trace-codes
De la autor
Turn free-form notes from reading agent traces into trace codes: named, yes/no failure or quality patterns with definitions, examples and counts. Use this skill whenever someone has annotated traces or review notes and asks to "cluster my notes", "create trace codes", "find the failure modes", "do error analysis on these annotations", "what patterns are in these traces", or "what should we fix first". Also use to merge new notes into an existing set of codes. Output is a trace codes file, a labeling sheet for human review, and proposed rubric updates.
Instalare
npx skills add Calibre-Labs/reforge-ai-evals --skill trace-codes -a claude-code
Se instalează în .claude/skills/trace-codes/ · Fiecare comandă descarcă skill-ul direct de pe GitHub cu utilitarul open source skills.
Identic octet cu octet cu commit-ul scanat, cu licența depozitului și un fișier SOURCE.txt.
Vrei ca agentul să-ți propună skill-uri în timp ce scrii? Vezi cum folosești skill-urile din IDE.
Verificări de siguranță pe SKILL.md
Niciun avertisment.
De ce 83
aiqbench calculează scorul de încredere din semnale publice. Nu este un audit de securitate, așa că citește un skill înainte să-l instalezi.
Skill-uri similare
Cele mai apropiate de acesta prin ce fac și când sunt folosite.
- trace-review-appCalibre-Labs/reforge-ai-evalsDesign and build a custom trace review app for one AI product: a single-page tool where the team reads traces, writes notes, labels pass or fail, tags trace codes and exports the results for other skills. Built around that product's own trace shape, rubric and failure modes, and set up so reviewing becomes a habit (a queue, progress, streaks, quick keys). Use this skill whenever someone asks to "build a trace viewer", "make an annotation tool", "set up a review page for our traces", "make trace review less painful", "build a labeling app", or says the team isn't reading traces because the tool is clunky.Inginerie★ 85
- taste-code-reviewmadebymustafa/design-tasteStructured review of agent-generated code: a fixed pass order (behavior → structure → taste → security → performance → accessibility), severity-ranked findings, diff discipline, and a review checklist that stops "it works" from being the bar. Use when auditing any generated or changed code. Stack on the design-taste core skill.Inginerie★ 196
- review-codetobihagemann/turboReview code for bugs, security vulnerabilities, API misuse, consistency issues, simplicity problems, or test coverage gaps and low-value tests by running internal reviews and a peer review in parallel and returning combined findings. Single-concern with a type argument, or full review with no argument. Use when the user asks to "review my code", "full code review", "review my changes", "check for bugs", "scan for bugs", "review correctness", "security audit", "find vulnerabilities", "review security", "check API usage", "verify against docs", "check for cross-file duplication", "review consistency", "check for code reuse", "review simplicity", "find untested code", "find redundant tests", or "review test coverage".Inginerie★ 416
- trace-debugtonone-ai/tononeDebug AI system behavior using traces — prompt reconstruction, output comparison, failure attribution. Use when asked "why did the model output this", "debug this LLM failure", or "reconstruct the prompt".Inginerie★ 76
- refactoring-patternswondelai/skillsApply named refactoring transformations to improve code structure without changing behavior. Use when the user mentions "refactor this", "code smells", "extract method", "replace conditional", "technical debt", "move method", "inline variable", "decompose conditional", or "clean up this messy code". Also trigger when cleaning up legacy code, preparing code for new features by restructuring, or identifying which transformation fits a specific code smell. Covers smell-driven refactoring, safe transformation sequences, and testing guards. For code-quality foundations, see clean-code. For managing complexity, see software-design-philosophy.Inginerie★ 2.5K
- make-traceAIScientists-Dev/FlowtraceTurn any source that describes how a kind of task gets done (a SKILL.md, a chat log, a runbook, plain prose) into a runnable Morph trace. Lift it into a DAG, write a contract per step, place inputs, and drive the full run lifecycle to verify it. Use whenever someone wants to make a trace from a source.Juridic★ 484
Note și recenzii
—
nicio recenzie
Ai încercat acest skill? Notează-l ca să-i ajuți pe alții. Autentifică-te
Discuție
Intră în discuție. Autentifică-te