Menu
SkillsMP a collecté 54 skills depuis Archive228/loopkit. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 54.
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.
Langue du texte source : anglais
Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.
Langue du texte source : anglais
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…
Langue du texte source : anglais
Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so feature_list.json stays immutable
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Calibrate a reviewer persona with few-shot rubric examples so skepticism stays consistent and doesn't drift lenient over long runs.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Systematically remove one harness component at a time and measure impact, killing scaffolding that no longer earns its complexity.
Langue du texte source : anglais
Author idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on.
Langue du texte source : anglais
Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Verify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.
Langue du texte source : anglais
Keep the agent's context lean so accuracy doesn't collapse. Use on long sessions, big files, or when the agent starts hallucinating.
Langue du texte source : anglais
Test the boundary between two systems by the contract, not the implementation. Use for APIs, integrations, and shared interfaces.
Langue du texte source : anglais
Validate and constrain untrusted input at the boundary. Use on any handler that accepts external data.
Langue du texte source : anglais
Design the three states every data UI forgets. Use for any component that fetches or lists data.
Langue du texte source : anglais
Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.
Langue du texte source : anglais
Flatten deeply nested conditionals into readable, early-return code. Use on any function with 3+ levels of indentation.
Langue du texte source : anglais
Undo a bad change without nuking unrelated work. Use when a specific commit or change broke something.
Langue du texte source : anglais
Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.
Langue du texte source : anglais
Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
Langue du texte source : anglais
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.
Langue du texte source : anglais
Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.
Langue du texte source : anglais
Turn a set of commits or a diff into a clean, user-facing changelog entry. Use before a release or PR description.
Langue du texte source : anglais
Turn messy WIP into clean, atomic commits with messages that explain why. Use before opening a PR.
Langue du texte source : anglais
Find the untested code paths that actually matter, not just the coverage percentage. Use after adding tests.
Langue du texte source : anglais
Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.
Langue du texte source : anglais
Decide whether to add, keep, or remove a dependency. Use before adding any package.
Langue du texte source : anglais