agentsclimarketplace

Superpowers

Skill alebgl77/claude-inc/skills/superpowers

Runs 14 numbered engineering protocols in one pack — brainstorm, spec, plan, scaffold, TDD red-green-refactor, systematic debugging, refactoring, code review, performance, security, docs, git hygiene, release checklist, postmortem. Use when the user says "build this feature properly", "debug this systematically", "review my diff", "run a security pass", "ship the release", "write the postmortem", or names any engineering phase from idea to retrospective.From its SKILL.md

Install
npx -y skills add alebgl77/claude-inc --skill superpowers

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 8 stars8 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

4.2 KB, 958 tokens by cl100k_base, as published. Nobody here has run it

Superpowers — Skill Forge

"14-skill power pack"

When to use

  • End-to-end feature work that deserves discipline — "let's build this properly, not vibe-code it"
  • A bug that resists poking — "debug this systematically", "it fails randomly and I'm lost"
  • Pre-merge and pre-ship gates — "review my diff", "run a security pass", "are we ready to release?"
  • After an incident — "write the postmortem"
  • Any single phase named outright — spec it, plan it, refactor it, profile it, document it

The 14 protocols

#ProtocolCore move
P1BrainstormGenerate 3+ approaches, score against constraints, pick one on the record.
P2SpecAcceptance criteria and non-goals written before any code.
P3PlanOrdered steps, each independently verifiable.
P4ScaffoldSkeleton with tooling wired — lint, test runner, entry point, CI hook.
P5TDDRed-green-refactor: failing test first, minimal pass, then clean.
P6Systematic debuggingReproduce → isolate → hypothesize → fix → regress.
P7RefactoringBehavior-preserving change under green tests, one move at a time.
P8Code reviewLine-level and design-level pass — correctness, security, perf, readability.
P9Performance passMeasure first, profile the hot path, fix, re-measure.
P10Security passInputs, authn/z, secrets, dependencies, injection surfaces.
P11DocsREADME, API reference, runbook — written from the reader's seat.
P12Git hygieneSmall atomic commits, imperative messages, clean history.
P13Release checklistVersion, changelog, tests green, rollback plan, ship, verify live.
P14PostmortemBlameless timeline, root cause, action items with owners.

Workflow

  1. Identify the task's phase: idea, build, break/fix, ship, or learn.
  2. Pick the matching protocol(s) from the table and announce the pick — "Running P6 — systematic debugging."
  3. Execute the protocol as concrete steps. P6, for example: reproduce deterministically, isolate by bisecting code/data/env, state one falsifiable hypothesis, fix, add a regression test.
  4. For a full feature, chain: P1 → P2 → P3 → P4 → P5 → P8 → P11 → P12 → P13. Skip a link only by saying so and why.
  5. End every protocol with an artifact — spec file, failing-then-passing test, review notes, changelog — never just narrative.
  6. If the task changes phase mid-flight (the build surfaces a bug), switch protocols explicitly; don't blur two into mush.
  7. Log each run in the output format below and hand the next protocol its inputs.

Output format

## Protocol run — P<n> <name>
Phase: <idea | build | fix | ship | learn>
Trigger: <the ask, one line>
Steps executed:
1. <step> → <result>
2. <step> → <result>
Artifact: <path or inline block>
Verdict: PASS | FAIL — <one-line reason>
Next: P<n> <name> | done

Quality bar

  • Protocol named before work started, not retrofitted after
  • Every run produced a concrete artifact, not just prose
  • P5/P6 runs end with a test that fails without the fix and passes with it
  • Feature chains hit at least P2, P5, and P8 — or the skip is justified in writing
  • Verdicts are earned: FAIL reported as FAIL, never softened to "mostly works"

Example

Ask: "The login test is flaky — fix it properly."

Run P6: reproduced 5x (fails ~40%), isolated to the token-expiry check reading the real clock, hypothesis "clock skew between test container and issuer" confirmed by freezing time, fixed with an injected clock, regression test added that fails on the old code. Artifact: tests/auth/token-clock.spec.ts. Verdict PASS. Next: P12, one atomic commit.

Credits

Inspired by obra/superpowers.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.