원클릭으로
ecp-propose
Create a formal EOU Change Proposal from a diagnosed failure or refactor option.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Create a formal EOU Change Proposal from a diagnosed failure or refactor option.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Audit a generated candidate EOU set for boundary quality, minimality, overlap, authority, operational value, and governance risk.
Audit value_invocations in run traces for EOUs with classification.judgment_authorized:true. Verifies invocations against the captured_workflow's declared priority (no F15), checks for drift over multiple runs (no F16), detects hallucinated value ids (no F17), catches silent decisions on contested cases (F14), and runs counterfactual-swap audit as the V1 anti-theater defense.
Audit EOU specs for Foundry V2 faceted classification, authority limits, schemas, validation, failure modes, trace, blast radius, and responsibility ownership.
Synthesize a Stage 0 captured_workflow (D2.4 step 1–5 outputs + per-app constitutional domain_values layer) from a user goal, structured 5-role reference set, and constraints. For users entering an unfamiliar craft domain who cannot articulate a workflow unaided, and for any user who needs the constitutional layer made explicit before downstream EOU generation begins.
Generate a minimal, ranked candidate EOU set from a messy workflow using Foundry V2 constraints. Candidates are proposal-only and cannot be activated.
Audit a generated candidate EOU set for boundary quality, minimality, overlap, authority, operational value, and governance risk before any candidate advances to specification. <example> Context: A generation run has just produced a candidate set; the owner wants to know which candidates survive audit before promotion. user: "$audit-candidate-eou-set foundry/self-evolution/candidate-sets/cs-generate-eou-candidates-20260520-1430.yml" assistant: "I'll run the eight tests (boundary, non-overlap, minimality, authority, operational value, counter-generation, set composition, high-stakes) and write the audit report under foundry/audits/candidate-set-audits/." </example> <example> Context: User wants to audit a candidate set that contains a generating EOU without a corresponding audit path. user: "$audit-candidate-eou-set ./my-candidates.yml" assistant: "I'll audit. Heads-up that if any candidate has authority_level approve/publish or proposes weakening validators, I'll escalate to FAIL regardless of other test outc
| name | ecp-propose |
| description | Create a formal EOU Change Proposal from a diagnosed failure or refactor option. |
Create a formal EOU Change Proposal (ECP) from $target.
schemas/ecp.schema.yml — field types and constraintsfoundry/constitution.yml — invariants the ECP must not violateHalt and report before drafting the ECP if:
$target does not identify a concrete failure or refactor option — a goal that names no concrete failure class, incident id, or refactor-option id is not accepted.target_eou cannot be determined from $target.foundry/constitution.yml — use the constitutional change process instead.$target to extract the diagnosed failure or refactor option.foundry/failure-taxonomy.yml) driving the change.approval.status is proposed — never set it higher.foundry/self-evolution/ecp/proposed/{target_eou}-ecp-{YYYYMMDD}.yml.foundry/runs/{eou_id}/{run_id}.yml.Field names match schemas/ecp.schema.yml. Do not use the old names (eou_id, observed_problem, simulation_status, required_tests).
id: # ecp-{target_eou}-{YYYYMMDD}
target_eou: # ID of the EOU being changed
target_version_from: # current version of the EOU (e.g. "0.2.0")
target_version_to: # intended version after this change (e.g. "0.3.0")
failure_class: # F1-F12 taxonomy code(s) — supplementary, not schema-required
problem: # Concrete failure symptom, not a vague label
proposed_change: # One specific structural change (scope, steps, inputs, authority, blast_radius, validators, stop_conditions, approval_requirements, or responsibility boundaries)
expected_benefit: # Observable outcome if the change is applied
risks: # What can go wrong; who is affected
tests_required: # List of regression case IDs or new test fixtures to add
simulation: # not_run | run_pass | run_fail
approval:
status: # must be "proposed" — never "approved" from this EOU
approver: # left blank until human owner approves
rollback_considerations: # How to revert if the change degrades outcomes (supplementary)
All output files written by this skill:
| Artifact | Path |
|---|---|
| ECP proposal | foundry/self-evolution/ecp/proposed/{target_eou}-ecp-{YYYYMMDD}.yml |
| Run trace | foundry/runs/{eou_id}/{run_id}.yml |
approval.status to anything other than proposed.foundry/constitution.yml via ordinary ECP — constitutional changes require a separate process with explicit human review.risk_level: high or critical) must include a non-empty rollback_considerations field.rollback_considerations is supplementary in the schema but mandatory in this skill for high-risk changes — these two statements are not contradictory: the schema does not enforce presence, but this skill does.