aliatx2017/reasonix-hermes/ready-means-tested

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Nothing is ready until end-to-end tested with real evidence. Blocks DONE/READY/LIVE claims without build output in the same response.

Install

npx vskill@latest install aliatx2017/reasonix-hermes/ready-means-tested

SKILL.md

Ready Means Tested

One rule, one gate, one evidence chain.

Rule

No change is ready unless end-to-end verified with real evidence in the same response. Code inspection, "it compiles," "the tests pass locally" — these do not qualify. Show the tool output.

"Fixed" is a banned word — only the user declares something fixed. Say "should be resolved" or "try it."

Gate

Must pass all before claiming a step is done:

  1. go build ./... — clean
  2. go vet ./... — clean
  3. go test ./... for affected packages — pass
  4. cd desktop/frontend && npx tsc --noEmit for desktop changes — clean
  5. Show the output in the same response

If any step fails, the step is not done. Iterate, don't claim.

Evidence chain

complete_step requires ≥1 evidence item per completion. Each verification evidence must include the exact command as it ran. The host matches commands against the session transcript — approximate citations are rejected. Use the command string from the bash output, verbatim.

Failure modes

  • Inspection-as-evidence — reading code and concluding it works. Build output only.
  • Stale-timestamp "passes" — citing a test run from a previous turn. Re-run it.
  • Command mismatch — the host rejects evidence when the cited command doesn't match what actually ran. Copy the command from bash output exactly.

Related

  • pre-action-gate — pre-write safety checkpoint
  • evidence-first-reasoning — diagnostic verification under ambiguity

Security

  • Security scanPassed, 100 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/aliatx2017/reasonix-hermes/ready-means-tested/badge)](https://verified-skill.com/skills/aliatx2017/reasonix-hermes/ready-means-tested)

Something wrong with this skill or its page? Tell us.