← all publishers

archive228

@archive228 source repo

54 published skills

  1. Spec First · archive228
    Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.
    0
    installs
  2. SQL Review · archive228
    Review SQL and ORM queries for correctness, safety, and performance before they ship.
    0
    installs
  3. Pr From Diff · archive228
    Write a PR description a reviewer can approve fast. Use when opening any pull request.
    0
    installs
  4. Context Budget · archive228
    Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.
    0
    installs
  5. Read The Trace · archive228
    Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.
    0
    installs
  6. My New Skill · archive228 bundle
    One sentence that describes WHEN to invoke this skill. Write it as a trigger phrase, not a summary — include the words a user would say ("fix bug", "add feature", "review diff"). The agent routes on this field.
    0
    installs
  7. Simplify · archive228
    Reduce a change to the minimum that solves the problem. Use when code is over-engineered or a diff is bloated.
    0
    installs
  8. A11Y Pass · archive228
    Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
    0
    installs
  9. Authz Check · archive228
    Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.
    0
    installs
  10. Schema Diff · archive228
    Compare two schema states and surface the risky changes. Use before applying migrations or after a model change.
    0
    installs
  11. Secret Scan · archive228
    Catch hardcoded secrets, keys, and tokens before they get committed. Use before any commit and on any file with credentials.
    0
    installs
  12. Shift Notes · archive228
    Write and read the between-session handoff file so a fresh agent with no memory can pick up where the last one stopped without re-deriving context. Structured prose, not JSON — the model writes prose better.
    0
    installs
  13. Eval Harness · archive228
    Build a repeatable eval loop that grades agent output with an LLM judge, so prompt/skill changes get scored against a baseline instead of eyeballed. Reuses loopkit's verifier subagent as the grader — do not build a new one.
    0
    installs
  14. Flaky Hunter · archive228
    Diagnose and fix tests that pass sometimes and fail other times. Use when CI is red intermittently.
    0
    installs
  15. Owasp Review · archive228
    Security-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.
    0
    installs
  16. Readme Audit · archive228
    Check whether a README actually lets a stranger run the project. Use on any repo's README before publishing.
    0
    installs
  17. Clean Commits · archive228
    Turn messy WIP into clean, atomic commits with messages that explain why. Use before opening a PR.
    0
    installs
  18. Contract Test · archive228
    Test the boundary between two systems by the contract, not the implementation. Use for APIs, integrations, and shared interfaces.
    0
    installs
  19. Coverage Gaps · archive228
    Coverage Gaps
    0
    installs
  20. Design System · archive228
    Make frontend output look intentional, not AI-generated. Use for any UI work — components, pages, layouts.
    0
    installs
  21. Hitl Escalate · archive228
    Escalate blocked runs to a human via configured channel or fallback to BLOCKED.md and exit the loop. Use when the loop hits an ambiguous spec, a missing credential, a destructive action needing approval, or 3+ consecutive verify failures on the same task.
    0
    installs
  22. Model Routing · archive228
    Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.
    0
    installs
  23. PDF Ingestion · archive228
    Get a PDF into the model without blowing the context window or losing structure. Native PDF beats OCR-then-text for most cases; extract-then-summarize beats native for very long docs.
    0
    installs
  24. Rebase Safely · archive228
    Rebase, squash, or rewrite history without losing work or breaking shared branches. Use before any history rewrite.
    0
    installs
  25. Using Loopkit · archive228
    Use when starting any conversation in a loopkit-enabled project - establishes how to find and use loopkit's 49 skills, requiring skill invocation before ANY response including clarifying questions.
    0
    installs
  26. Kill Dead Code · archive228
    Find and remove unreachable/unused code safely. Use during cleanup or before a refactor.
    0
    installs
  27. Prompt Caching · archive228
    Cache the parts of the prompt that don't change so a long-running loop stops paying full price on every turn. Use when the system prompt, tool defs, or reference docs are stable across many turns.
    0
    installs
  28. Reduce Nesting · archive228
    Flatten deeply nested conditionals into readable, early-return code. Use on any function with 3+ levels of indentation.
    0
    installs
  29. Self Eval Bias · archive228
    Detect and interrupt the pattern where an agent confidently praises work it just produced instead of reviewing it critically. Same-context grading is not review — it's rationalization.
    0
    installs
  30. Tool Restraint · archive228
    Don't over-equip an agent with tools/MCP servers. More tools = more ways to fail and a higher cognitive load. Use when wiring tools or an agent underperforms.
    0
    installs
  31. Decision Record · archive228
    Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.
    0
    installs
  32. Revert Surgical · archive228
    Surgical Revert
    0
    installs
  33. Sprint Contract · archive228
    Negotiate a pre-code contract between generator and evaluator personas that defines what "done" means before any code is written. Turns fuzzy specs into a testable target the evaluator can hold the generator to.
    0
    installs
  34. Subagent Fanout · archive228
    Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.
    0
    installs
  35. Dependency Audit · archive228
    Decide whether to add, keep, or remove a dependency. Use before adding any package.
    0
    installs
  36. Input Validation · archive228
    Validate and constrain untrusted input at the boundary. Use on any handler that accepts external data.
    0
    installs
  37. Migration Writer · archive228
    Write safe, reversible database migrations for this repo's conventions. Use for any schema change.
    0
    installs
  38. Bisect Regression · archive228
    Bisect the Regression
    0
    installs
  39. Feature List JSON · archive228
    Enumerate every end-to-end feature as strict JSON entries with passes:false, editable-passes-only discipline, and priority order. The ledger fresh-context sessions read to know what's done, what's next, and what they're forbidden to touch.
    0
    installs
  40. Harness Stripping · archive228
    Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.
    0
    installs
  41. Structured Output · archive228
    Get JSON out of the model reliably. Prefer tool_use with a schema over prompted-JSON, validate on receive, retry on parse fail. Use when downstream code will parse the response.
    0
    installs
  42. Adversarial Verify · archive228
    Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.
    0
    installs
  43. Broken Window Check · archive228
    Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.
    0
    installs
  44. Changelog From Diff · archive228
    Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.
    0
    installs
  45. Planner Spec Expand · archive228
    Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.
    0
    installs
  46. Init Script Contract · archive228
    Author idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on.
    0
    installs
  47. Systematic Debugging · archive228
    Use for ANY bug, test failure, crash, or unexpected behavior. Forces reproduce-then-isolate before proposing a fix. Stops the agent from guessing.
    0
    installs
  48. Evaluator Calibration · archive228
    Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.
    0
    installs
  49. Suggest Next Features · archive228
    Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so feature_list.json stays immutable
    0
    installs
  50. Active Memory Reminder · archive228
    Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.
    0
    installs
  51. Write Failing Test First · archive228
    Before fixing any bug, write a test that reproduces it and watch it fail. Use for every bug fix.
    0
    installs
  52. Progress Reading Protocol · archive228
    Run the fixed 6-step session-opening sequence — pwd, read progress, git log, count remaining features, init.sh, smoke-test last feature — before touching any new work. The orientation ritual that lets fresh-context sessions reconstruct project state in under a minute.
    0
    installs
  53. Loading Empty Error States · archive228
    Design the three states every data UI forgets. Use for any component that fetches or lists data.
    0
    installs
  54. Verification Before Completion · archive228
    Use before claiming work is complete, fixed, or passing — before committing, opening a PR, or handing off. Requires running the verification command in THIS turn and reading its output before any success claim.
    0
    installs