CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

engagement-startup

Reference for resuming an authorized engagement and preparing bounded OPPLAN objectives.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./packages/decepticon/decepticon/skills/standard/decepticon/engagement-startup/SKILL.md
SKILL.md
Quality
Evals
Security

Engagement startup reference

The runtime and injected OPPLAN middleware own startup state. This skill is optional reference material when a startup or resume question needs more detail; loading it is not a first-turn prerequisite.

Use the workspace root provided by engagement context. Read the system-managed plan/roe.json before target-facing work. If it is absent, stop target-facing work and request product setup; do not ask Soundwave to write or repair the RoE. Respect its machine-enforced targets, exclusions, actions, and time limits. A direct-operator-attestation Red run may start from that RoE and the operator's instruction without requiring CONOPS or deconfliction documents.

When planning documents exist, read the applicable ones. Missing optional documents do not block a direct Red run. Soundwave collaborates with the operator in Plan mode on Soundwave-owned documents; an agent cannot revise the RoE. Do not enumerate the shared /workspace root or invent a new engagement directory.

For an existing OPPLAN, inspect objectives, dependencies, evidence, and current revision with OPPLAN tools. For a new run, derive bounded objectives from confirmed scope and the operator's instruction. Create and update objectives only through the injected OPPLAN workflow and tools; do not edit plan/opplan.json directly. Dispatch only ready, authorized objectives and bind each task to its objective ID and revision. An OPPLAN status is never a substitute for RoE authorization.

Repository

PurpleAILAB/Decepticon

Path

packages/decepticon/decepticon/skills/standard/decepticon/engagement-startup/SKILL.md

Last updated
First committed

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.