standards
GitHub根据用户提供的代码变更、语言和风险，加载相关标准并报告具体发现。支持针对Go等语言的编码规范检查及批量重构的突变安全审查，不执行编辑或提交操作。
Trigger Scenarios
Install
npx skills add boshu2/agentops --skill standards -g -y
SKILL.md
Frontmatter
{
"name": "standards",
"consumes": [],
"metadata": {
"tier": "knowledge",
"effects": [],
"disposition": "keep_specialist",
"capabilities": [
"standards"
],
"dependencies": [],
"canonical_status": "canonical"
},
"produces": [
"stdout"
],
"practices": [
"pragmatic-programmer",
"clean-code"
],
"context_rel": [],
"description": "Load only the standards relevant to a caller-supplied change, then report concrete findings. Triggers: \"check standards\", \"which standards apply\".",
"hexagonal_role": "supporting",
"output_contract": "cited standards and factual findings",
"skill_api_version": 1
}
Standards — focused engineering guidance
Load the smallest set of standards justified by the caller's files, language, and risks. Do not preload the entire reference corpus.
Procedure
- Record the supplied paths, language, change type, and risk cues.
- Load
common-standards.mdplus only the matching language or checklist references. - Compare the supplied artifact to those sources.
- Return cited findings with path and line when possible, plus checked and not-checked scope.
- Stop.
This skill provides context and findings. It does not edit, validate, retry, approve, commit, release, deliver, or decide continuation.
Load-bearing conventions for produced code (MEASURED)
When the caller is about to WRITE code (not only review it), surface the matching language rules INLINE in the working context — a behind-the-link reference does not change behavior; an inline imperative does. The Go core:
- Wrap every propagated error with context:
fmt.Errorf("doing X: %w", err)— never return a bare inner error. - Multi-case functions get TABLE-DRIVEN tests (
[]structcases +t.Runper case), asserting exact expected values including the error cases.
For other languages, pull the matching reference below and inline its top rules the same way.
Measured 2026-08-04, probe
standards-go-conventions(gpt-5.6-luna, N=2, directional): control produced the%w-wrapped + table-driven shape in 1/2 runs; with these rules inline, 2/2. Inline-imperative beats reference-link — the graphify probe measured a linked doc instruction obeyed 0/2. Ledger:evals/skill-probes/LEDGER.md.
Mutation-safety standards
When the supplied change rewrites existing files in bulk — formatters, codemods, migration scripts, generators pointed at hand-written sources — check it against three standards and report each as a finding when absent:
- Single audited mutation chokepoint. All rewrites flow through one named command or script whose inputs, outputs, and dry-run mode can be inspected. Edits scattered across ad-hoc one-liners and manual touch-ups are the diffuse mutation failure mode: no single point can be audited, re-run, or blamed. Finding: name every mutation path outside the chokepoint.
- Hash-witnessed backups before rewrite. Before the chokepoint runs, the originals are preserved with content hashes recorded (a committed baseline counts), so "the rewrite changed only what it claims" is checkable byte-for-byte, not asserted. Finding: a bulk rewrite with no verifiable before-state.
- Self-administered ambition gate. The change states what it deliberately does not touch, and the diff respects it. A formatter run that also renames, a codemod that also refactors, is the scope-creep rewrite failure mode. Finding: any file class in the diff outside the change's own stated scope.
Stop condition for this check: all three standards have an explicit pass or finding; a bulk-rewrite review that reports style nits but skips these is incomplete.
References
Version History
-
7b07a7d
Current 2026-08-19 22:00
新增基于评估实验的测量数据块，强化Go语言错误包装和表格驱动测试的内联指令，以验证行为改进效果。
- 3f402e5 2026-07-24 22:08
