Agent skill
findings
Write reviewer findings to a <slug>.findings.md file for any scoped review target.
Install this agent skill to your Project
npx add-skill https://github.com/majiayu000/claude-skill-registry/tree/main/skills/other/other/findings
SKILL.md
Findings
Write reviewer findings for any scoped target using a two-file message bus. This command applies to a file, ADR, doc set, PR context, diff, uncommitted workspace, or another named review scope.
Protocol
<slug>.findings.md— owned by the reviewer; primary output of this command; deleted on acceptance<slug>.response.md— owned by the author; deleted on acceptance
Inputs
- Review target or scope
- Slug for the exchange files
- Optional existing
<slug>.response.mdwhen iterating
Reviewer workflow
- Read the target under review. If
<slug>.response.mdalready exists, read it before revising findings. - Write findings to
<slug>.findings.md:# Review: <target name> ## Findings ### Critical - [path:line or section] Issue. Suggested fix. ### Major / Minor - ... ## Decision: Request Changes | Approve - Tell the author: "findings written to
<slug>.findings.md."
Do not stop at chat-only review output. The findings file is the contract.
Author workflow
- Read
<slug>.findings.md. - For each finding: fix, defer (with reason), or reject (with reason).
- Write response to
<slug>.response.md:# Response: <target name> ## Responses - [Finding ref] Fixed | Deferred: <reason> | Rejected: <reason> ## Target status: Revised | Accepted as-is - Tell the reviewer: "response written to
<slug>.response.md."
Closing the loop
Reviewer reads <slug>.response.md. If satisfied: both files deleted, target accepted. If not: iterate.
Notes
- Use a stable slug for the review scope:
pr-524,workspace-uncommitted,movement-system,2026-03-01-network-flow-logistics-system. - Use
<issue-number>-<slug>naming when the review is tied to a GitHub issue. - This protocol is relay-agnostic; future tooling can automate the file exchange.
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
agent-ops-spec
Manage specification documents in .agent/specs/. Use when user provides requirements, acceptance criteria, or feature descriptions that need to be tracked and validated against implementation.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-testing
Test strategy, execution, and coverage analysis. Use when designing tests, running test suites, or analyzing test results beyond baseline checks.
agent-ops-state
Maintain .agent state files. Use at session start, after meaningful steps, and before concluding: read/update constitution/memory/focus/issues/baseline consistently.
Didn't find tool you were looking for?