V0.8.1/agent smith - #33
Merged
Merged
Conversation
Restructured skill to emphasize concise communication and bounded-concurrency assessment for independent retrieval and validation work. Added skill-authoring reference with guidance on progressive disclosure, tool batching, script selection, candidate-versus-baseline evaluation, and real-task grounding for AI agents authoring skills.
Added validation rules to verify skill-authoring reference exists and contains required guidance on concise communication, parallelism assessment, progressive disclosure, and skill lifecycle. Expanded evals to test bounded-concurrency scenarios for independent endpoint retrieval.
Updated agent-smith skill summary to document new skill-authoring capabilities, concise-reporting guidelines, and bounded-concurrency assessment for independent operations. Added guidance on progressive disclosure pattern, faster skill workflows, and Agent Skills lifecycle for real-task grounding and baseline evaluation.
The commit workflow now requires a visible full-context audit when a multi-file change initially collapses into one category, so the plan stays explicit and the quality gate cannot be skipped by yolo or auto.
The template validator now checks for the new quality gate language in the skill, its evals, and the repo README so the documented contract remains enforced.
Greptile SummaryThe PR expands Agent Smith鈥檚 skill-authoring workflow and adds a visible quality gate for multi-file commit plans that initially collapse into one category.
Confidence Score: 5/5The PR appears safe to merge. No blocking failure remains. Important Files Changed
Reviews (2): Last reviewed commit: "馃挰 clarify auto-approval wording in read..." | Re-trigger Greptile |
The description now clarifies that yolo and auto are auto-approval modifiers only within an explicit commit request, never as standalone triggers for unrelated work. Added two new eval cases to enforce this contract: one verifies yolo in a non-commit context does not trigger the workflow, and another checks that auto in a formatter task does not cause unwanted commits. This tightens the triggering behavior and prevents accidental misuse.
Updated the auto-approval bullet point to explicitly state that yolo and auto should be used within a commit request, not as standalone modifiers. This clarification helps users understand the correct usage pattern and prevents confusion about when these keywords apply.
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.
This pull request updates the documentation for the
agent-smithandgit-visual-commitsskills to clarify and expand their quality gates, skill authoring, and workflow requirements. The most important changes are summarized below.Skill Workflow and Quality Gate Updates:
git-visual-commitsto require a visible full-context quality gate for multi-file plans that initially collapse to one category, while single-file changes retain the fast path.Skill Authoring and Agent-Smith Enhancements:
agent-smithdescription to explicitly include skill authoring, with new requirements for real execution, bounded-concurrency assessment, and reusable C#/.NET scripts and validators. Also references Agent Skills guidance for progressive disclosure, candidate evaluation, and human review.These changes improve documentation clarity and enforce stricter, more transparent quality standards for skill workflows and authoring.