54 skills (repositories by Archive228) · sorted by popularity
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.
The English summary is being prepared. Showing the original description.
Check whether a README actually lets a stranger run the project. Use on any repo's README before publishing.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Reduce a change to the minimum that solves the problem. Use when code is over-engineered or a diff is bloated.
The English summary is being prepared. Showing the original description.
Parallelize independent sub-jobs across fresh-context subagents instead of one bloated context. Use when a goal branches into many independent pieces.
The English summary is being prepared. Showing the original description.
Read git log since initial scaffold + last 3 progress notes, draft feature additions to a SEPARATE suggestions file so feature_list.json stays immutable
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Author idempotent init.sh under 120s plus sibling test.sh, stop.sh, reset.sh, serve.sh with fixed names the harness relies on.
The English summary is being prepared. Showing the original description.
Extract the actual cause from a stack trace instead of pattern-matching the error type. Use on any crash or exception.
The English summary is being prepared. Showing the original description.
Capture an architectural decision so the next session (or engineer) knows WHY. Use after any non-obvious technical choice.
The English summary is being prepared. Showing the original description.
Security-review a diff against the OWASP Top 10. Use before merging anything that touches auth, input handling, queries, or external calls.
The English summary is being prepared. Showing the original description.
Flatten deeply nested conditionals into readable, early-return code. Use on any function with 3+ levels of indentation.
The English summary is being prepared. Showing the original description.
Write the goal spec on disk before the agent acts, so it can't drift. Use before any multi-step task.
The English summary is being prepared. Showing the original description.
Review SQL and ORM queries for correctness, safety, and performance before they ship.
The English summary is being prepared. Showing the original description.
Use for ANY bug, test failure, crash, or unexpected behavior. Forces reproduce-then-isolate before proposing a fix. Stops the agent from guessing.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Compare two schema states and surface the risky changes. Use before applying migrations or after a model change.
The English summary is being prepared. Showing the original description.
Rebase, squash, or rewrite history without losing work or breaking shared branches. Use before any history rewrite.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Catch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Expand a 1-4 sentence product brief into a full spec with a design language, acceptance surface, and an ordered feature list.
The English summary is being prepared. Showing the original description.
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.
The English summary is being prepared. Showing the original description.
Undo a bad change without nuking unrelated work. Use when a specific commit or change broke something.
The English summary is being prepared. Showing the original description.