At a glance
What it does
A documented DSH workflow skill.
Before you choose it
A documented DSH workflow skill. The supplied skill document describes its workflow and boundaries.
Best for
Users who need a repeatable engineering workflow.
Common tasks
- Follow the documented workflow when its trigger matches the task.
Permissions and data
The skill guides local workflow decisions; external behavior is not independently audited.
Permissions- Uses the documented workflow.
- Data handling was not independently audited.
- External services follow the supplied project instructions.
- Credential requirements were not independently tested.
Limitations
- Runtime compatibility and installation behavior are not established.
What DSHub checked
- The pinned source and skill document were captured.
What DSHub did not check
- Installation and runtime behavior were not tested.
Pinned install
Primary action
This standalone skill does not have a DSH Plugin install action. Use its source documentation for the delivery method.
Maintainer source
Skill instructions
SPDX-FileCopyrightText: Copyright (c) 2026 Process Mission
SPDX-License-Identifier: MIT
name: simplify description: >- Simplify code or a patch by removing dead code, duplicated facts, redundant abstractions, excess state, and unjustified compatibility paths while preserving required behavior. Use for cleanup, deduplication, reducing LOC or complexity, deepening modules, or narrowing over-generalized designs.
Simplify
Set the boundary
Treat required behavior, public contracts, ownership, permissions, data
migrations, and cross-surface compatibility as hard constraints. Read the root
AGENTS.md, inspect the worktree, and record the baseline in the task audit.
Optimize in this order:
- Remove concepts, states, branches, and source lines.
- Derive duplicated facts from one authoritative source.
- Merge abstractions that split one invariant or workflow.
- Generalize only around demonstrated variation.
Moving code into helpers or reformatting it is not simplification.
Find excess
- Search declarations, production consumers, tests, docs, build files, and history before calling code dead.
- Treat a duplicated fact as a missing single source of truth.
- Treat one-mode registries, callbacks, wrappers, and fallbacks as candidates for deletion or narrowing.
- Treat forwarding-only interfaces as shallow modules; move policy and validation behind a smaller boundary.
- Keep compatibility paths only when a current requirement depends on them.
Classify each candidate as delete, derive, merge, deepen, narrow, or keep. Choose the coherent option that removes the most concepts with the fewest new rules.
Change safely
- For review-only requests, stop with evidence and a reduction proposal.
- Otherwise, apply the smallest behavior-preserving reduction.
- Remove orphaned imports, types, configuration, tests, and documentation with the deleted model.
- Do not add dependencies, compatibility layers, generic helpers, or broad API changes merely to make the patch look smaller.
- Preserve unrelated worktree changes and pinned upstream code.
Verify
Run the smallest sufficient build, test, smoke, and style checks for the
affected contract. Search again for orphaned consumers and stale configuration,
then run git diff --check.
Report removed concepts, retained behavior, evidence, and unresolved gaps. If LOC is material to the request, measure the same source scope before and after; never present lower LOC as success without behavioral evidence.
Operate deliberately
Install and manage
Prerequisites and target Profile
Target: No native DSH Profile target.
Delivery: Skill Files — https://github.com/hust-open-atom-club/oh-dsh。
Compatibility and access
Requires_host_review: Not established by supplied evidence。
Review compatibility evidence ↗
Risk facts
Review instructions before use.
Evidence ↗Evidence and editorial reviewManifest, Bundle patch, distribution and freshness
Immutable evidence
Review status and source activity
Approved for publication after reviewing the source-linked content and immutable release record. AI assisted with the draft; the publication decision was human.
Human reviewed Aug 29, 2026, 3:16 PM UTC。GitHub facts last checked Aug 29, 2026, 3:11 PM UTC。
No material source change has been recorded since this evidence baseline.