steel-quench
SolidAll-angle verification meta-skill for near-complete artifacts. Turns vague design anxiety into structured challenger waves using fh-commons:quench-challenger, then drives defense and convergence until root weaknesses, residual risks, and added complexity are explicit. Covers standard attack/defense rounds, optional Meta-Aware Adversary mode for AI-specific risks such as hallucination, context collapse, prompt injection, and tool lock-in, and Wave-P3 re-attack after an upstream gate declares PASS. Built-in outputs emphasize attack-plus-prescription pairs and can feed fh-meta:persona-innovator after convergence. Triggered by: "quench this", "devil's judgment", "all-angle review", "end-to-end verification", "steel quench", "deep pre-completion inspection", "did it really pass?".
Install
Quality Score: 81/100
Skill Content
Details
- Author
- chrono-meta
- Repository
- chrono-meta/forge-harness
- Created
- 2 months ago
- Last Updated
- today
- Language
- Shell
- License
- MIT
Integrates with
Similar Skills
Semantically similar based on skill content — not just same category
phantom-quench
Input-tracing grounding audit for artifacts such as test cases, analysis reports, and design docs. Extracts proper nouns, numbers, citations, version claims, and branching conditions, then back-traces each to declared local files by grep or to external sources by fetch-and-support checks. Marks missing anchors as Phantom Claims and cited-but-unsupporting anchors as Unsupported. A claim is grounded only by non-model evidence: a local hit or literal source span, never another model's agreement. Renamed from source-grounding-audit; old-name references still route here. Triggered by: "phantom detection", "phantom claim", "source back-trace", "where did this come from", "verify source", "does the source support this claim", "grounding audit", "source grounding audit", "citation support check".
bs-check
Use before telling a client or stakeholder "this is fixed", before deploying changes to a production site or service, before activating or modifying a live automation/workflow, before claiming an integration works end-to-end, before quoting pricing or API behavior in a comparison, or before running a destructive infrastructure command. Also use when the user says "confidence check", "how confident are you", "validate this", "pressure-test this", "/bs-check", or whenever a confident-sounding claim has not been directly validated by a query, observation, comparison, or quotable source. ALSO covers design-time reasoning audits via subcommands - "bs-check premise" (are we solving the right problem? premise acceptance - Socratic + Steelman), "bs-check approach" (did we commit too fast? - Burden of Proof, Cold Start, Alternatives, Pre-mortem), "bs-check fresh" (all 9 patterns, fresh-context sub-agent). Trigger phrases for those - challenge this, push back, devil's advocate, poke holes, steelman this, are we solving
devilsadvocate
Stress-test mode — attack the user's idea to find what's wrong with it before reality does, so it comes back stronger. Invoke when the user wants their plan, decision, or assumption rigorously challenged rather than built.