all publishers

painhardcore

@painhardcore source repo

73 published skills

  1. ▌
    CI Standard · painhardcore bundle
    Use when the user asks to create, edit, or review a GitHub Actions workflow or CI under .github/workflows/.
    22 repo stars
  2. ▌
    Compose Standard · painhardcore bundle
    Use when the user asks to write, edit, or review a local Docker Compose file (compose.yaml / docker-compose.yml) or a local service stack.
    22 repo stars
  3. ▌
    Makefile Standard · painhardcore bundle
    Use when the user asks to create or edit a Makefile, add or rename a make target, or review Make target names.
    22 repo stars
  4. ▌
    Dockerfile Standard · painhardcore bundle
    Use when the user asks to write, edit, review, migrate, or optimize a Dockerfile, .dockerignore, or container image build.
    22 repo stars
  5. ▌
    Go Project Standard · painhardcore bundle
    Use when the user asks to create or review a Go module's layout (cmd/internal), go.mod, or golangci-lint config.
    22 repo stars
  6. ▌
    Unslop 2 · painhardcore
    Cut AI tells from any writing. Must always apply.
    22 repo stars
  7. ▌
    Architect 2 · painhardcore bundle
    Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
    22 repo stars
  8. ▌
    Interrogate 2 · painhardcore bundle
    Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
    22 repo stars
  9. ▌
    No Comments 2 · painhardcore
    Use before review when the user asks to strip, remove, or clean up comments in code.
    22 repo stars
  10. ▌
    Poteto Mode 2 · painhardcore bundle
    Apply poteto's rigorous engineering workflow to non-trivial coding, investigation, review, migration, and verification tasks.
    22 repo stars
  11. ▌
    Blast Radius 2 · painhardcore
    Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
    22 repo stars
  12. ▌
    Figure It Out 2 · painhardcore
    Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.
    22 repo stars
  13. ▌
    Show Me Your Work 2 · painhardcore bundle
    Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
    22 repo stars
  14. ▌
    Technical Writing 2 · painhardcore
    Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
    22 repo stars
  15. ▌
    Create Verification Skill 2 · painhardcore bundle
    Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
    22 repo stars
  16. ▌
    Principle Build The Lever 2 · painhardcore
    Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
    22 repo stars
  17. ▌
    Principle Fix Root Causes 2 · painhardcore
    Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
    22 repo stars
  18. ▌
    Principle Experience First 2 · painhardcore
    Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
    22 repo stars
  19. ▌
    Principle Model The Domain 2 · painhardcore
    Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
    22 repo stars
  20. ▌
    Maintain Verification Skill 2 · painhardcore
    Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
    22 repo stars
  21. ▌
    Principle Laziness Protocol 2 · painhardcore
    Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
    22 repo stars
  22. ▌
    Principle Boundary Discipline 2 · painhardcore
    Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
    22 repo stars
  23. ▌
    Principle Minimize Reader Load 2 · painhardcore
    Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
    22 repo stars
  24. ▌
    Principle Foundational Thinking 2 · painhardcore
    Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
    22 repo stars
  25. ▌
    Principle Type System Discipline 2 · painhardcore
    Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.
    22 repo stars
  26. ▌
    Principle Subtract Before You Add 2 · painhardcore
    Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
    22 repo stars
  27. ▌
    Principle Exhaust The Design Space 2 · painhardcore
    Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
    22 repo stars
  28. ▌
    Principle Guard The Context Window · painhardcore
    Apply when context is filling up: large outputs, long files, repeated reads, fan-out planning. Route bulk to subagents; keep summaries in the main thread, not raw payloads.
    22 repo stars
  29. ▌
    Principle Never Block On The Human · painhardcore
    Apply when tempted to ask 'should I do X?' on reversible work. Proceed, present the result, let the human course-correct after the fact; reserve confirmation for irreversible actions.
    22 repo stars
  30. ▌
    Principle Sequence Verifiable Units 2 · painhardcore
    Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
    22 repo stars
  31. ▌
    Principle Make Operations Idempotent · painhardcore
    Apply when designing commands, lifecycle steps, or processing loops that run amid crashes, restarts, and retries. Converge to the same end state regardless of partial prior runs.
    22 repo stars
  32. ▌
    Principle Outcome Oriented Execution · painhardcore
    Apply during planned rewrites and migrations with explicit phase boundaries. Converge on the target architecture; don't preserve smooth intermediate states with throwaway compatibility code.
    22 repo stars
  33. ▌
    Principle Redesign From First Principles · painhardcore
    Apply when integrating a new requirement into an existing design. Redesign as if the requirement had been a foundational assumption from day one, instead of bolting it on.
    22 repo stars
  34. ▌
    Principle Migrate Callers Then Delete Legacy Apis · painhardcore
    Apply when introducing a new internal API while old callers still exist. Migrate callers and delete the old API in the same wave instead of preserving compatibility layers.
    22 repo stars
  35. ▌
    Principle Separate Before Serializing Shared State · painhardcore
    Apply when concurrent actors might write to the same file, branch, key, or state object. Eliminate the sharing first; serialize structurally only when one shared writer is a real invariant.
    22 repo stars
  36. ▌
    Bro 2 · painhardcore
    Use when the user asks to restate or explain the last message in plain, jargon-free language.
    22 repo stars
  37. ▌
    How 2 · painhardcore bundle
    Explain how a subsystem works, trace a runtime flow, or determine where code and ownership belong before making a change.
    22 repo stars
  38. ▌
    Tdd · painhardcore
    Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.
    22 repo stars
  39. ▌
    Why 2 · painhardcore bundle
    Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
    22 repo stars
  40. ▌
    Arena 2 · painhardcore
    Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
    22 repo stars
  41. ▌
    Swarm 2 · painhardcore
    Fan out N independent workers, collect their results, and return one report for coverage, races, gauntlets, or exploration.
    22 repo stars
  42. ▌
    Teach 2 · painhardcore
    Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
    22 repo stars
  43. ▌
    Recall 2 · painhardcore
    Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.
    22 repo stars
  44. ▌
    Blast Radius · painhardcore
    Find what a change could break somewhere else before it ships, beyond the diff, and prove the one fact it's safe because of by running real code instead of writing it up. Use for 'blast radius of X', 'what could this break', or reviewing a small diff you don't trust.
    22 repo stars
  45. ▌
    Technical Writing · painhardcore
    Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
    22 repo stars
  46. ▌
    Principle Build The Lever · painhardcore
    Apply to any non-trivial work, not just bulk work: edits, migrations, analyses, checks. Build the tool that does it or proves it (codemod, script, generator, or a skill your subagents follow) instead of working by hand. The tool is the artifact a reviewer can rerun.
    22 repo stars
  47. ▌
    Principle Experience First · painhardcore
    Apply when product, UX, or feature-scope tradeoffs come up. Choose user delight over implementation convenience; ship fewer polished features over more rough ones.
    22 repo stars
  48. ▌
    Principle Model The Domain · painhardcore
    Apply when writing stateful logic, or when code branches a lot or repeats a shape assumption across files. Encode the domain in a structure instead of scattered conditionals.
    22 repo stars
  49. ▌
    Principle Laziness Protocol · painhardcore
    Apply when refactoring, evaluating diff size, or tempted to add abstractions, layers, or signal threading. Bias toward deletion and the smallest change that solves the problem.
    22 repo stars
  50. ▌
    Principle Boundary Discipline · painhardcore
    Apply when wiring validation, error handling, or framework adapters. Concentrate guards at system boundaries (CLI, config, network, external APIs); trust internal types and keep business logic in pure functions.
    22 repo stars
  51. ▌
    Principle Minimize Reader Load · painhardcore
    Apply when reviewing or shaping code that's hard to trace. Count layers between question and answer, and hidden state in the reader's head; collapse one-caller wrappers and shrink mutable scope.
    22 repo stars
  52. ▌
    Principle Foundational Thinking · painhardcore
    Apply before writing logic: choosing core types and data structures, sequencing scaffold-vs-feature work, asking what concurrent actors share. Get the data structures right so downstream code becomes obvious.
    22 repo stars
  53. ▌
    Principle Subtract Before You Add · painhardcore
    Apply when sequencing an addition, refactor, or rewrite. Remove dead weight, redundant validators, and stub references first, then build on the simpler base.
    22 repo stars
  54. ▌
    Principle Exhaust The Design Space · painhardcore
    Apply when facing a novel UI interaction or architectural decision with no precedent in the codebase. Build 2-3 competing prototypes and compare side by side before committing.
    22 repo stars
  55. ▌
    Principle Sequence Verifiable Units · painhardcore
    Apply to multi-step work (sweeps, migrations, runs of similar edits) and to how you stack commits and PRs. Break work into small units that each end in a verifiable state, check each before the next, and order delivery so the sequence proves itself to a reviewer.
    22 repo stars
  56. ▌
    Bro · painhardcore
    Use when the user asks to restate or explain the last message in plain, jargon-free language.
    22 repo stars
  57. ▌
    Figure It Out · painhardcore
    Design an auditable playbook when no narrower one fits: a large migration, an ambitious multi-part change, or work a human reviews after stepping away. Scales rigor to the task, runs a hypothesis loop, and logs decisions via show-me-your-work. Use for /figure-it-out, 'figure it out', a large migration, or when no narrower playbook applies.
    22 repo stars
  58. ▌
    Principle Type System Discipline · painhardcore
    Apply when designing types, reviewing a function signature, or writing code in any statically-typed language. Make illegal states unrepresentable, brand semantic primitives, parse external data at boundaries, refuse to lie to the compiler, exhaust variants, derive from authoritative schemas.
    22 repo stars
  59. ▌
    How · painhardcore bundle
    Explain how a subsystem works, trace a runtime flow, or determine where code and ownership belong before making a change.
    22 repo stars
  60. ▌
    Why · painhardcore bundle
    Use for 'why does X work this way', 'why we picked Y', design rationale, regressions, postmortems, or data-backed thresholds. Discovers available MCPs and queries each evidence category (source control, issue tracker, long-form docs, real-time chat, infrastructure observability, error tracking, product analytics warehouse) in parallel, then returns a cited read on decisions and tradeoffs. Use how for runtime behavior.
    22 repo stars
  61. ▌
    Arena · painhardcore
    Spawn N parallel candidates at the same task, pick a base, graft the strongest parts of the losers into it. Use for /arena, 'arena this', 'throw it in the arena', or when one attempt at a non-trivial artifact would lock in the wrong shape.
    22 repo stars
  62. ▌
    Swarm · painhardcore
    Fan out N independent workers, collect their results, and return one report for coverage, races, gauntlets, or exploration.
    22 repo stars
  63. ▌
    Teach · painhardcore
    Explain a body of work plainly so a person actually understands it. Runs the `how` and `why` skills and weaves what they find into one clear explanation. Use for 'teach me this', 'help me really understand X', 'explain this change or subsystem to me'.
    22 repo stars
  64. ▌
    Recall · painhardcore
    Reconstruct your recent working context from your own chat history, live state, and the shared record (user reports, prior fixes, incidents), then hand back a tight current-state brief. Use for 'recall my work on X', 'catch me up', 'what have I been working on', 'where did I leave off', before starting or resuming work.
    22 repo stars
  65. ▌
    Unslop · painhardcore
    Cut AI tells from any writing. Must always apply.
    22 repo stars
  66. ▌
    Architect · painhardcore bundle
    Sketch types, signatures, and module structure before code, then stay in the loop while implementation fills in. Use for /architect, 'architect this', 'design this', or non-trivial work where jumping to code would lock in the wrong shape.
    22 repo stars
  67. ▌
    Interrogate · painhardcore bundle
    Use for "interrogate", "adversarial review", "multi-model review", "challenge this", "stress test this code", "find blind spots", or "tear this apart". Multiple LLM reviewers challenge changes from independent angles.
    22 repo stars
  68. ▌
    No Comments · painhardcore
    Use before review when the user asks to strip, remove, or clean up comments in code.
    22 repo stars
  69. ▌
    Poteto Mode · painhardcore bundle
    Apply poteto's rigorous engineering workflow to non-trivial coding, investigation, review, migration, and verification tasks.
    22 repo stars
  70. ▌
    Show Me Your Work · painhardcore bundle
    Keep a reviewable decision trail for long-running or unattended work: a TSV log with one row per decision (what, why, evidence, result). Local by default; commit it when a reviewer needs the trail to trust the result. Use for /show-me-your-work, autonomous or multi-phase runs, or work a human reviews after stepping away.
    22 repo stars
  71. ▌
    Create Verification Skill · painhardcore bundle
    Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform. Use for /create-verification-skill, "make a control skill for this repo", or when a project has no scripted way to prove UI/CLI/service behavior.
    22 repo stars
  72. ▌
    Principle Fix Root Causes · painhardcore
    Apply when debugging. Trace each symptom to its root cause and fix it there; reproduce first, ask why until you reach it, resist nil-check guards that silence crashes.
    22 repo stars
  73. ▌
    Maintain Verification Skill · painhardcore
    Periodic pass that keeps a project's verification skill and feature map honest: parallel source readers per feature, one live session driving every feature, at most one PR of proven corrections. Use for /maintain-verification-skill or "audit the verify skill".
    22 repo stars