dillenberg/ECC
1
0
Fork 0
mirror of https://github.com/Jeuners/ECC.git synced 2026-09-12 08:22:29 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions
ECC/skills
History
Hidai Bar-Mor 0f40fd030c
feat(skills): add evalview-agent-testing skill and MCP server (#828) 
* feat(skills): add evalview-agent-testing skill and MCP server

Add EvalView as a regression testing skill for AI agents. EvalView
snapshots agent behavior (tool calls, parameters, output), then diffs
against baselines after every change — catching regressions before they
ship.

Skill covers:
- CLI workflow (init → snapshot → check → monitor)
- Python API (gate() / gate_async() for autonomous loops)
- Quick mode (no LLM judge, $0, sub-second)
- CI/CD integration (GitHub Actions with PR comments)
- MCP integration (8 tools for Claude Code)
- Multi-turn test cases
- OpenClaw integration for autonomous agents

Also adds evalview MCP server to mcp-servers.json.

* fix(skills): pin action SHA and remove unvetted external links

- Pin hidai25/eval-view action to commit SHA instead of @main
- Replace external GitHub links with PyPI package link (vetted registry)

Addresses cubic-dev-ai review feedback.

* fix(skills): replace third-party action with pip install + CLI

Use plain pip install + evalview CLI instead of a third-party GitHub
Action. No external actions, no secrets passed to unvetted code.

Addresses cubic-dev-ai supply-chain review feedback.

* fix(skills): add destructive revert warning for gate_or_revert

Add prominent warning that gate_or_revert runs git checkout,
discarding uncommitted changes. Documents the revert_cmd override
for safer alternatives like git stash.

Addresses cubic-dev-ai review feedback.

* fix(skills): pin pip version range and document fail-on tradeoffs

- Pin evalview to >=0.5,<1 to prevent breaking CI on major upgrades
- Document --fail-on REGRESSION vs --strict tradeoff so users
  understand what gates and what passes through

Addresses greptile-apps review feedback.

* fix: use python3 -m evalview for venv compatibility in MCP config

Follows the same pattern as insaits entry. Resolves correctly even
when evalview is installed in a virtual environment that isn't on
the system PATH.

* fix: align MCP install command with mcp-servers.json pattern

Use python3 -m evalview mcp serve consistently across both the
skill docs and the MCP config catalog.

* fix: use evalview CLI entry point for MCP command

pip install evalview installs the evalview binary to PATH, so using
it directly is consistent with the install docs and avoids python3
version mismatch issues.

* fix: pin install version to match CI section

* fix: pin all pip install references consistently

* fix: add API key placeholder and pin install version in MCP config

Add OPENAI_API_KEY env placeholder matching other entries. Note that
the key is optional — deterministic checks work without it. Pin
install version to match skill docs.

* fix: guard score_delta format for non-scored statuses

---------

Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
2026-03-31 14:13:32 -07:00
..
agent-eval security: remove supply chain risks, external promotions, and unauthorized credits 2026-03-21 18:10:05 -07:00
agent-harness-construction feat: deliver v1.8.0 harness reliability and parity updates 2026-03-04 14:48:06 -08:00
agent-payment-x402 Update skills/agent-payment-x402/SKILL.md 2026-03-24 15:43:59 -05:00
agentic-engineering feat: deliver v1.8.0 harness reliability and parity updates 2026-03-04 14:48:06 -08:00
ai-first-engineering feat: deliver v1.8.0 harness reliability and parity updates 2026-03-04 14:48:06 -08:00
ai-regression-testing fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
android-clean-architecture fix: address PR review comments for Kotlin/Android/KMP docs 2026-03-10 20:53:39 -07:00
api-design fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
architecture-decision-records feat(skills): add architecture-decision-records skill (#555) 2026-03-20 00:20:25 -07:00
article-writing feat: add generic content and investor skills 2026-02-27 05:50:23 -08:00
autonomous-agent-harness fix: CI fixes, security audit, remotion skill, lead-intelligence, npm audit (#1039) 2026-03-31 15:08:55 -04:00
autonomous-loops security: remove supply chain risks, external promotions, and unauthorized credits 2026-03-21 18:10:05 -07:00
backend-patterns fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
benchmark fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
blueprint docs: tighten blueprint install guidance 2026-03-10 19:23:00 -07:00
browser-qa fix(skills): add missing YAML frontmatter to 7 skills 2026-03-28 20:06:42 -04:00
bun-runtime fix: address PR review — skill template (When to use, How it works, Examples), bun.lock, next build note, rust-reviewer CI note, doc-lookup privacy/uncertainty 2026-03-16 14:03:40 -07:00
canary-watch fix(skills): add missing YAML frontmatter to 7 skills 2026-03-28 20:06:42 -04:00
carrier-relationship-management fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
ck fix: narrow unicode cleanup scope 2026-03-29 21:21:18 -04:00
claude-api feat: add orchestration workflows and harness skills 2026-03-12 14:49:05 -07:00
claude-devfleet Add Claude DevFleet multi-agent orchestration skill (#505) 2026-03-16 13:35:50 -07:00
click-path-audit feat: add click-path-audit skill — finds state interaction bugs (#729) 2026-03-22 15:40:55 -07:00
clickhouse-io fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
codebase-onboarding feat(skills): add codebase-onboarding skill (#553) 2026-03-20 00:20:20 -07:00
coding-standards fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
compose-multiplatform-patterns docs: tighten kotlin support examples 2026-03-10 20:53:39 -07:00
configure-ecc feat: add laravel skills (#420) 2026-03-16 13:35:23 -07:00
content-engine feat: add generic content and investor skills 2026-02-27 05:50:23 -08:00
content-hash-cache-pattern fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
context-budget fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
continuous-agent-loop fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
continuous-learning fix: narrow unicode cleanup scope 2026-03-29 21:21:18 -04:00
continuous-learning-v2 fix(clv2): resolve cwd to git root before project detection 2026-03-30 04:46:31 -04:00
cost-aware-llm-pipeline fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
cpp-coding-standards fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
cpp-testing chore: replace external repo links with @username attribution 2026-03-03 12:32:35 -08:00
crosspost feat: orchestration harness, selective install, observer improvements 2026-03-14 12:55:25 -07:00
customs-trade-compliance fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
data-scraper-agent feat(skill): add data-scraper-agent — AI-powered public data collection for any source (#503) 2026-03-16 13:35:44 -07:00
database-migrations feat(skills): add Kysely migration patterns to database-migrations (#731) 2026-03-22 15:40:53 -07:00
deep-research feat: add orchestration workflows and harness skills 2026-03-12 14:49:05 -07:00
deployment-patterns fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
design-system fix(skills): add missing YAML frontmatter to 7 skills 2026-03-28 20:06:42 -04:00
django-patterns fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
django-security fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
django-tdd fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
django-verification fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
dmux-workflows security: remove supply chain risks, external promotions, and unauthorized credits 2026-03-21 18:10:05 -07:00
docker-patterns fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
documentation-lookup fix: address PR review — skill template (When to use, How it works, Examples), bun.lock, next build note, rust-reviewer CI note, doc-lookup privacy/uncertainty 2026-03-16 14:03:40 -07:00
e2e-testing fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
energy-procurement fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
enterprise-agent-ops feat: deliver v1.8.0 harness reliability and parity updates 2026-03-04 14:48:06 -08:00
eval-harness feat: deliver v1.8.0 harness reliability and parity updates 2026-03-04 14:48:06 -08:00
evalview-agent-testing feat(skills): add evalview-agent-testing skill and MCP server (#828) 2026-03-31 14:13:32 -07:00
exa-search feat: orchestration harness, selective install, observer improvements 2026-03-14 12:55:25 -07:00
fal-ai-media feat: orchestration harness, selective install, observer improvements 2026-03-14 12:55:25 -07:00
flutter-dart-code-review feat(agents): add flutter-reviewer agent and skill (#716) 2026-03-20 06:40:28 -07:00
foundation-models-on-device fix(skills): improve code examples in iOS 26 skills 2026-02-24 14:39:25 +09:00
frontend-patterns fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
frontend-slides chore: replace external repo links with @username attribution 2026-03-03 12:32:35 -08:00
gan-style-harness feat: add GAN-style generator-evaluator harness (#1029) 2026-03-31 14:06:20 -07:00
git-workflow fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
golang-patterns fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
golang-testing fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
healthcare-cdss-patterns fix: address Greptile review — frontmatter, CI safety, null guards 2026-03-27 04:02:44 +00:00
healthcare-emr-patterns fix: address Greptile review — frontmatter, CI safety, null guards 2026-03-27 04:02:44 +00:00
healthcare-eval-harness fix(docs): repair healthcare eval harness examples 2026-03-29 00:04:36 -04:00
healthcare-phi-compliance fix: address Greptile review — frontmatter, CI safety, null guards 2026-03-27 04:02:44 +00:00
hexagonal-architecture feat: add hexagonal architecture SKILL. (#1034) 2026-03-31 14:05:27 -07:00
inventory-demand-planning fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
investor-materials feat: add generic content and investor skills 2026-02-27 05:50:23 -08:00
investor-outreach feat: add generic content and investor skills 2026-02-27 05:50:23 -08:00
iterative-retrieval fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
java-coding-standards fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
jpa-patterns fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
kotlin-coroutines-flows docs: tighten kotlin support examples 2026-03-10 20:53:39 -07:00
kotlin-exposed-patterns feat: add kotlin commands and skill pack 2026-03-10 21:25:52 -07:00
kotlin-ktor-patterns feat: add kotlin commands and skill pack 2026-03-10 21:25:52 -07:00
kotlin-patterns feat: add kotlin commands and skill pack 2026-03-10 21:25:52 -07:00
kotlin-testing fix: align kotlin diagnostics and heading hierarchy 2026-03-12 23:53:23 -07:00
laravel-patterns feat: add laravel skills (#420) 2026-03-16 13:35:23 -07:00
laravel-plugin-discovery fix(skills): align laravel plugin discovery docs 2026-03-28 20:41:45 -04:00
laravel-security feat: add laravel skills (#420) 2026-03-16 13:35:23 -07:00
laravel-tdd feat: add laravel skills (#420) 2026-03-16 13:35:23 -07:00
laravel-verification fix(skills): add missing YAML frontmatter to 7 skills 2026-03-28 20:06:42 -04:00
lead-intelligence fix: CI fixes, security audit, remotion skill, lead-intelligence, npm audit (#1039) 2026-03-31 15:08:55 -04:00
liquid-glass-design fix(skills): improve code examples in iOS 26 skills 2026-02-24 14:39:25 +09:00
logistics-exception-management fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
market-research feat: add generic content and investor skills 2026-02-27 05:50:23 -08:00
mcp-server-patterns feat(skills): add mcp-server-patterns (#531) 2026-03-16 13:35:11 -07:00
nanoclaw-repl feat: deliver v1.8.0 harness reliability and parity updates 2026-03-04 14:48:06 -08:00
nextjs-turbopack fix: address PR review — skill template (When to use, How it works, Examples), bun.lock, next build note, rust-reviewer CI note, doc-lookup privacy/uncertainty 2026-03-16 14:03:40 -07:00
nutrient-document-processing security: remove supply chain risks, external promotions, and unauthorized credits 2026-03-21 18:10:05 -07:00
nuxt4-patterns feat: add nuxt 4 patterns skill (#702) 2026-03-20 04:44:31 -07:00
openclaw-persona-forge fix(skills): harden openclaw persona forge 2026-03-30 04:41:47 -04:00
opensource-pipeline feat(agents,skills): add opensource-pipeline — 3-agent workflow for safe public releases (#1036) 2026-03-31 14:06:23 -07:00
perl-patterns docs: tighten perl support guidance 2026-03-10 20:42:54 -07:00
perl-security docs: tighten perl support guidance 2026-03-10 20:42:54 -07:00
perl-testing feat: add Perl skills (patterns, security, testing) 2026-03-10 20:42:54 -07:00
plankton-code-quality security: remove supply chain risks, external promotions, and unauthorized credits 2026-03-21 18:10:05 -07:00
postgres-patterns chore: replace external repo links with @username attribution 2026-03-03 12:32:35 -08:00
product-lens fix(skills): add missing YAML frontmatter to 7 skills 2026-03-28 20:06:42 -04:00
production-scheduling fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
project-guidelines-example fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
prompt-optimizer feat(skills): add prompt-optimizer skill and /prompt-optimize command (#418) 2026-03-12 23:40:02 -07:00
python-patterns fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
python-testing fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
pytorch-patterns feat(skills): add pytorch-patterns skill (#550) 2026-03-19 20:49:34 -07:00
quality-nonconformance fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
ralphinho-rfc-pipeline feat: deliver v1.8.0 harness reliability and parity updates 2026-03-04 14:48:06 -08:00
regex-vs-llm-structured-text fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
remotion-video-creation fix: CI fixes, security audit, remotion skill, lead-intelligence, npm audit (#1039) 2026-03-31 15:08:55 -04:00
repo-scan fix(skills): tighten repo-scan install flow 2026-03-28 20:29:51 -04:00
returns-reverse-logistics fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
rules-distill fix: narrow unicode cleanup scope 2026-03-29 21:21:18 -04:00
rust-patterns fix: resolve Windows CI failures and markdown lint (#667) 2026-03-20 00:29:17 -07:00
rust-testing feat(agents): add Rust language support (#523) 2026-03-16 13:34:25 -07:00
safety-guard fix(skills): add missing YAML frontmatter to 7 skills 2026-03-28 20:06:42 -04:00
santa-method feat(skills): add santa-method - multi-agent adversarial verification (#760) 2026-03-22 15:41:04 -07:00
search-first feat: separate core vs niche skills and enforce research-first default 2026-02-28 10:06:43 -08:00
security-review fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
security-scan fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
skill-comply feat(skills): add skill-comply — automated behavioral compliance measurement (#724) 2026-03-22 21:51:49 -07:00
skill-stocktake fix: narrow unicode cleanup scope 2026-03-29 21:21:18 -04:00
social-graph-ranker fix: CI fixes, security audit, remotion skill, lead-intelligence, npm audit (#1039) 2026-03-31 15:08:55 -04:00
springboot-patterns fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
springboot-security fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
springboot-tdd fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
springboot-verification fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
strategic-compact fix: narrow unicode cleanup scope 2026-03-29 21:21:18 -04:00
swift-actor-persistence fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
swift-concurrency-6-2 fix(skills): improve code examples in iOS 26 skills 2026-02-24 14:39:25 +09:00
swift-protocol-di-testing fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
swiftui-patterns fix: correct SwiftUI skill ViewModel injection and Equatable comparison 2026-02-17 17:04:31 +02:00
tdd-workflow fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
team-builder feat(team-builder): use claude agents command for agent discovery (#1021) 2026-03-31 14:05:20 -07:00
token-budget-advisor fix(skills): clarify token-budget-advisor triggers 2026-03-29 00:20:04 -04:00
verification-loop fix: add origin metadata to skills for traceability 2026-02-23 19:00:57 +03:00
video-editing feat: add orchestration workflows and harness skills 2026-03-12 14:49:05 -07:00
videodb fix: narrow unicode cleanup scope 2026-03-29 21:21:18 -04:00
visa-doc-translate fix: harden unicode safety checks 2026-03-29 21:21:18 -04:00
x-api fix: harden orchestration status and skill docs 2026-03-12 15:07:57 -07:00