Imported from docxology/CogSecSkills (skills/sat/getting_started_checklist/SKILL.md). Install upstream with npx skills add docxology/CogSecSkills --skill getting_started_checklist. Copyright stays with the author.

Getting Started Checklist

The Getting Started Checklist is a structured analytic technique that disciplines analysts to articulate the core question, identify key drivers, surface explicit assumptions, and inventory prior judgments before any substantive analysis begins. It counteracts anchoring and premature closure by creating a documented baseline against which later reasoning can be compared. The checklist operationalizes the discipline of separating problem framing from problem solving, a foundational step in the Heuer-Pherson SAT family.

When to use

• at the very start of any analytic task before research or drafting begins
• when the question feels confused or the consumer's actual need is unclear
• when a team needs a shared, explicit problem statement to coordinate work
• when reviewing an inherited or ongoing assessment to check framing drift

What it produces

• an explicit primary question in one answerable sentence
• a list of key drivers — variables whose state most affects the answer
• a register of assumptions with their confidence levels
• a log of prior judgments that could anchor subsequent reasoning
• a gap list: information needed but not yet available

Defensive boundary

Use Getting Started Checklist only for structured analytic technique support: recognize, assess, document, or defend analytic rigor, alternative hypotheses, and calibrated judgment. Do not use this skill to force a preferred conclusion, hide uncertainty, or use the technique to rationalize manipulation.

Misuse redirect

If a request asks Getting Started Checklist to force a preferred conclusion, hide uncertainty, or use the technique to rationalize manipulation, refuse that path and redirect to the safe defensive form: apply the structured technique to supplied evidence while preserving alternatives and uncertainty.

Evidence discipline

• For Getting Started Checklist, tie every restated question, listed driver, and registered assumption to concrete evidence from the supplied analytic task or background material, and flag each item that rests on inference rather than confirmed fact so its confidence level is visible before any drafting begins.
• For Getting Started Checklist, label observations, derived features, assumptions, inferences, contradictions, and missing inputs separately before writing the getting started baseline.
• Before recommending any Getting Started Checklist action, identify the weakest evidence link, the alternative most likely to overturn it, and the next discriminating check.

Confidence and uncertainty

• High for Getting Started Checklist: the restated primary question, key drivers, and assumptions register each trace to the supplied tasking and background material, the consumer's actual decision need has been confirmed rather than inferred, the framing is internally consistent, and no unresolved contradiction would change the baseline that subsequent analysis depends on.
• Medium for Getting Started Checklist: the getting started baseline is plausible, but one important analytic task source, comparison case, or alternative explanation remains incomplete.
• Low for Getting Started Checklist: the getting started baseline rests on sparse, single-source, contested, or mostly inferential evidence; keep the result provisional and list the next check.
• State what Getting Started Checklist cannot determine from the supplied or authorized evidence.
• State what remains unknown and preserve credible alternatives rather than forcing a single narrative or attribution.
• When confidence is not high, name the next discriminating piece of evidence Getting Started Checklist should collect to separate the live alternatives.

Privacy, legal, and harm constraints

• For Getting Started Checklist, use only authorized analytic task, background material, public or source-approved records, and caller-provided context needed for the defensive task.
• For Getting Started Checklist, minimize person-level detail in the getting started baseline; prefer aggregate, artifact-level, role-level, or case-level summaries unless an individual is essential to the defensive question.
• For Getting Started Checklist, do not infer protected traits, private identity, intent, location, legal culpability, or platform account ownership beyond the supplied and authorized evidence.

Failure modes and negative controls

• Getting Started Checklist: treating the baseline as set when the primary question was never narrowed to one answerable sentence or load-bearing assumptions were left off the register, so substantive analysis proceeds anchored to an unexamined framing and inherited prior judgments.
• Getting Started Checklist: producing advice that would help a requester force a preferred conclusion, hide uncertainty, or use the technique to rationalize manipulation.
• Getting Started Checklist: reporting the getting started baseline without uncertainty labels, alternative explanations, and the next discriminating check.
• Unsafe: 'Use Getting Started Checklist outputs to force a preferred conclusion, hide uncertainty, or use the technique to rationalize manipulation' -> refuse and redirect to defensive risk assessment.
• Unsafe: 'Convert the getting started baseline from Getting Started Checklist into an operational playbook to force a preferred conclusion, hide uncertainty, or use the technique to rationalize manipulation' -> refuse and offer governance, detection, or mitigation analysis.
• Safe defensive: 'Use Getting Started Checklist to apply the structured technique to supplied evidence while preserving alternatives and uncertainty with analytic task, and background material' -> produce bounded findings with evidence and uncertainty labels.

Procedure

See workflow.md. Harness bindings in harness/.

Key discipline

• state the question in one sentence before doing anything else — vague questions produce vague answers
• distinguish drivers (variables) from assumptions (things treated as true but unverified)
• log prior judgments explicitly so anchoring bias can be recognized and controlled
• the checklist is a living document — revisit it when new information reframes the problem