eval-harness-campaign
Skill1 starsChanged 4 months agoNo licenceView on GitHub
The decision-gated campaign plan for what the 2026-07-10 handoff identifies (assumption A2, owner-unconfirmed) as this repo's hardest live problem: no repeatable eval harness — evals.json shipped buried inside a zip inside files.zip (a byte-identical working copy now sits in this skill's references/), so there is no repeatable way to measure whether a SKILL.md edit helped or hurt. Load this when you are asked to "build the eval harness", "make evals runnable/repeatable", "extract the evals", "set up eval automation", "score the council skill", or when you are about to edit claude-council/SKILL.md prose and realize you have no before/after measurement. Do NOT load this for what counts as evidence or the eval schema (validation-and-evals), for mechanical artifact checks like parity or lint (diagnostics-and-tooling), for whether a change is allowed at all (change-control), or for turning a wording hunch into a tested hypothesis (research-methodology).
In this repository14 other files it gives its agents.
- architecture-contractSkill
- build-and-envSkill
- change-controlSkill
- claude-councilSkill
- debugging-playbookSkill
- diagnostics-and-toolingSkill
- docs-and-writingSkill
- domain-referenceSkill
- failure-archaeologySkill
- logic-treeSkill
- release-and-packagingSkill
- research-methodologySkill
- skill-authoringSkill
- validation-and-evalsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

