quality-evaluation
Run and interpret the project's quality matrix after correctness and route gates are closed.
Skill by linjuhon
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/linjuhon-quality-evaluation
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/quality-evaluation
What's inside
- Skill name
quality-evaluation- Description
- Run and interpret the project's quality matrix after correctness and route gates are closed. Use for paired quality checks, repeatability, and regression evidence.
- License
- MIT
- Instructions
- 32 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# quality-evaluation Use this skill only when the active gate names a quality comparison. ## Responsibilities - verify the accepted model, workload, and baseline identity - run the required quality matrix and repetitions - separate quality failure from environment or identity failure - package observations for gate adjudication ## Required Output - workload and baseline identity - command and repetition count - observed quality metrics - variance or repeatability result - first failure and next action ## Hard Rules - Do not run quality before correctness and route prerequisites are PASS. - Do not call one successful sample a matrix PASS. - Do not change the metric or threshold to fit the result. ## Entry And Return Read `CURRENT_PLAN`, the active gate card, and the accepted workload matrix. Return raw result paths and an evidence-ready summary; gate status remains the active gate's responsibility.
From linjuhon/codex-personal-skills, MIT.
More from linjuhon/codex-personal-skills
- 0.524score
ask-matt
linjuhon
Choose one skill or workflow for a task across personal, Matt Pocock, Codex, and plugin capabilities.
SkillBFreshness: BClaude Code +9 - 0.524score
documentation-organization
linjuhon
Organize project documentation into a clear authoritative structure, classify source documents, preserve traceability, and create indexes or handoff maps.
SkillBFreshness: BClaude Code +9 - 0.524score
oracle-validation
linjuhon
Compare runtime or kernel output with the project oracle, isolate the first divergence, and produce an evidence-ready verdict.
SkillBFreshness: BClaude Code +9 - 0.524score
patch-decomposition
linjuhon
Decompose fork-versus-base changes into one reviewable plugin patch with hunk ownership, dependencies, activation boundaries, verification, and rollback…
SkillBFreshness: BClaude Code +9 - 0.524score
upstream-rebase
linjuhon
Rebase an accepted, dependency-ordered patch onto an already locked upstream revision with conflict, verification, and rollback evidence.
SkillBFreshness: BClaude Code +9 - 0.521score
cuda-kernel-debug
linjuhon
Narrow a CUDA kernel correctness failure to the first failing coordinate and one semantic owner using minimal probes.
SkillBFreshness: BClaude Code +9 - 0.521score
route-evidence
linjuhon
Route multi-step correctness, quality, performance, release, or upstream-integration evidence work when the next gate is unclear.
SkillBFreshness: BClaude Code +9 - 0.521score
evidence-packaging
linjuhon
Package completed bounded execution output into one evidence claim with identity, observations, limitations, and receipt.
SkillBFreshness: BClaude Code +9 - 0.521score
git-worktree-protection
linjuhon
Protect dirty worktrees and narrow file ownership during execution, evidence archival, and cleanup.
SkillBFreshness: BClaude Code +9 - 0.521score
route-operations
linjuhon
Route multi-step document, artifact, browser, GitHub, Gmail, website, or image operations when the correct managed capability or write authorization is unclear.
SkillBFreshness: BClaude Code +9 - 0.521score
route-planning
linjuhon
Route multi-step planning, research, design decisions, specifications, and ticketing when the next planning skill is unclear.
SkillBFreshness: BClaude Code +9 - 0.521score
route-diagnostics
linjuhon
Route multi-step bug, regression, CI, CUDA, or performance diagnosis when failure isolation requires choosing a method.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 8, 2026 (2 months ago)
- Last release
- Aug 8, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from linjuhon
- 0.524score
oracle-validation
linjuhon
Compare runtime or kernel output with the project oracle, isolate the first divergence, and produce an evidence-ready verdict.
SkillBFreshness: BClaude Code +9 - 0.524score
upstream-rebase
linjuhon
Rebase an accepted, dependency-ordered patch onto an already locked upstream revision with conflict, verification, and rollback evidence.
SkillBFreshness: BClaude Code +9 - 0.524score
ask-matt
linjuhon
Choose one skill or workflow for a task across personal, Matt Pocock, Codex, and plugin capabilities.
SkillBFreshness: BClaude Code +9 - 0.524score
documentation-organization
linjuhon
Organize project documentation into a clear authoritative structure, classify source documents, preserve traceability, and create indexes or handoff maps.
SkillBFreshness: BClaude Code +9 - 0.524score
patch-decomposition
linjuhon
Decompose fork-versus-base changes into one reviewable plugin patch with hunk ownership, dependencies, activation boundaries, verification, and rollback…
SkillBFreshness: BClaude Code +9 - 0.521score
cuda-kernel-debug
linjuhon
Narrow a CUDA kernel correctness failure to the first failing coordinate and one semantic owner using minimal probes.
SkillBFreshness: BClaude Code +9
Cite this page
quality-evaluation skill. Agent Mart. https://agentmart.dev/skills/linjuhon-quality-evaluation (last updated 2026-10-24)