Plugins

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

Registers the dsh-mol stdio MCP server, built on RDKit with no network access, into a DSH profile. It exposes 12 tools: three-level SMILES validation with human-readable diagnostics and character positions, molecular properties, drug-likeness and structural alerts, structure rendering to PNG/SVG, multi-molecule grids, format conversion (SMILES, InChI, InChIKey, MOL, SDF, formula), standardisation with a per-step change log, deduplication, SMARTS substructure matching, fingerprint similarity, and batch clean-up that reports every rejected row. The patch only registers the server; the tools live in this repository's Python package and must be installed first — the README gives a `pip install` route and a from-source route, and until the package is on PyPI the from-source one is what works.

Acceptance-criteria-driven goal completion: locks verifiable criteria, tracks task dependencies, and gates completion behind formal reviewer validation (18 MCP tools).

Compares coding agents in isolated Git worktrees with deterministic validation, scoring, and explicit winner application.

Real-compute verification gates: math simplification, logic proofs, regex validation, E-prover FOL, state-machine checks, and code repair, backed by Go-compiled binaries with prebuilt Windows executables.

Windows desktop LaTeX workspace with 24 template presets, dsh AI writing and selection editing, managed TeX compilation, PDF preview, and BibTeX validation.

Pulls your chat.deepseek.com conversations into a local knowledge base — one Markdown file per conversation, a JSONL transcript and a catalog — and searches them from a control page inside DSH. Daily increments plus a full-history backfill from the official export, an integrity check, and an optional model step that runs through the host llm service and writes only after its JSON passes validation. Reads the web userToken from the DSH credential store and calls chat.deepseek.com only; no install scripts, no runtime dependencies.

Doubao video workshop: a gated pipeline from storyboard to finished cut. Locked art direction, shot validation, character-card vs reference-image separation, first/last-frame continuity and clip dedup; model-aware duration caps (Mini/Fast 10s, 2.0 15s, 2.5 40s). Uses ffmpeg for frame extraction, concatenation and subtitles; speech synthesis calls a separately installed local TTS plugin, and ASR subtitles need Python with faster-whisper.

Long-term memory for dsh with defense-in-depth hardening. Two tiers (project `.dsh-memory/` and user `$DSH_HOME/memory/`), each a plain hand-editable JSON file with bounded entries and tags. Writes are atomic (unique temp file + rename, previous revision kept in a bounded history/) and serialized across processes by a per-tier lock with stale reclaim; a disk-revision check refuses lost updates instead of silently overwriting another writer. Memory text is wrapped in explicit untrusted-data boundaries (forged wrappers stripped on write) to blunt prompt injection from remembered content, load-time validation rejects out-of-bounds stores, and symlink escapes out of the tier directory are refused with MEMORY_STORE_ESCAPE. No content-heuristic filtering and no confirmation step, so headless auto-consolidation stays intact. Install: dsh plugin --profile web add github:RocoFish/deepseek-memory.

One prompt row carrying two independently switchable halves. Identity: a fixed self-reference restated at the head, at the tail after every other section, and in the runtime snapshot, with an instruction to treat contradicting claims as stale cache. Discipline: ten rules, each paired with the condition a reviewer checks — external evidence before claiming done, change face equal to review face, correctness from named call points rather than timing, one source of truth, extension through the registered seam, runtime validation only at real boundaries, loud failure instead of silent skips, orthogonal outcomes reported separately, tests through the delivered entry point, and answer shape (conclusion first, length set by the change).

Cross-session memory as plain Markdown per workspace: weighted injection, bi-temporal invalidation, TTL review with stale markers, credential redaction, error and session retrospectives, SOP skills, and approval-gated self-improvement proposals.

Reasoning-effort gear presets for third-party models: 16 vendor/model presets with per-mode custom wire values, written into dsh-llm-pi-ai with pre-write validation and per-rule rejection; per-model switching between OpenAI Chat Completions, OpenAI Responses and Anthropic Messages with automatic route regrouping; plus a composer Optimize button and a settings section that rewrite the input text with a model you pick.

21 read-only lifecycle governance tools in one self-contained DSH plugin: task tiering, state/plan/evidence validation, gate precheck and aggregation, release/install audits, context and progress analysis, critical path, resume reconciliation, and a mutation preview that always denies execution. Installs from npm as @240xu/dsh-tech-lead.

Ren'Py galgame production workbench: a host-side project service (write gateway plus git snapshots, a dialogue/scene dialect parser, derived progress, human-only review stamps, pinned-SDK validation and playtest, local publish) behind one seam, driven by an embedded web panel and agent tools.

Makes the AI default to Mermaid diagrams in development conversations — system prompt guidance, a mermaid_validate syntax-check tool with real-parser validation, and an output gate that auto-fixes or removes broken diagrams. Rendering via dsh-mermaid.

Adds parametric CAD modeling, geometry validation, previews, design history, and STEP/STL export to DSH.

21 read-only lifecycle governance tools in one self-contained DSH plugin: task tiering, state/plan/evidence validation, gate precheck and aggregation, release/install audits, context and progress analysis, critical path, resume reconciliation, and a mutation preview that always denies execution. Installs from npm as @240xu/dsh-tech-lead.

Experience validation layer for DSH: zero-token collection of tool-failure/retry/search signals, AI refinement into verified skill books (three-layer verification), looked up at task start. Ships 10 trial skills and benchmark data (complex-task success 100% vs 60% bare).

Per-profile settings overlay for DeepSeek Harness: global settings.yaml stays the baseline while each profile overrides any namespace through its own profiles/<name>/settings.patch.yml — object sections merge recursively, scalars and arrays replace wholesale, and !unset masks an inherited value. The overlay is transparent to existing plugins (they keep reading ctx.settings unchanged), writes land in the profile overlay only, and official schema validation, revision semantics, expectedRevision conflicts, watchers and events are untouched. Ships a settings command family (get/set/unset/mask/unmask/promote/demote/migrate/diff/layers) plus a Profile Settings section in the web Settings panel over a loopback RPC channel.

Native DeepSeek Harness plugin for IsingQ: guided QUBO modeling and validation on-device, then user-confirmed remote solving.

Infrastructure as code: gated plan/apply, state and output inspection, and configuration validation via the terraform CLI.

Human-operated Git worktree task board for DeepSeek Harness with validation-bound merge delivery.

Adds 17 barotrauma_* tools to DeepSeek Harness for making Barotrauma mods: environment probing, mod skeleton, item and weapon XML, afflictions, creatures, random events, Lua and C# script scaffolding, localization, validation, icon generation, zip packaging and Steam Workshop publish notes. barotrauma_gen_icon sends your prompt to image.pollinations.ai and writes the returned image into the mod folder; on Windows the Steam install path is read with reg query.