MyGO/mygo
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

skill: refine repo-review skill instructions for clarity and calibration

Browse Source
This commit is contained in:
Sunday
2026-07-14 13:52:52 +08:00
parent 5674fa2eb5
commit a62a5bc0e2
3 changed files with 41 additions and 49 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.agents/skills/mygo-api-repo-review/SKILL.md
+12 -25
View File
@@ -5,7 +5,7 @@ description: Review the MyGO backend repository for material, evidence-backed ar
# MyGO API Repository Review
Perform a read-only, evidence-first review of the MyGO backend. Find real defects and systemic risks without manufacturing findings from stylistic preferences, unsupported hypotheticals, or intentional design choices.
Perform a read-only, evidence-first review of the MyGO backend. Find material defects and systemic risks without turning unfinished product scope, stylistic preferences, or unsupported hypotheticals into findings.
## Resolve the review scope
@@ -32,29 +32,20 @@ Keep the review read-only unless the user separately asks for fixes.
3. Do not fetch, pull, commit, stage, or discard changes.
4. Capture Git status again before reporting. If the workspace changed, identify the change and do not erase it.
## Establish context
## Review the implementation
Read `AGENTS.md`, `docs/roadmap.md`, `docs/architecture.md`, `docs/decisions.md`, and `docs/development.md` before judging the implementation. Treat documented decisions as intent, not as proof that their implementation is correct.
Map the reviewed packages, dependency direction, public entry points, state owners, external resources, and important lifecycle operations. Use `rg` and targeted file reads; do not read `go.sum` in full.
Apply production-grade correctness, security, resilience, and architecture standards to behavior and components that already exist, including implemented paths within WIP features. Do not interpret that standard as requiring every capability of the finished product to exist now.
## Review objective
1. Map the reviewed packages, dependency direction, entry points, state owners, external resources, and lifecycle operations. Use `rg` and targeted reads; do not read `go.sum` in full.
2. Reconstruct behavior, boundaries, invariants, state transitions, and trust assumptions from code, tests, configuration, and documentation.
3. Trace important control, data, ownership, resource, concurrency, and failure flows without starting from a predetermined bug list.
4. Use the lenses below for minimum coverage, then challenge every candidate before reporting it.
Find material, evidence-backed flaws in the repository's architecture, design, and implementation. Prioritize problems that can meaningfully harm correctness, security, resilience, data integrity, scalability, extensibility, decoupling, customizability, or maintainability. Favor systemic causes and cross-component interactions over local code smells.
Treat the lenses as perspectives, not an exhaustive checklist, taxonomy, or finding quota:
Do not begin from a predetermined list of expected bugs. Reconstruct intended behavior, boundaries, invariants, state transitions, and trust assumptions from code, tests, configuration, architecture documentation, technical decisions, and the roadmap.
## Analyze in phases
1. Build a working system model before producing findings.
2. Perform an open-ended pass by tracing important control, data, state, ownership, resource, and failure flows across component boundaries.
3. Perform a coverage pass using the review lenses below.
4. Challenge each candidate by seeking evidence that the behavior is intentional, unreachable, contained, or already protected.
5. Classify and report findings only after discovery and falsification.
Treat these lenses as minimum coverage, not as an exhaustive checklist, required taxonomy, or finding quota:
- **Architecture and evolution:** Evaluate whether responsibilities, dependencies, boundaries, data flows, or resource use create material obstacles to supported behavior, realistic scaling, roadmap work, extensibility, decoupling, customization, or maintenance.
- **Architecture and evolution:** Evaluate whether responsibilities, dependencies, boundaries, data flows, or resource use materially obstruct supported behavior, scaling, committed evolution, extensibility, decoupling, customization, or maintenance.
- **Security:** Evaluate whether trust, identity, authorization, ownership, confidentiality, integrity, availability, or exposure assumptions can be violated through a reachable execution path or component interaction.
- **Resilience:** Evaluate whether plausible partial failures, dependency failures, cancellation, concurrency, malformed inputs, or interrupted lifecycle operations can cause disproportionate impact, cascading failure, loss of service, or an unrecoverable state.
- **Data consistency:** Evaluate whether persistent state, external resources, ownership, and lifecycle transitions preserve required invariants across normal, concurrent, retried, interrupted, and partially failed execution paths.
@@ -67,7 +58,7 @@ Keep small `diff` and narrowly targeted reviews in the main agent by default. Fo
Give every reviewer the complete, non-exhaustive review objective and one primary emphasis such as architecture and performance, security, or resilience and data consistency. Make the emphasis a starting perspective rather than an exclusive boundary. Wait for all reviewers, then independently verify, deduplicate, and rank their candidates in the main agent.
## Verify deterministically
## Verify and report
Run the repository-wide checks below unless the user explicitly limits command execution or the environment prevents them:
@@ -76,10 +67,6 @@ Run the repository-wide checks below unless the user explicitly limits command e
- `go test ./...`
- a non-mutating `gofmt -l` check over tracked Go files
Record each check and its result. When a test fails, inspect the test first and follow the debugging principles in `AGENTS.md`. Do not convert a command failure into an architecture finding without validating its cause. Put checks that cannot run and their reasons under `Unverified areas`.
Record each check and its result. When a test fails, inspect the test first and follow the debugging principles in `AGENTS.md`. Do not convert a command failure into an architecture finding without validating its cause.
## Filter and report
After discovering candidate findings, read [review-calibration.md](references/review-calibration.md) and apply its evidence and falsification rules. Before writing the final response, read [report-template.md](references/report-template.md) and follow it exactly.
Report a candidate only when another developer can verify its location, causal path, and material impact. Place unresolved hypotheses under `Unverified areas` with the evidence needed to resolve them. If no candidate qualifies, state `Findings: None` rather than lowering the threshold.
After open-ended discovery, read [review-calibration.md](references/review-calibration.md) and apply its admission and falsification rules. Then read [report-template.md](references/report-template.md) and follow it exactly. If no candidate qualifies, state `Findings: None` rather than lowering the threshold.