superpowers
Skill263 starsChanged 35 days agoMITView on GitHub
Use when the user wants a disciplined software development workflow with design-first planning, implementation plans, TDD, systematic debugging, code review, or verification-before-completion, adapted from obra/superpowers.
15 other projects use a version of this.
Adopted by
Most recently taken up by
- kazemcodes/skill-treetheir own version, first seen Nov 8, 2026
- ZhouYinLong-lab/Dog-Skillstheir own version, first seen Nov 8, 2026
- salmandev/everything-geminitheir own version, first seen Nov 1, 2026
- lucasnscr/issue-to-pr-aitheir own version, first seen Oct 25, 2026
- Thirumalai-Tech-Developer/Kratos_Agenttheir own version, first seen Oct 8, 2026
- belos-street/skill-kittheir own version, first seen Sep 16, 2026
Used with
Projects with it also use context7, to-prd and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JetBrainsSkillcontext7
Up-to-date library and framework documentation via Context7 MCP. Use when setup, API, or version-specific questions require current documentation.
Also in 4 projects that use this
GoogleSkillto-prd
Turn the current conversation into a PRD and publish it to the project issue tracker — no interview, just synthesis of what you've already discussed.
Also in 3 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 3 projects that use this
- +1 more from google
Other versions15 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 15
- alebgl77/claude-inc★ 21same name
- belos-street/skill-kit★ 8same name
- ZhouYinLong-lab/Dog-Skills★ 7same name
- HK-hub/AgentSkills★ 6same name
- Agnik47/claude-skills★ 3same name
- grasscaograss/AwesomeWeldoneSkills★ 2same name
- hillwang1983-web/agent-factory★ 2same name
- salmandev/everything-gemini★ 2same name
- kazemcodes/skill-tree★ 1same name
- Thirumalai-Tech-Developer/Kratos_Agent★ 1same name
5 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository37 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .cursor/rules/code-citation-clickable.mdcCursor rule
- .cursor/rules/commit-message-english.mdcCursor rule
- autonomous-maintainability-campaignSkill
- autonomous-requirement-discoverySkill
- delivering-delegated-linear-issuesSkill
- development-deliverySkill
- development-designSkill
- development-implementationSkill
- development-lifecycleSkill
- development-retrospectiveSkill
- development-reviewSkill
- development-task-understandingSkill
- development-validationSkill
- idea-search-funnelSkill
- nextclaw-agent-instructions-governanceSkill
- nextclaw-product-blog-storytellingSkill
- nextclaw-product-visual-assetsSkill
- x-twitter-birdSkill
- aigen-image-generationSkill
- bb-browserSkill
- browser-controlSkill
- claude-code-narp-runtimeSkill
- clawhub-nextclawSkill
- codex-narp-runtimeSkill
- find-skillsSkill
- gemigo-cliSkill
- impeccableSkill
- lark-cliSkill
- linear-cliSkill
- mmx-cliSkill
- nextclaw-skin-studioSkill
- opencliSkill
- proxy-local-ai-subscriptionsSkill
- publish-to-nextclaw-marketplaceSkill
- skillhub-guideSkill
- ui-ux-pro-maxSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
29 rules. 0 are common, 27 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 12 edited versions we read keep these.
27
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Use this skill when the user wants a stronger engineering workflow inside NextClaw.
- Distinctive: line 24
Do not present bundled superpowers guidance as a higher-priority authority than the user's instructions, the current project's AGENTS.md, …
- Distinctive: line 30
test-driven development for feature and bugfix work,
- Distinctive: line 46
Always distinguish these paths:
- Very specific: line 57
Do not ask the user to install the upstream repo separately unless they explicitly want the original Codex or Claude plugin setup outside …
- Distinctive: line 61
When this skill triggers, follow this order.
- Distinctive: line 72
If either file is missing, the skill is not correctly installed in the current workspace.
- Distinctive: line 88
Read only the smallest relevant reference instead of loading everything at once:
- Distinctive: line 100
before saying work is done: references/verification-before-completion.md
- Distinctive: line 105
Do not bulk-read all references unless the task truly spans multiple workflow stages.
- Distinctive: line 109
Before following any bundled superpowers guidance, reconcile it with:
- Distinctive: line 116
If there is a conflict, follow the higher-priority local rule and use the bundled superpowers material as methodology, not authority.
- Distinctive: line 120
Prefer the project's existing validation and review commands when they already exist.
- Distinctive: line 121
If the current repository has stricter branching, testing, review, or release rules, follow those.
- Distinctive: line 122
If the environment lacks multi-agent support, skip the subagent path and continue with the non-delegated workflow.
- Distinctive: line 123
If the task is trivial, keep the workflow compact rather than theatrical, but still choose an explicit workflow.
- Distinctive: line 133
If the work becomes multi-step or cross-module, continue with:
- Distinctive: line 141
Before declaring success, use:
- Distinctive: line 155
Before closing the task, use:
- Distinctive: line 165
If the work was executed from a formal plan and the runtime supports delegation, optionally use:
- Distinctive: line 171
Treat the bundled references as workflow assets, not as license to ignore local project rules.
- Distinctive: line 172
Prefer the smallest process that still makes the work explicit and honest.
- Distinctive: line 173
Do not claim TDD happened unless a failing test was observed first.
- Distinctive: line 174
Do not claim a bug is fixed unless the original failure mode was re-verified.
- Distinctive: line 175
Do not claim completion without fresh verification evidence.
- Distinctive: line 176
Do not require subagent usage when the current runtime, product tier, or user request does not support it.
- Distinctive: line 188
Follow the stricter local rule.
- Distinctive: line 189
Use superpowers references only for the missing part of the workflow.
- Distinctive: line 201
verify before claiming completion.
“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Superpowers
Overview
Use this skill when the user wants a stronger engineering workflow inside NextClaw.
This marketplace skill adapts the upstream obra/superpowers project into a single installable NextClaw skill. Because NextClaw marketplace installs one skill directory at a time, this package provides:
- one top-level workflow router,
- bundled local reference files for the most useful upstream superpowers skills,
- and clear rules for when to load which reference.
Be explicit about the boundary:
- This skill owns workflow selection, expectation-setting, and reference routing.
- The bundled reference files own the detailed superpowers methodology.
- NextClaw, the current project rules, and the actual tool runtime own execution.
Do not present bundled superpowers guidance as a higher-priority authority than the user's instructions, the current project's AGENTS.md, or the host platform's rules.
What This Skill Covers
- design-first brainstorming before implementation,
- implementation plan writing for multi-step work,
- test-driven development for feature and bugfix work,
- root-cause-first debugging,
- pre-merge or post-task code review prompts,
- evidence-before-claims verification,
- optional subagent-driven execution when the environment actually supports it.
What This Skill Does Not Cover
- overriding user instructions or project rulebooks,
- pretending NextClaw natively supports the upstream superpowers multi-directory auto-discovery model,
- forcing subagent workflows when the current runtime does not support them,
- claiming a workflow step happened when the needed evidence was not actually collected,
- replacing domain-specific project skills that are more specific than this general workflow skill.
Install Boundary
Always distinguish these paths:
- NextClaw marketplace install:
nextclaw skills install superpowers - Installed NextClaw skill assets:
<workspace>/skills/superpowers/ - Upstream standalone installation outside NextClaw:
clone
https://github.com/obra/superpowersand follow the upstream install docs
For NextClaw users, prefer the marketplace-installed assets already bundled under skills/superpowers/.
Do not ask the user to install the upstream repo separately unless they explicitly want the original Codex or Claude plugin setup outside NextClaw.
Deterministic First-Use Workflow
When this skill triggers, follow this order.
Step 0: Verify bundled references exist
Check:
test -f skills/superpowers/references/brainstorming.md
test -f skills/superpowers/references/systematic-debugging.mdIf either file is missing, the skill is not correctly installed in the current workspace.
Step 1: Classify the user's need
Choose the smallest matching workflow:
- feature or behavior design,
- implementation planning,
- implementation or bugfix execution,
- debugging an existing problem,
- review before merge or handoff,
- verification before claiming completion,
- plan execution with parallel agents.
Step 2: Load only the matching reference
Read only the smallest relevant reference instead of loading everything at once:
- design or requirements refinement: references/brainstorming.md
- implementation plan writing: references/writing-plans.md
- implementation or bugfix execution: references/test-driven-development.md
- debugging and root-cause analysis: references/systematic-debugging.md
- pre-merge or task-level review: references/requesting-code-review.md
- before saying work is done: references/verification-before-completion.md
- executing an approved plan with agent delegation: references/subagent-driven-development.md
Do not bulk-read all references unless the task truly spans multiple workflow stages.
Step 3: Reconcile with host rules before acting
Before following any bundled superpowers guidance, reconcile it with:
- the user's explicit request,
- the current repository's
AGENTS.md, - the host runtime's tool and permission model,
- and any more specific installed skill that directly matches the task.
If there is a conflict, follow the higher-priority local rule and use the bundled superpowers material as methodology, not authority.
Step 4: Execute with honest boundaries
- Prefer the project's existing validation and review commands when they already exist.
- If the current repository has stricter branching, testing, review, or release rules, follow those.
- If the environment lacks multi-agent support, skip the subagent path and continue with the non-delegated workflow.
- If the task is trivial, keep the workflow compact rather than theatrical, but still choose an explicit workflow.
Workflow Routing Guidance
New feature, refactor, or behavior change
Start with:
- references/brainstorming.md
If the work becomes multi-step or cross-module, continue with:
- references/writing-plans.md
During implementation, use:
- references/test-driven-development.md
Before declaring success, use:
- references/verification-before-completion.md
Bug, failing test, or unexpected behavior
Start with:
- references/systematic-debugging.md
Once root cause is understood and a fix is ready, use:
- references/test-driven-development.md
Before closing the task, use:
- references/verification-before-completion.md
Review or handoff checkpoint
Use:
- references/requesting-code-review.md
If the work was executed from a formal plan and the runtime supports delegation, optionally use:
- references/subagent-driven-development.md
Safe Usage Rules
- Treat the bundled references as workflow assets, not as license to ignore local project rules.
- Prefer the smallest process that still makes the work explicit and honest.
- Do not claim TDD happened unless a failing test was observed first.
- Do not claim a bug is fixed unless the original failure mode was re-verified.
- Do not claim completion without fresh verification evidence.
- Do not require subagent usage when the current runtime, product tier, or user request does not support it.
Troubleshooting
Reference files missing
- Re-check the skill installation.
- Confirm
skills/superpowers/exists in the active workspace. - Reinstall the marketplace skill if needed instead of inventing fallback paths.
The current project already has stricter workflow rules
- Follow the stricter local rule.
- Use superpowers references only for the missing part of the workflow.
The task needs the upstream standalone ecosystem
- Be explicit that the marketplace skill is a NextClaw adaptation, not the original multi-plugin install.
- Point the user to the upstream repository and install docs only if they want that exact standalone setup.
The user wants speed over process
- Compress the workflow, but still keep the key gates:
- clarify intent for creative work,
- find root cause before fixing bugs,
- verify before claiming completion.
Success Criteria
This skill is working correctly when:
- the user gets an explicit workflow instead of ad-hoc thrashing,
- the smallest relevant superpowers reference is loaded for the task,
- local project rules remain the source of truth,
- debugging starts with root-cause investigation,
- implementation uses test-first discipline when appropriate,
- and completion claims are backed by fresh verification evidence.
Attribution
This skill adapts the upstream obra/superpowers project for the NextClaw marketplace.
Upstream source mapping is documented in references/SOURCES.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

