Matt Pocock Agent Skills — for DeepSeek Harness (DSH)
⚠️ Unofficial community adaptation. This package is an adaptation, not
the upstream project. The skill bodies were written by Matt Pocock
(mattpocock/skills, MIT, © Matt Pocock)
— we did not author them. We only re-arranged them into DSH's skill layout
and wrapped them in a DSH bundle plugin. If you find them useful, star the
upstream repo. License & attribution: LICENSE.
A DeepSeek Harness bundle plugin that ports Matt Pocock's
"Skills for Real Engineers" set into
native, discoverable DSH skills.
This is a skill-set adaptation, not a fork of the Claude Code plugin harness:
the SKILL.md bodies are preserved as-is (same prompts, same process),
re-arranged so DSH's one-level skill discovery (<root>/<name>/SKILL.md) finds
them. Upstream keeps its skills in four buckets (engineering/, productivity/,
misc/, in-progress/); this package flattens them into skills/ and records
each skill's upstream bucket in upstream.json.
Synced with upstream mattpocock-skills 1.3.2 (commit
4ae2317,
2026-10-31). Adapted and verified against DSH 0.2.1-rc.5.
Contents — 39 skills
Engineering (20)
| Skill | What it does |
|---|
ask-matt | Router: which skill or flow fits your situation |
code-review | Two-axis review (Standards + Spec) of a diff from a fixed point, via parallel sub-agents |
codebase-design | Shared vocabulary and discipline for designing deep modules |
diagnosing-bugs | Disciplined diagnosis loop for hard bugs and performance regressions |
domain-modeling | Build and sharpen the project's domain model, glossary, and ADRs |
grill-with-docs | Grilling session that also builds the domain model and docs as it goes |
implement | Implement a spec or tickets, driving TDD at pre-agreed seams |
implement-spec | Implement a whole spec on one integration branch, ticket by ticket |
improve-codebase-architecture | Scan for deepening opportunities, report as HTML, then grill one |
pr | Write the PR body from a fixed template (summary, evidence, merge danger) |
prototype | Throwaway prototype to answer a design question (logic or UI) |
research | Research a question against primary sources into a cited Markdown file |
retro | Retrospective on a coding session, with environment improvements |
setup-matt-pocock-skills | Per-repo setup: issue tracker, triage labels, domain doc layout |
tdd | Red-green-refactor discipline with mocking and test guides |
to-spec | Turn the current conversation into a spec on the issue tracker |
to-tickets | Break a plan or spec into tracer-bullet tickets with blocking edges |
triage | Move issues and external PRs through a triage state machine |
wayfinder | Plan work too large for one session as a shared map of decision tickets |
wizard | Generate an interactive bash wizard for steps only a human can perform |
Productivity (7)
| Skill | What it does |
|---|
grill-me | Relentless interview to sharpen a plan or design |
grilling | Grill a plan, decision, or idea until the design tree is resolved |
handoff | Compact the conversation into a handoff document for another agent |
teach | Teach a skill or concept across sessions in a stateful workspace |
to-questionnaire | Turn a decision into a questionnaire for someone else to fill in |
wait-what | Re-pitch a message that did not land, in plain language |
writing-for-agents | Write documents (skills, AGENTS.md) that agents can actually follow |
Misc (4, rarely used upstream, not promoted in their plugin)
| Skill | What it does |
|---|
git-guardrails-claude-code | Claude Code hooks that block dangerous git commands before they run |
migrate-to-shoehorn | Migrate test files from as assertions to @total-typescript/shoehorn |
scaffold-exercises | Create exercise directory structures that pass linting |
setup-pre-commit | Set up Husky + lint-staged + type checking + tests |
In-progress (8, upstream beta: public on purpose, feedback wanted, content may change)
| Skill | What it does |
|---|
chief-of-staff | Pursue a long-running goal in one session by coordinating sub-agents |
claude-handoff | Hand the conversation off to a fresh background agent |
loop-me | Grill the user about specs for the workflows they want to build |
setup-ts-deep-modules | Wire dependency-cruiser so each TypeScript package is a deep module |
software-factory | Shared language for designing a software factory |
writing-beats | Writing, exploit: assemble raw material into a journey of beats |
writing-fragments | Writing, explore: mine raw fragments, no structure yet |
writing-shape | Writing, exploit: shape raw material into an article, paragraph by paragraph |
Each skill is a single-level skills/<name>/ directory with its resources
(agents/openai.yaml, scripts/*, reference .md) kept alongside. DSH discovers
them exactly like any local skill.
How to invoke each skill
DSH classifies skills by who may load them. This bundle's 39 skills fall into
two groups (verified against the real skill-filesystem provider):
| Group | Skills | How to use |
|---|
| Model + user (15) | code-review, codebase-design, diagnosing-bugs, domain-modeling, pr, prototype, research, tdd, wizard, grilling, writing-for-agents, git-guardrails-claude-code, migrate-to-shoehorn, scaffold-exercises, setup-pre-commit | The model may load them on its own when a task matches; they also appear in the / slash menu for you to force-invoke. |
| User only (24) | ask-matt, grill-with-docs, implement, implement-spec, improve-codebase-architecture, retro, setup-matt-pocock-skills, to-spec, to-tickets, triage, wayfinder, grill-me, handoff, teach, to-questionnaire, wait-what, chief-of-staff, claude-handoff, loop-me, setup-ts-deep-modules, software-factory, writing-beats, writing-fragments, writing-shape | Only you can start them — pick them in the / slash menu, or type /name <args> in the composer. Most carry disable-model-invocation: true upstream. |
Why so many are user-only: upstream marks interactive coaching flows and
work-intake flows as user-gesture-only so the model does not start a
multi-session process unprompted. To let the model pick one up by itself,
remove the disable-model-invocation: true line from that skill's SKILL.md.
Install
Requires DSH 0.2.1-rc.5 (the bundle pins
@deepseek-ai/dsh-skill-filesystem@0.2.1-rc.5; bump the pin when you upgrade
the runtime).
# from the GitHub release (latest published tarball)
dsh plugin --profile web add https://github.com/xiaoxiaosrm/dsh-mattpocock-skills/releases/download/v0.5.0/mattpocock-community-dsh-engineering-skills-0.5.0.tgz
# or from a local checkout / tarball
dsh plugin --profile web add file:./mattpocock-dsh-engineering
In DSH Desktop, install the same package from the Plugins view (or add
it to the Desktop profile's package.json dependencies and
dsh.profile.bundles) and restart the app.
Then restart the profile. Verify the bundle loaded and its skills are visible:
dsh --profile web --dump-config | grep -A5 'skill-filesystem-mattpocock'
The skills appear in the model's catalog alongside your normal local skills —
on every DSH surface (web, TUI, headless). User-only skills additionally appear
in the / slash menu after the profile restarts and a session (re)opens.
Note on agents/*.yaml resource files. The agents/*.yaml companions are
Claude Code interface descriptors and are not interpreted by DSH. They ship
only for fidelity to the source set and are inert. Several skills also reference
docs/agents/issue-tracker.md and similar per-repo files created by
/setup-matt-pocock-skills; run that skill (or provide an issue tracker) once
in your project for the tracker-dependent skills (code-review, triage,
to-tickets, to-spec) to resolve a spec source.
Updating from upstream
Upstream changes often; this repo keeps the sync mechanical and reproducible:
npm run check:upstream # download upstream, validate all skills, report adds/updates/removes (no writes)
npm run sync:upstream # write skills/, refresh upstream.json
node scripts/sync-upstream.mjs --prune # also delete skills upstream removed
The script downloads the upstream tarball, validates every SKILL.md against the
DSH frontmatter contract (name equal to the directory and kebab-case,
description present, kebab-case invocation keys), asserts the upstream plugin
manifest's promoted set is covered, and only then writes. upstream.json
records the synced commit and plugin version.
Why a plugin vs. just copying to ~/.dsh/skills/
- Distributes and version-skills from one deliverable across machines/repos.
- Lives under your profile's
node_modules, so dsh plugin remove cleans it.
- A single
cordis.patch.yml registers its own dedicated host
skill-filesystem instance (skill-filesystem-mattpocock) into DSH's
global skill layer — so the set loads in every surface (web, TUI,
headless). The bundle does not patch the shared skill-filesystem row:
the web profile ships that row disabled ("presets own local discovery"), so
appending customSkillDirs to it made the whole set invisible on web. Instead
this bundle inserts a distinct instance with providerName: mattpocock and
includeDefaultRoots: false, isolating its discovery to exactly this bundle's
skills/ directory. Verified against DSH 0.2.1-rc.5's bundle patch baseUrl
(the profile directory).
Note: the npm tarball intentionally ships only the runtime files
(skills/, upstream.json, cordis.patch.yml, LICENSE, README.md). The
full change history lives in the repository's CHANGELOG.md on GitHub.
License & attribution
MIT. The skill bodies are adapted from
mattpocock/skills (MIT, © Matt Pocock).
See LICENSE. If you find the originals useful, star the upstream
repo; this package is a community distribution adaptation only.
