High-cost orchestrator workflow for large, high-risk, multi-phase coding efforts with meaningful dependencies and review gates. Do not activate for routine multi-file changes.
63
74%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./src/skills/deepwork/SKILL.mdDeepwork is an orchestrator workflow for heavy coding sessions. Use it only when the work is clearly large or high-risk: multiple dependent phases, cross-cutting architectural change, unsafe-to-partially-ship migration, or sustained coordination across several specialist lanes.
Do not infer Deepwork merely because a task touches multiple files. Do not use it for trivial edits, quick docs changes, simple bug fixes, or routine bounded features.
When deepwork is active, the orchestrator must manage the work as a scheduler, not as the default implementation worker.
.slim/deepwork/;src/, docs/); reserve
.slim/deepwork/ strictly for progress files;Create a task-specific file such as:
.slim/deepwork/<short-task-slug>.mdBefore creating this file—and before planning or delegation—inspect the existing
.gitignore and .ignore. Add only missing entries and do not add duplicates:
# .gitignore
.slim/deepwork/# .ignore
!.slim/deepwork/
!.slim/deepwork/**These rules keep deepwork state git-local while allowing OpenCode to read it.
Do not follow a rigid template. Choose whatever markdown structure best fits the work. The file only needs to remain useful as persistent session state and should capture, as applicable:
@librarian to avoid oracle doing its own
research;Update this file after major decisions, accepted research, reviews, phase completions, validation results, and scope changes. Record accepted findings and reference local files by path rather than copying their contents.
@oracle review
mandatory after each one; record the phase order, specialist ownership, gate
order, and one-line gate rationale in the deepwork file; share a compact
version with the user;Use the scheduler model throughout:
@oracle gate before continuing;@explorer structure scan in parallel with the Oracle gate;Every planned Oracle gate has one initial review and may have at most two re-reviews. Request a re-review only when the remediation materially changes the reviewed decision or risk, or when the original concern cannot be verified with focused evidence. Do not spend a re-review on a mechanical or already-verified change.
State the attempt in every Oracle prompt, for example:
Gate 2 — review attempt 2 of 3 (1 re-review remaining)For re-reviews, tell Oracle to prioritize unresolved material findings, risks introduced by remediation, and whether prior findings are resolved. It must not reopen accepted, unchanged, or resolved concerns. When the two re-reviews are exhausted, record any remaining material risk or blocker in the deepwork file and ask the user whether to accept the risk, change scope, or authorize an exceptional additional review.
When a deepwork phase includes @designer, treat the delivered UI/UX as
accepted design intent for later phases. Record any important design decisions in
the deepwork file before continuing.
After designer work:
@designer;@fixer only for bounded mechanical follow-up that preserves the design
exactly, such as wiring, tests, type fixes, or non-visual behavior changes;3222930
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.