bg-szy/TOP-SKILLS / skills/agent-skills/agentic-eval
agentic-eval
VerifiedEvaluate and improve AI-generated output with explicit rubrics, reflection loops, and stop conditions. Use when building self-critique workflows, evaluator-optimizer pipelines, or acceptance gates for code, docs, analysis, or plans.
| File | Kind | Size |
|---|---|---|
| CHANGELOG.md | markdown | 6.1 KB |
| SKILL.md | skill md | 8.3 KB |
CHANGELOG.md
View on GitHub# Changelog
## [2026-09-08] - Catalog Freshness And Source Sync
### Added
- Refreshed the catalog metadata and retained-client portability baseline.
### Changed
- Updated the catalog metadata and last-updated state for the 2026-09-08 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
### Fixed
- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.
## [2026-09-05] - Catalog Freshness And Source Sync
### Added
- Refreshed the catalog metadata and retained-client portability baseline.
### Changed
- Updated the catalog metadata and last-updated state for the 2026-09-05 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
### Fixed
- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.
## [2026-08-31] - Catalog Freshness And Source Sync
### Added
- Refreshed the catalog metadata and retained-client portability baseline.
### Changed
- Updated the catalog metadata and last-updated state for the 2026-08-31 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
### Fixed
- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.
## [2026-08-29] - Catalog Freshness And Source Sync
### Added
- Refreshed the catalog metadata and retained-client portability baseline.
### Changed
- Updated the catalog metadata and last-updated state for the 2026-08-29 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
### Fixed
- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.
## [2026-08-24] - Catalog Freshness And Source Sync
### Added
- Refreshed the catalog metadata and retained-client portability baseline.
### Changed
- Updated the catalog metadata and last-updated state for the 2026-08-24 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
### Fixed
- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.
## [2026-08-14] - Catalog Freshness And Source Sync
### Added
- Refreshed the catalog metadata and retained-client portability baseline.
### Changed
- Updated the catalog metadata and last-updated state for the 2026-08-14 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
### Fixed
- Preserved explicit no-MCP fallbacks and the catalog's safety, approval, and source-boundary guidance.
## [2026-07-29] - Version 2.0 Client Support Reset
### Added
- Added the current GitHub Copilot, Claude Code, and Codex portability baseline.
### Changed
- **BREAKING:** Removed Gemini CLI and Antigravity as supported clients.
- Refreshed catalog metadata and last-updated state for the 2026-07-29 maintenance pass.
- Kept the retained-client portability, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
### Fixed
- Prevented catalog modernization from reintroducing removed Gemini or Antigravity guidance.
## [2026-07-11] - Catalog Maintenance Refresh
### Added
- Added the current catalog verification baseline where it was missing.
### Changed
- Refreshed catalog metadata and last-updated state for the 2026-07-11 maintenance pass.
- Kept the cross-client, MCP fallback, Anti-Patterns, Verification Protocol, and Related Skills sections aligned.
- Reclassified historical `Tested` or `Verified` changelog headings under the allowed changelog vocabulary without dropping their evidence.
### Fixed
- Closed validator and documentation drift so the enforced schema matches the documented skill baseline.
## [2026-04-25] - Version 1.2 Verification Protocol Refresh
### Added
- Added a `Verification Protocol` section with skill-specific pass/fail checks, one pressure-test scenario, and a measurable success metric.
- Added guidance to leverage native parallel subagent dispatch and 200k+ context windows where available.
### Changed
- Updated `SKILL.md` frontmatter to `version: "1.2"` and `last_updated: 2026-04-25`.
- Reframed activation guidance toward symptom -> action triggers and standardized two-stage review wording where applicable.
## [2026-04-24] - Version 1.1 Refresh
### Changed
- Updated the SKILL frontmatter version to `1.1` for the 2026-04-24 catalog refresh.
## [2026-04-24] - Post-Refresh Cleanup
### Fixed
- Renamed the self-check section to explicit phase-gate questions so completion criteria are clearer for evaluator agents.
## [2026-04-24] - Skill Refresh
### Changed
- Standardized the SKILL frontmatter with version metadata, last-updated date, tags, and a concise catalog description.
- Reformatted the portability and MCP guidance with a preferred server line, a copy-paste fallback prompt, and consistent bullet lists.
- Added a catalog-standard Anti-Patterns section and refreshed the Related Skills links at the end of the skill.
- Added a self-verification phase gate so evaluators must ask evidence-backed completion questions before passing work.
## [2026-04-04] - Initial Import and Catalog Upgrade
### Added
- Imported `agentic-eval` from the `awesome-copilot` reference catalog into the canonical maintained workspace
- Reframed the skill around repeatable rubric design, evidence-based evaluation, and stop conditions
- Added `references/rubric-template.json`, `references/example-scores.json`, and `scripts/rubric-scorecard.py` so the workflow can be exercised locally across clients
### Changed
- Ran `python agentic-eval/scripts/rubric-scorecard.py --rubric agentic-eval/references/rubric-template.json --scores agentic-eval/references/example-scores.json --threshold 0.8`
- Planned validation through `python scripts/validate-skills.py`
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| writing-skillsobra/superpowersUse when creating new skills, editing existing skills, or verifying skills work before deployment | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| xlsxanthropics/skillsUse this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .xltx, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting, cleaning messy data); create a new spreadsheet from scratch or from other data sources; or convert between tabular file formats. Trigger especially when the user references a spreadsheet file by name or path — even casually (like "the xlsx in my downloads") — and wants something done to it or produced from it. Also trigger for cleaning or restructuring messy tabular data files (malformed rows, misplaced headers, junk data) into proper spreadsheets. The deliverable must be a spreadsheet file. Do NOT trigger when the primary deliverable is a Word document, HTML report, standalone Python script, database pipeline, or Google Sheets API integration, even if tabular data is involved. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| shipping-and-launchaddyosmani/agent-skillsPrepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy. | Stars: 119k | Updated | Claude CodeCodex | Verified | Install |
| childhoodthedotmack/claude-memBabysit a shipped release after merge, publication, or deployment. Verify published packages, production behavior, installed plugins, and late CI or user reports until the observation window is clean; use babysit for PR readiness before release. | Stars: 118k | Updated | Claude CodeCodex | Verified | Install |