dicklesworthstone/eidetic_engine_cli

active-learning-experiment-planner

Use when planning active-learning experiments from ee observation ledgers, learning uncertainty reports, evaluation records, causal/economy/context evidence, or ee.skill_evidence_bundle.v1 artifacts without moving experiment-planning judgment into the Rust ee…

Langue du texte source : anglais

causal-credit-review

Use when reviewing causal credit assignments from ee causal ledgers to determine whether measured associations warrant promote/demote/reroute recommendations without moving causal judgment into the Rust CLI.

Langue du texte source : anglais

counterfactual-failure-analysis

Use when analyzing whether different ee lab evidence, context packs, or memory interventions might have changed a coding-agent failure outcome without moving counterfactual judgment into the Rust CLI.

Langue du texte source : anglais

preflight-risk-review

Use when reviewing pre-task risk from ee evidence matches, preflight JSON, tripwire JSON, dependency audits, project rules, destructive-command warnings, migrations, production deploys, or no-evidence/degraded preflight output before an agent acts.

Langue du texte source : anglais

procedure-distillation

Use when distilling recorder runs, curation events, procedure records, verification fixtures, or procedure exports into evidence-bound reusable procedures or render-only skill capsules without moving procedure authoring judgment into the Rust ee CLI.

Langue du texte source : anglais

rehearsal-promotion-review

Use when reviewing rehearsal dry-run artifacts and producing conservative promotion checklists; requires real ee rehearse output or explicit unavailable degradation.

Langue du texte source : anglais

session-review-memory-distillation

Use when reviewing CASS or ee session evidence to distill observed facts, candidate memories, procedural rules, anti-patterns, and curation candidate files without moving session-review judgment into the Rust ee CLI.

Langue du texte source : anglais

situation-framing

Frame coding-agent tasks and choose evidence-backed ee command plans without moving judgment into the Rust CLI. Use when an agent needs task classification, required evidence, command sequence selection, degraded-mode handling, or a concise handoff before…

Langue du texte source : anglais

claim-certificate-review

Use when reviewing ee claim or certificate verification manifests, deciding whether a claim is persuasive, stale, overbroad, expired, assumption-bound, or missing evidence without putting qualitative judgment into the Rust CLI.

Langue du texte source : anglais

ee-skill-standards

Use when creating, reviewing, or updating project-local ee skills that consume mechanical ee CLI JSON and apply agent judgment outside the Rust binary.

Langue du texte source : anglais