dsh-superpowers

description: "obra/superpowers skills provider plus a system-prompt bootstrap for DeepSeek Harness." kind: "package-bundle"

@firefly0621/dsh-superpowers

English | 中文

Summary

Bring the obra/superpowers workflow kernel and its fused extensions into a DeepSeek Harness profile as one skill catalog plus a standing skill-first bootstrap. Use it when product sessions should move from intent through plan, test, debug, review, and verification in a repeatable order. It is opt-in and ships no harness peers.

Table of Contents

• Summary
• Model Experience
• Known Limitations and Deferred Work
• Dev Note

Package identity

Installable DeepSeek Harness plugin bundle that brings obra/superpowers into product sessions: a 35-skill catalog split into core, advanced, product, and authoring bundles, adapted to dsh tooling, plus a SessionStart-equivalent bootstrap. The default profile loads the 19-skill core bundle (diagnosing-superpowers stays out until a deep dsh port).

Publish name: @firefly0621/dsh-superpowers (version tracks the harness family, currently 0.1.0-rc.41). Source of record for this fork package: github.com/oThTJx/dsh-superpowers. This package is opt-in and is not part of the official main dsh-base composition.

What it restores

Superpowers behavior · dsh realization Skills library under skills/*/SKILL.md · ctx.skills provider superpowers (packaged skills/ directory, dsh-adapted) SessionStart hook injecting using-superpowers · system-prompt/assemble section skill:superpowers with the same ` framing (every non-subagent request); using-superpowers is user-only in the skill catalog Platform references/*-tools.md · bundled skills/using-superpowers/references/dsh-tools.md appended inside that section Subagent skip (SUBAGENT-STOP) · no full using-superpowers bootstrap when session.header.origin === 'subagent'; injects a short skill:superpowers-worker preamble instead Model loads other skills on demand · existing dsh-tool-skill catalog + skill` tool

The skill bodies ship as dsh-adapted prose under skills/ (no vendored source, no git submodule). Foreign-harness tool names and platform references were rewritten for dsh, and the superpowers: skill-name prefix was removed. The published tarball includes skills/, assets/NOTICE.md, and the offline scorer scripts/score-skill-first.mjs. NOTICE records obra/superpowers (2ce8aa15, v7.0.1), mattpocock/skills (5beb35b0), addyosmani/agent-skills (aeac41d4), and bmad-code-org/BMAD-METHOD (61e01f82, with trademark notice) as review pins.

Capabilities that overlap are fused into one owning skill. When an upstream source has material that does not justify a second skill directory, it ships as a reference pack under the owner and is loaded only at the step that needs it. The catalog therefore stays at 35 skills while the fused behavior keeps growing.

Bundles

The package ships four bundles. core is always loaded; the others are opt-in through the bundles config.

Bundle · Default · Skills · Purpose core · yes · 19 · The day-to-day workflow: brainstorming, planning, execution, TDD, debugging, review, verification, finish, domain/design, security, sources, constraints advanced · no · 6 · Subagent-driven execution and parallel dispatch, context engineering, prototype, wizard, grilling product · no · 8 · Idea, PRFAQ, PRD, spec, UX, retrospective, course correction, and multi-role debate for multi-stakeholder product work authoring · no · 2 · writing-skills and dsh-harness-contributor for skill and repository maintainers

Core is always included, even when bundles names only an optional bundle. A bare install therefore sees 19 skills; a full install sees 35. The model-visible core catalog is 16 skills after using-superpowers, handoff, and wait-what stay user-only.

Matt skills and fused extensions

Superpowers remains the workflow kernel (brainstorming → writing-plans → TDD / debugging / review / verify). Selected mattpocock/skills, addyosmani/agent-skills, and BMAD-METHOD practices ship as one fused catalog: every skill declares at most one bundle label, and that label is the only catalog metadata this provider publishes.

Session skills (grilling, handoff, wait-what) are absent from the model ` catalog and refused by the model skill tool. Users invoke them with a whitespace-bounded /name token in a user message (for example /grilling); dsh-tool-skill injects the skill body as instructions. using-superpowers is also disable-model-invocation: true, but its standing copy arrives through the system-prompt bootstrap rather than that gesture (users may still /using-superpowers` to reload the body without the adapter).

Obra skills that absorbed merges (keep on obra sync): brainstorming (inline Architectural grilling; Not Doing; Always/Ask/Never; reject aim-past-100), using-superpowers (≤5-line intent fork; anti-stack; tiny-edit; implementation priority; contextual gates), test-driven-development, systematic-debugging, requesting-code-review (Standards ∥ Spec + checklists + review lenses + doubt pass), executing-plans (slice discipline + impact map), refactoring (clarity + structural modes), source-driven-development (research mode), codebase-design, writing-plans, handoff, verification-before-completion.

Implementation and quality extensions: executing-plans owns the task loop, slice discipline, and impact map; refactoring owns clarity and structural modes; source-driven-development owns API-grounded work and the research mode; requesting-code-review owns post-hoc review and the in-flight doubt pass; subagent-driven-development owns per-task dispatch and parallel-dispatch reference. dsh-harness-contributor and explaining-changes live in the authoring and advanced bundles and do not enter the default core catalog.

bundle is catalog metadata only — not a router. Invocation frontmatter is parsed privately by this provider (plugin-only; upstream harness packages unchanged).

Fusion map

Each skill owns one capability, and every selected source that covers that capability feeds its body. When two sources overlap, the package keeps one skill and merges both contributions — it never ships two peers for one job, and it does not drop a selected source's behaviour because another source moved first. Unselected capabilities are listed as out of scope in the debt table.

Skill · Sources fused into it · It owns brainstorming · obra spine · BMAD product scheme · agent-skills anti-patterns · intent → approved design, size-based gates writing-plans · obra plan format · agent-skills task breakdown · Matt spec-to-tickets · approved spec → ordered plan test-driven-development · obra Iron Law · agent-skills trigger breadth · RED-GREEN-REFACTOR loop subagent-driven-development · obra controller · dsh settlement wait · parallel dispatch · per-task dispatch, review, and parallel investigation executing-plans · obra inline execution · agent-skills slicing rules · dsh script wiring · inline plan execution, slice discipline, impact map systematic-debugging · obra four phases · agent-skills error recovery · observability and performance · root cause before any fix refactoring · agent-skills clarity body · dsh structural extension · agent-skills deprecation/migration · clarity and structural modes, retirement requesting-code-review · obra Standards ∥ Spec · agent-skills quality body · BMAD review lenses · in-flight doubt pass · review request, lenses, and disposition verification-before-completion · obra gate · agent-skills browser and CI evidence · proof before claiming done finishing-a-development-branch · obra finish · agent-skills shipping, git, CI/CD · Matt PR body · integrate, release, roll back codebase-design · Matt deep modules · agent-skills interface contracts · BMAD architecture spine · module, interface, and architecture decisions domain-modeling · Matt glossary · agent-skills ADRs and docs · model and decisions grilling · Matt design tree · agent-skills interview · BMAD advanced elicitation · user-requested interview forge-idea · BMAD distillation · agent-skills idea refine · idea verdict security-and-hardening · agent-skills controls · dsh untrusted-output stance · threat model and boundaries source-driven-development · agent-skills API facts · research mode · BMAD deep recon · docs-grounded API facts and cited investigation constraint-driven-development · agent-skills · project quality floor context-engineering · agent-skills hierarchy · dsh budget model · BMAD project context · context budget, packing, project instructions ux-spec · BMAD spines · agent-skills frontend acceptance and engineering · UX acceptance and implementation contracts

The map is an inventory, not a lock: a skill may gain a source, but it never splits into one peer per source, and a merged section is never replaced by whichever upstream moved last.

Reference packs

The following capabilities ship behind their owner rather than as extra skill directories. The owner links the pack at the step that needs it, so the model pays for the material only when that branch is reached.

Owner · Reference · Fuses systematic-debugging · references/observability-and-performance.md · production observability · performance regression workflow refactoring · references/clarity.md · behavior-preserving clarity pass refactoring · references/structural.md · structural change after repeated fixes refactoring · references/deprecation-and-migration.md · deprecation decision · strangler/adapter/flag · expand → contract executing-plans · references/slice-discipline.md · slice loop · slicing strategies · scope discipline executing-plans · references/impact-analysis.md · short impact map before a cross-boundary change ux-spec · references/frontend-engineering.md · component and state ownership · design-system adherence · accessibility · responsive UI context-engineering · references/project-context.md · AGENTS.md setup/adopt/refresh/audit · writing for agents codebase-design · references/architecture-spine.md · architecture invariants · stable AD IDs · reviewer gate; plus TypeScript entry-point enforcement in the body writing-plans · references/spec-to-tickets.md · spec-driven workflow · tracer-bullet tickets · wayfinding · triage requesting-code-review · references/review-lenses.md · adversarial · edge-case · verification-gap · claims/deletion checks · walkthrough requesting-code-review · references/doubt-driven-review.md · in-flight adversarial review of a decision about to lock in subagent-driven-development · references/parallel-dispatch.md · independent parallel investigations and prompt structure writing-skills · references/skill-evals.md · baseline/variant/quality/trigger evals · toolsmith pass source-driven-development · references/research-mode.md · open-ended cited investigation · research budget source-driven-development · references/deep-recon.md · decision-grade research · research firewall · claim sources test-driven-development · references/retrofitting-tests.md · end-to-end/API tests for existing behavior grilling · references/advanced-elicitation.md · pre-mortem · red team · first principles · questionnaire prd · references/product-brief.md · discovery · coaching/fast paths · right-sized brief retrospective · references/evidence-review.md · evidence inventory · range attribution · acceptance verdict · follow-through constraint-driven-development · references/floor-guard.md · diff-scoped floor guard · five bar-lowering moves · exit 0/1/2 security-and-hardening · references/hardening-patterns.md · OWASP patterns · input validation · destructive paths · dependency audit · rate limiting · secrets · data classification · LLM output handling explaining-changes · references/walkthrough.md · intent → broad strokes → slices → periphery finishing-a-development-branch · references/ci-and-delivery.md · pipeline order · previews · staged rollout · dependency automation finishing-a-development-branch · references/pr-description.md · Summary · Evidence · Test plan · Merge danger brainstorming · references/technique-catalog.md · working modes · divergence lenses · convergence tests

Reference packs are part of the owner's contract: tests/superpowers.spec.ts checks that each fusion pack listed above ships with its defining pins, that every reference file is linked from its owner's prose, and that every relative Markdown link under skills/ resolves. A pack is not a second router and does not appear in ``.

Install into a dsh profile

Requires DeepSeek Harness peers (@deepseek-ai/dsh-skill and related packages), typically from the official CLI/dsh-base stack. Source-workspace workspace:* peers mean the matching DSH release; packed manifests substitute that exact version. DSH checks those peer ranges at install and profile startup and refuses an incompatible pair without an exact version exemption — see Version compatibility.

dsh plugin --profile web add @firefly0621/dsh-superpowers

From a harness source tree:

pnpm dsh plugin --profile web add @firefly0621/dsh-superpowers

Then boot dsh --profile web (or pnpm dsh web). If this fork's dsh-base already mounts id: superpowers, do not add the same row again — disable the base row first, or use a profile that does not include it.

Local / pre-publish check

pnpm run build:lib:host
pnpm --filter @firefly0621/dsh-superpowers pack
pnpm dsh plugin --profile superpowers-demo add ./firefly0621-dsh-superpowers-0.1.0-rc.41.tgz

(pnpm pack writes the tarball to the repository root by default. There is no per-package build script; host lib build produces lib/.)

Enable from this monorepo without npm

This package is opt-in in the harness source tree. Mount the shipped overlay patch (or dsh plugin add):

pnpm dsh web --patch packages/skill/superpowers/cordis.patch.yml
pnpm dsh --profile headless --patch packages/skill/superpowers/cordis.patch.yml "task"

Fork trees that already mount id: superpowers in their base need no extra step; set disabled: true on that row to omit it.

Config

Field · Default · Meaning skillsRoot · packaged skills/ directory · Absolute skills directory; a relative path fails at apply bootstrap · true · Contribute parent using-superpowers (+ dsh adapter) as skill:superpowers, and the short worker preamble as skill:superpowers-worker on subagent-origin sessions bundles · ['core'] · Bundles to expose: core is always included; add advanced, product, and/or authoring

Example full install:

- id: superpowers
  name: '@firefly0621/dsh-superpowers'
  config:
    bundles: [core, advanced, product, authoring]

Update Superpowers

There is no vendored submodule. To re-port newer upstream releases: for each source, diff content baseline → target, then walk every open row in sync debt below, then re-apply the dsh adaptation by hand. Do not use assets/NOTICE.md review pins as the sole diff baseline — those pins record last review, not “skills/ equals that tree”.

Adaptation rules: replace foreign-harness tool names and platform references, remove the superpowers: skill-name prefix, keep the behavioral content verbatim (dsh exceptions only in the table below), and distill Matt / agent-skills / BMAD ADDs (never dump BMAD _bmad runtime, memlog, HTML seals, or trademark personas).

Since the v7.0.1 sync, subagent-driven-development and writing-skills keep their long guidance in references/ and read a file from disk at the step that needs it, so a compacted session can reload one section instead of losing the whole body. Keep that layout when re-porting: a rule that lives inline again defeats it. The same sync removed the executing-plans worked example for the same reason, and rebuilt brainstorming onto the v7.0.1 text (which already carries 961a26d): first message → conversation → playback → size the work, a design doc at every size (a short one for a small change), and a gate that never skips without consent. The dsh decision-support format for architectural clarifying stays inline and states its one-question exception; the older three-path router and its separate gate tables are gone so one gate is stated once. Every packaged SKILL.md stays under upstream's 20,000-byte compaction cut, and the package suite enforces it.

Fusion, not port. Several upstreams feed one skill, and each keeps its own role: obra supplies the behavioral spine, agent-skills supplies ADDs and OPTIMIZE merges, Matt supplies named extensions, BMAD supplies product-discovery distillations. Never replace a merged section with one upstream's version because that upstream moved — re-apply the merge onto the new spine and keep every selected source's contribution (for example brainstorming keeps Not Doing / Always·Ask·Never through the v7 rebuild, and test-driven-development keeps the agent-skills trigger breadth inside obra's description). When the contribution is a distinct capability rather than a replacement section, add a reference pack under the owner; do not create a second skill directory for it. Capabilities outside the selected scope are named as out of scope in the debt table rather than silently counted as ported.

dsh adaptation exceptions (allowed non-verbatim edits):

Exception · Why Strip superpowers: / foreign skill-name prefixes · Catalog names are bare in dsh Rewrite foreign harness tools → dsh (subagent / subagent_fork, todo_write, dsh-tools.md) · Platform adapter writing-plans handoff label Native → Inline · Avoid “native harness” ambiguity; still means same-session executing-plans sdd-workspace: refuse marker-less existing dirs (no adopt) · Deliberate ownership tighten vs obra; documented in the script header Invoke bundled scripts via bash … · Packaged extractors may strip Unix exec bits Keep catalog Do not use negatives / description contracts · Fusion routing gates

Content baseline and sync debt

Source · Content baseline (landed in skills/) · NOTICE review pin · Open sync debt obra/superpowers · Spine through v7.0.1 at 2ce8aa15, with brainstorming following the v7.0.1 text (which already carries 961a26d): first message → conversation → playback → size the work, a design doc at every size, never skip without consent, one red-flag table, no three-path router; subagent-driven-development / writing-skills guidance split into references/, the executing-plans worked example removed for the compaction cut, inline task loop kept (scripts/task-start / task-done); review-lens and walkthrough distillations landed in existing owners; bundled scripts carry the post-baseline task-ID, unclosed-fence, Windows-path, and relative---project-dir fixes · 2ce8aa15 (v7.0.1) plus the post-baseline fixes f75c01f, 750ba92, 3735a50, bb3a5aa, fa50d83, 8b0eefc, with 369bd87 re-expressed; 961a26d, 2b2ef34, c7730f7, and 6ff820e are already in 2ce8aa15, and 699edc6 deletes a test harness absent from that tree · *(none)* for the selected obra spine; diagnosing-superpowers and cross-harness reference material stay in Known Limitations mattpocock/skills · GLOSSARY-FORMAT + domain-modeling/handoff/grilling/wizard aligned to 49dd158d1; resolving-merge-conflicts removed; re-read at 5beb35b0 (only chief-of-staff, not shipped); to-spec / to-tickets / wayfinder / triage distilled into writing-plans; writing-for-agents into context-engineering · 5beb35b0 · *(none)* for selected capabilities; unselected Matt skills (for example ask-matt, teach, retro, in-progress, and misc sets) stay out of scope addyosmani/agent-skills · Distilled ADDs; context-engineering OPTIMIZE; security-and-hardening + references/hardening-patterns.md; constraint-driven-development + restored references/floor-guard.md; re-read at aeac41d4 (zod chain order fix landed, TDD trigger breadth fused); observability/performance, deprecation/migration, frontend engineering, CI/delivery, and API/interface material distilled into existing owners · aeac41d4 · *(none)* for shipped ADDs BMAD-METHOD · Distilled product ADDs under functional names (no _bmad runtime); re-read at 61e01f82; correct-course and spec-kernel follow the v7 PO replan.md / spec.md contracts; PRD Essential Spine, graded PRFAQ verdict, DESIGN.md/EXPERIENCE.md, retrospective dispositions, architecture spine, project context, deep recon, review lenses, advanced elicitation, e2e test generation, skill evals, product brief, and evidence-based retrospective distilled into existing owners · 61e01f82 · *(none)* for shipped ADDs — v7 replaced bmad-correct-course/bmad-spec with the PO replan/spec references; personas/runtime and unselected build/review/customize skills stay out of scope

Fusion gate checklist (before/after merge):

1. Catalog length stays 35; each skill carries at most one bundle label, the default core catalog is 19 skills, and no skill declares a removed tier label; no second meta-router; no bmad-* skill directory names.
2. Re-assert OPTIMIZE merges (brainstorming Scheme B / Not Doing / Always·Ask·Never; TDD; review Standards ∥ Spec; grilling user-only; executing slice/impact; refactoring clarity/structural pins) after any obra spine overwrite.
3. Same-name overlaps from agent-skills (refactoring, test-driven-development) OPTIMIZE in place — do not add peer directories; merged skills keep their capability as references under the owner.
4. Update SEMANTIC_DESCRIPTION_GROUPS / NEGATIVE_BOUNDARY_BANNED when obra changes skill routing semantics (for example executing-plans inline vs subagent-driven-development).
5. Bump NOTICE review pins when you re-read upstream; update the content baseline / debt table when landed content or debt changes; keep ADD Do not use when… and BMAD exit-state pins.
6. Run pnpm exec vitest run packages/skill/superpowers/tests/superpowers.spec.ts.
7. Confirm executing-plans ships scripts/task-start and scripts/task-done and the SKILL body invokes them (tests failing ≠ tests not recorded).
8. Keep every reference pack linked from its owner and every relative Markdown link resolvable; fusion reference packs in the package suite checks both.
9. Keep the bundle map honest: a skill whose capability is everyday coding belongs in core; product-management, authoring, and opt-in discipline skills stay in their bundles.

Preserve on obra sync: Matt-added skill directories (domain-modeling, codebase-design, prototype, wizard, grilling, handoff, wait-what and companions); agent-skills / BMAD ADD directories (constraint-driven-development, source-driven-development, context-engineering, security-and-hardening, forge-idea, party-mode, spec-kernel, correct-course, prd, prfaq, ux-spec, retrospective); merged owne