Skip to content

hassan-mohiddin/freeflow / .deprecated/skill-tooling-pre-rewrite/skills/evaluate-skill

evaluate-skill

Verified

Use when evaluating, comparing, or making readiness claims about agent-skill behavior.

references/grading-priority.md

View on GitHub
# Grading Priority

Use the strongest available evidence:

1. Filesystem state, before/after manifests, diff, created/deleted paths, and git state.
2. Command output, exit codes, structured events, tool calls, logs, traces, and saved reports.
3. Final response.
4. Full transcript when the earlier surfaces cannot explain the result.
5. Agent self-assessment.

Lower-priority evidence cannot repair a contradiction above it.

## Deterministic First

Use mechanical checks for paths, content, JSON fields, frontmatter, line counts, events, activation reads, exit status, usage, and protocol fields.

Use fresh model or human judgment for reasoning quality, user-authority preservation, architectural fitness, recommendation quality, and semantic completeness.

Semantic grading cannot turn a failed objective assertion into a pass.

## Evidence Labels

Record unavailable fields explicitly. Do not convert missing cost to zero, injected wording to native activation, or a one-shot conversation to multi-turn proof.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall