Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →github/agent-skill-stack
Find, evaluate, and assemble the smallest compatible set of AI Agent Skills for an end-to-end natural-language goal.
Passed 11 of 16 test cases with the skill, and 5 of 16 without it.
and 9 more in the full report
11 fixed4 passed either way4 still failing3 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
We ran a dry-run project profile creation command using scripts/project_profile.py. What flag is added to execute and write the project profile after the user confirms?
| Checked | Without skill | With skill |
|---|---|---|
| The response specifies adding the --apply flag to apply the profile after confirmation. | Missed | Passed |
The instructions your model reads when the skill loads.
Build the smallest useful stack for the user's actual outcome. Never force a domain example or a fixed lifecycle onto a different request.
Default to plain-language mode. Assume the user does not need to understand paths, revisions, hashes, manifests, static analysis, or runtime details.
In plain-language mode, show:
Keep source paths, revisions, file fingerprints, raw scores, audit evidence, and dependency details in the internal record. Show them only when the user asks for technical details or when a specific technical fact is necessary for informed consent.
Read references/workflow-model.md. Begin with the final result the user wants, not the domain words in the request.
Ask only questions whose answers materially change the result, access boundary, cost, or stack. Derive the workflow backward from success, then validate it forward from the available starting point.
Do not reuse a previous numbered flow. Do not assume that every request needs research, content creation, publishing, analytics, storage, or automation. Add a step only when the user's outcome requires it.
Stop decomposing when a step has one understandable action, one main result, one access boundary, and one observable success condition. Keep the technical capability cards internal; show the user a short plain-language flow.
Read references/local-index-and-profiles.md.
If a current local Skill index exists, search it before the filesystem or internet. If it is missing or stale, rebuild it from the relevant Skill roots:
python3 scripts/skill_index.py build \
--root ~/.codex/skills \
--root ~/.codex/plugins/cache \
test cases passed, vs 5 / 16 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.