Run a blind verification loop checking drafts against user requirements.
npx skills add https://github.com/buYoung/skills --skill iterative-self-review
Please help me install this Agent Skill. Skill: iterative-self-review Source: https://github.com/buYoung/skills/tree/main/skills/iterative-self-review Command: npx skills add https://github.com/buYoung/skills --skill iterative-self-review
Run a clean-context blind verification loop when the user explicitly asks for verification, review, re-check, cross-check, proof, or another second-pass quality gate. The main agent drafts the current response, a clean-context sub-agent verifies only the applicable user requirements plus that current response, and the main agent revises and re-verifies until every blocker/major issue is gone and only minor residuals remain. Applies to all response types: code changes, document edits, design proposals, summaries, plans, recommendations, explanations, and file-change reports. If the user explicitly narrows verification to a specific part, scope both the user-input slot and the response slot to only that requested part. Do not auto-trigger on ordinary conversation or routine task completion.
Trigger the iterative self-review to run a blind verification pass on the current draft and iterate until all blockers are resolved.
High-intent search queries and answers about installing and using this skill.
You trigger a blind verification loop by explicitly asking for a review or cross-check, which prompts a separate sub-agent to verify the draft and iterate until all blockers are resolved.
Blind self-review verification is a process where a clean-context sub-agent checks a main draft against user requirements without editing artifacts, needed when explicitly requesting proof or re-checks for designs, code, or documents.
Yes, you can explicitly narrow verification to a specific part, which scopes both the user-input slot and the response slot to only that requested section for targeted quality assurance.
Automated self-review works with all response types including code changes, document edits, design proposals, summaries, and plans, applying verification uniformly across any output format.
The verification sub-agent operates with read-only context to ensure clean blind review checks, meaning it only verifies the main draft and applicable requirements without making direct edits to artifacts.
You should not use an iterative self-review loop for ordinary conversation or routine task completion, as it only triggers when you explicitly request verification, re-checks, or second-pass quality gates.
KartikSharma4448Draft emails, schedule calendar events, and prepare meeting agendas.
EvoClawCoordinate iterative multi-agent discussions to converge on a resolved artifact.
conn-castleCompare implementation against plan artifacts and report gaps to a markdown file.
mozilor-technologiesAnalyze feature code against design documents and coding standards.
