents-md.prompt.md | Adds a thin wrapper that routes to the canonical validation skill. |
| prompts/skills/create-usercontext-instructions.prompt.md | Adds a thin wrapper that routes to the canonical creation skill. |
| prompts/skills/create-skill.prompt.md | Adds a thin wrapper that routes to the canonical creation skill. |
| prompts/skills/create-project-instructions.prompt.md | Adds a thin wrapper that routes to the canonical creation skill. |
| prompts/skills/create-agents-md.prompt.md | Adds a thin wrapper that routes to the canonical creation skill. |
| prompts/skills/create-checkpoint.prompt.md | Adds a checkpoint wrapper prompt (currently minimal). |
| prompts/skills/restore-checkpoint.prompt.md | Adds a checkpoint wrapper prompt (currently minimal). |
| prompts/loop/01-readiness-check.prompt.md | Introduces the loop’s readiness assessment step prompt. |
| prompts/loop/02-implementation.prompt.md | Introduces the loop’s implementation step prompt. |
| prompts/loop/03-self-review.prompt.md | Introduces the loop’s self-review step prompt. |
| prompts/loop/04-learnings.prompt.md | Introduces the loop’s (optional) learnings capture prompt. |
| prompts/loop/05-human-in-the-loop.prompt.md | Introduces the loop’s final human approval / commit-readiness prompt. |
| AGENTS.md | Updates precedence and reference lists to include new prompt locations and loop prompts. |
| .claude-plugin/plugin.json | Updates manifest description/keywords to include the implementation loop prompts. |
| .claude-plugin/marketplace.json | Updates plugin entry metadata to include the implementation loop prompts. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
204
to
+208
| - Create prompts: | ||
| - [`prompts/create-agents-md.prompt.md`](prompts/create-agents-md.prompt.md) | ||
| - [`prompts/create-usercontext-instructions.prompt.md`](prompts/create-usercontext-instructions.prompt.md) | ||
| - [`prompts/create-project-instructions.prompt.md`](prompts/create-project-instructions.prompt.md) | ||
| - [`prompts/create-skill.prompt.md`](prompts/create-skill.prompt.md) | ||
| - [`prompts/skills/create-agents-md.prompt.md`](prompts/skills/create-agents-md.prompt.md) | ||
| - [`prompts/skills/create-usercontext-instructions.prompt.md`](prompts/skills/create-usercontext-instructions.prompt.md) | ||
| - [`prompts/skills/create-project-instructions.prompt.md`](prompts/skills/create-project-instructions.prompt.md) | ||
| - [`prompts/skills/create-skill.prompt.md`](prompts/skills/create-skill.prompt.md) |
Comment on lines
11
to
15
| "source": "github", | ||
| "repo": "MSiccDev/ai-context-kit" | ||
| }, | ||
| "description": "Context-aware AI collaboration skills for creating and validating user context, project AGENTS.md files, and skill artifacts across LLM providers.", | ||
| "description": "Context-aware AI collaboration skills and implementation loop prompts for creating and validating user context, project AGENTS.md files, and skill artifacts across LLM providers.", | ||
| "version": "1.4.2", |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
No description provided.