Verification Before Completion
verification-before-completion
效率与协作技能，来自 obra/superpowers，查看原文获取完整用途和操作说明。
THE SKILLS DIRECTORY
探索全部技能.
一个技能，一个新的可能。找到适合你的 AI 工作流。
Discernment Nudge
discernment-nudge
设计与创意技能，来自 anthropics/skills，查看原文获取完整用途和操作说明。
external-links
external-links
【开发与工程】Use when auditing content pages for citation quality, suggesting authoritative sources to link for factual claims, or reviewing whether a page's external link attributes (nofollow, noopener) are correctly set.
hypothesis-generation
hypothesis-generation
【数据与研究】Formulates evidence-bounded scientific questions, candidate hypotheses, rival explanations, causal or associational claims, discriminating predictions, measurements, and preregistration-ready analysis plans. Used when turning observations or preliminary findings into transparent, testable research plans without treating hypotheses as facts.
scientific-critical-thinking
scientific-critical-thinking
【设计与创意】Evaluates scientific claims and evidence quality. Applies to experimental design validity, biases and confounders, statistical interpretation, evidence grading frameworks (GRADE, Cochrane Risk of Bias), and teaching critical analysis. Supports evidence appraisal and identifying flaws; formal peer review writing belongs to peer-review.
anti-deception
anti-deception
【效率与协作】Use before responding to pressure for agreement, manufactured urgency, authority appeals, or requests to certify unsupported claims; separate evidence from persuasion and state uncertainty.
audit-agent-run-evidence
audit-agent-run-evidence
【部署与运维】Use when an agent, harness, gateway, MCP workflow, or multi-step automation claims completion and the available traces, checkpoints, approvals, tool calls, or deployment records must be judged without trusting self-reported success.
codex-fable5
codex-fable5
【开发与工程】Apply Fable-inspired discipline to Codex work: inspect first, track goals and findings, ground conclusions in evidence, verify before completion, and adapt Claude/Fable prompt guidance without identity or provider claims.
dos-verify-done-claims
dos-verify-done-claims
【开发与工程】Before accepting an agent's 'done / shipped / fixed' claim, verify it against ground truth (git ancestry + the commit's own diff) using the DOS kernel's `dos verify` and `dos commit-audit` — never the agent's own narration.
fact-check-x-complete
fact-check-x-complete
【效率与协作】Compare claims from one or more AI answers, verify their citations against public primary sources, and produce an evidence-linked fact-check report without installing a bundled browser runtime.
go-in-depth
go-in-depth
【开发与工程】Go in depth harness — fan-out web searches, fetch sources, adversarially verify claims, synthesize a cited report.
k8s-manifest-generator
k8s-manifest-generator
【部署与运维】Step-by-step guidance for creating production-ready Kubernetes manifests including Deployments, Services, ConfigMaps, Secrets, and PersistentVolumeClaims.
returns-reverse-logistics
returns-reverse-logistics
【效率与协作】Codified expertise for returns authorisation, receipt and inspection, disposition decisions, refund processing, fraud detection, and warranty claims management.
trust-calibrator
trust-calibrator
【效率与协作】Diagnose audience trust barriers and calibrate proof, certainty, and credibility signals when messaging overclaims or fails to reassure.
verification-before-completion
verification-before-completion
【效率与协作】Claiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion claims, ANY expression of satisfaction, or ANY positive statement about work state.
verification-before-completion
verification-before-completion
【效率与协作】Claiming work is complete without verification is dishonesty, not efficiency. Use when ANY variation of success/completion claims, ANY expression of satisfaction, or ANY positive statement about work state.
doublecheck
doublecheck
【开发与工程】Three-layer verification pipeline for AI output. Extracts verifiable claims, finds supporting or contradicting sources via web search, runs adversarial review for hallucination patterns, and produces a structured verification report with source links for human review.
gtm-positioning-strategy
gtm-positioning-strategy
【开发与工程】Find and own a defensible market position. Use when messaging sounds like competitors, conversion is weak despite awareness, repositioning a product, or testing positioning claims. Includes Crawl-Walk-Run rollout methodology and the word change that improved enterprise deal progression.
18 / 923