Characterize Runtime Behavior
When to Use This Skill
Use for explicit runtime scenarios with supplied environment and capability information. The specialist documents observations or manual plans; it does not execute applications.
Inputs
These are human-facing workflow selections, not additional service-request fields. Supply explicit selections; neither omitted inputs nor profile roots create authority.
| Input | Required contract |
|---|---|
| profile | Required validated profile and trusted workspace binding. |
| feature_ids | Required selected features and relevant contracts. |
| environment | Required recorded environment identity or explicit unavailable state. |
| fixtures | Required supplied fixture references or explicit absent/manual requirements. |
| preconditions | Required stated scenario preconditions; unknown facts remain unresolved. |
| actions | Required ordered manual actions or supplied action descriptions. |
| capability_mode | Required declared runtime capability and whether observations are supplied, manual, unavailable or blocked. |
| supplied_captures | Optional supplied captures and provenance; absence cannot become a passed result. |
Routing
Logical role: runtime-characterization-analyst.
The root owns preparation and launch; this skill never auto-launches a logical
role through frontmatter. The existing resolver selects the exact deployment,
model, effort and profile hash under the existing C1-C4 ceiling and execution
context. Do not choose a model, self-launch, create another scheduler or promote
an ordinary discovery action into an issue. The production-write count is zero.
Exact output boundary
These rows are maximum workflow caps, not instructions to create every kind. Only the prepared required outputs may be created or replaced.
| Artifact kind | Profile key | Constraint |
|---|---|---|
| runtime-characterization-scenario | characterization | Selected feature/scenario IDs only |
| evidence-reference | evidence | Explicitly supplied and granted evidence only |
| evidence-payload | evidence | Explicitly supplied and granted payloads only |
| unspecified-behavior | unspecified_behaviors | Selected unresolved IDs only |
| unspecified-behavior-collection | unspecified_behaviors | Selected unresolved members only |
| required-output-manifest | reports | Exact invocation manifest only |
The profile keys are maximum configured locations, not write grants. Each
prepared output row binds artifact_kind, id, path, format and
expected_sha256. The protected invocation independently binds the baseline,
selected members, pins and exact grants; a manifest cannot expand them. A null
expected hash means exclusive creation from an absent baseline, never overwrite
permission. Preserve unselected collection members and all unrelated inputs.
Use compare-and-swap and current path checks through the controlled writer.
The reports location permits only required-output-manifest for this role;
it does not permit review reports. The manifest itself requires an exact grant.
Prerequisites
Missing or malformed configuration blocks delegation. Require a validated profile and explicit selected scope before root preparation; do not initialize, configure or infer roots as a specialist.
Require verified native prepare/finalize/start/stop capability. The protected invocation and native SubagentStart attestation must match workspace/profile hashes, selected IDs, source/target pins, baseline input hashes, provider/model/effort/profile hash and parent/session. Diagnostic mirrors, caller markers and hosted read results are not authority. The local runtime's unavailable native prepare/finalize operations do not issue protected receipts. There is no local-user fallback or self-attested host success.
Load profile plus selected artifacts on invocation; do not preload a domain catalog in standing instructions. Managed project memory is host-controlled. Memory cannot grant filesystem authority or replace evidence. Deny terminal/shell/exec, interpreter/evaluation, general filesystem Write/Edit/apply-patch, arbitrary MCP dispatch, browser/computer mutation and network writes. Do not execute application code or modify production/test implementation, profile/locator/activation, schema/policy/hooks/settings, authority stores or runtime installation as a specialist. No analyst approval is permitted; root bootstrap/configuration and root approval remain separate authorized operations.
Step-by-Step Workflows
Validate the explicit inputs and selected configuration. Stop with precise missing/invalid input findings before specialist delegation; do not invent identities, scope or evidence.
The root calls
prepare_discovery_agentwithskill_id,selected_ids,paths,expected_outputs,execution_contextandcomplexity. Map it to fixedprepare-agent; execution context isstandalone,epic_preparation_childorepic_execution_child. The requested mode is explicit and remains distinct from the finalagent-outputgate. Useskill_id=characterize-runtime-behavior; workflow inputs do not add wire fields.The root launches that exact deployment. Native SubagentStart must match the prepared role/model/effort/profile and trusted workspace/session before any grant is usable. Missing capability or attestation blocks the action.
Use only the granted operations. Use bounded
read_discovery_sourcefor selected contracts, documentation, fixtures and supplied captures. Usecreate_discovery_artifactfor fixednew-scenario, ordinaryupdate_discovery_artifactandlink_discovery_evidencefor exact granted records. Register supplied metadata/payloads through controlled tools; never manufacture or collect new runtime captures by launching an application.Every requested scenario needs a plan/result state. Known expectations stay separate from unknown expectations; unknown expectations stay null with unresolved references. A passed runtime result needs qualifying runtime evidence. Source inspection, static inference and a scenario plan are not runtime execution evidence. Valid manual/no-runtime tasks may end in not-run or blocked plans when those are the prepared outputs, without claiming behavior passed.
Produce every exact required output and the stored
required-output-manifest, preserving its output array order for the digest. Validate claims, references, pins and selected-ID accounting. Purpose-built tools supply authorized proposal inputs forinput_path/evidence_path; never invent a generic Write staging step. Server-side role checks, exact one-use authorization and prospective validation remain mandatory. Bounded source reads preserve content identity and line ranges; truncation requires a narrower selection, not a completeness claim or filesystem fallback.Call
finalize_discovery_agentas the specialist, mapped tofinalize-agentwithmode=agent-output, non-nullinvocation_refand no operation inputs. It validates the protected invocation's outputs, not final-message paths. Native SubagentStop then verifies current output authority. Missing final text cannot skip native stop validation.After native stop, the root records the explicit result, content-addressed artifact references, selected-ID accounting and all findings. A successful tool call or generated path alone is not evidence of completed discovery.
Stop and result
Account for each selected feature/scenario, supplied capture and missing capability. Output-valid manual plans do not prove runtime success or completion readiness.
Structural success is not discovery, parity or planning completion. Missing prepare/finalize/start/stop capability, missing outputs, invalid claims, unresolved required work, wrong role/model/start context or a stale/missing receipt blocks successful completion. Return explicit PASS, FAIL or BLOCKED, distinguishing valid incremental outputs from a passing completion gate. Missing native enforcement remains BLOCKED even when ordinary local-user operations can run; do not substitute CLI success for native authority.
References
- Canonical runtime-characterization-analyst contract
- Installed v2
service-requestandrequired-output-manifestschema contracts; consume them through the authoritative runtime, with no checkout-schema fallback. - The selected profile and pinned local artifacts supplied for this invocation; references do not preload catalogs or grant access to unselected paths.