reality-check
GitHub将声称状态与仓库可观测证据对比，识别具体差距。用于审计完成度、检查范围升级及验证假设变更，确保基于事实而非仅代码存在性进行判断。
Trigger Scenarios
Install
npx skills add boshu2/agentops --skill reality-check -g -y
SKILL.md
Frontmatter
{
"name": "reality-check",
"consumes": [
"claim",
"repository-evidence"
],
"metadata": {
"tier": "judgment",
"effects": [
"write_advisory_gap_report"
],
"disposition": "keep_strategy",
"capabilities": [
"compare_claim_to_evidence"
],
"dependencies": [],
"canonical_status": "canonical"
},
"produces": [
"reality-check-report.v1"
],
"practices": [
"design-by-contract",
"evidence-based-engineering"
],
"context_rel": [
{
"kind": "supplier-to",
"with": "plan"
}
],
"description": "Compare a claimed state with observable repository evidence and report concrete gaps. Requires a claim or expected state to test. Triggers: \"reality check\", \"is this claim actually done\", \"compare claim to repo\".",
"hexagonal_role": "domain",
"user-invocable": true,
"output_contract": "reality-check-report.v1 JSON validated by skills\/reality-check\/scripts\/validate-output.sh",
"skill_api_version": 1
}
Reality Check
Compare an explicit claim with observable evidence. Cite every confirmed or missing behavior with a file, command result, or artifact. Separate:
- confirmed behavior;
- concrete gap;
- incomplete evidence;
- changed assumptions.
Vision-coverage audit
When the claim is a completion or status claim, audit it against the stated goals, not against what happens to exist. Enumerate every goal in the vision, plan, or intent source and give each a disposition: confirmed with evidence, concrete gap, or unverifiable. The audit is complete only when every stated goal carries a disposition; full coverage of the built surface alone proves nothing about completion. The named failure mode is built-world bias: auditing only the code that exists, so goals nobody started never surface as gaps.
Frozen question variants
When the same check runs across multiple passes or sessions, freeze the exact question wording before the first pass and ask it identically in every pass; record the frozen wording in the report. A pass that answers a reworded question starts a new baseline — comparing it against earlier passes is the drifting-rubric failure mode, and its answer does not count as a repeated measurement.
Ambition-escalation checkpoint
When invoked during planning, compare the currently planned scope against the originally stated goal. Planned work that cannot be traced to a stated goal is reported as an escalation gap, exactly like a missing behavior. Reality Check reports the escalation; the caller decides whether the ambition or the stated goal changes.
Output
- Artifact directory:
.agents/scratch/reality-check/<run-id>/. - Filename:
reality-check-report.json. - Format:
reality-check-report.v1JSON — the checked claim, one finding per confirmed behavior, concrete gap, incomplete-evidence item, or changed assumption (each with cited evidence), and, for a completion or status claim, the goal-by-goal coverage disposition. It carries noverdict,readiness, orPASSfield; the validator rejects one. - Validation command:
skills/reality-check/scripts/validate-output.sh <reality-check-report.json>.
If the claim cannot be tested against any observable evidence, report it as incomplete-evidence with the missing artifact named — never resolve an untestable claim as confirmed.
Boundary
Return the report to the caller. Plan may use concrete gaps to refine the
existing bead or caller intent. Reality Check reports observations; it does not
mint a verdict or PASS of any version, create work, schedule, claim,
implement, validate, retry, or deliver.
Version History
-
7b07a7d
Current 2026-08-19 22:00
W8版本修订：明确触发路由分离，规定必须提供待测声明才能执行；规范化效果词汇前缀；标记shared为非路由技能；修复输出契约以确保无裁决字段。
- 3f402e5 2026-07-24 22:07
