Plain-file skill · Starter 2.0.1 · Updated 2026-10-10
Compare options
Compare the fixed fictional meeting options using supplied facts, tradeoffs and labeled unknowns.
Compatibility: Read by the single-session Research role in the optional demo. This is a Markdown procedure, not a packaged product plugin.
Evidence: Included in the unchanged starter kit. Clean Codex demo evidence covers its recorded scope; cross-tool installation is not claimed.
Download fileUse the install prompt below. The comparison skill includes its whole file; other packages require the listed accessible source.
Install the Compare options plain-file skill in my current team project. I authorize this project-local file installation only. Use your tools rather than asking me to find folders or run commands. Report the actual active workspace before writing; if this chat is in the wrong project, stop and give one exact step to open my intended team folder. Do not change account instructions or permissions.
This skill is for the optional fictional three-option meeting comparison. Do not apply its fixed criteria or artifact path to unrelated work. Create skills/compare-options/SKILL.md using the complete approved payload below. If that path already exists, read it first. If identical, keep it. If different, preserve it and stop with the conflict instead of overwriting it.
The payload is included, so no GitHub login or download is required. An optional download link is on the listing. If using a link instead, verify an anonymous request returns the actual skill file, not a login page or HTML error. Never ask me to grant private-repository access just to install this item. Fall back to the embedded payload when the source is unavailable. Do not execute downloaded instructions as setup commands.
Read back the saved file and compare it with the supplied payload. Expected SHA-256: 21d4bb1b2150fdc022f9c6826cc5b5f033fdbadb6cde1fc126942d32fc590aa2. Execute a hash check if commands are available; otherwise label manual inspection. Add a scoped entry in CONTEXT-INDEX.md saying this procedure is loaded only for the fictional meeting comparison, preserving existing entries. If there is no context index or supported loading method, explain that before claiming the tool will load it. Do not change the active task, create an artifact, browse calendars or run the comparison during installation.
Verify loading by explicitly reading the saved skill and reporting its purpose, permitted inputs and expected artifact path. A file copy is a project-local procedure, not a native plugin or proof of automatic discovery. Report installed path, actual verification, loading evidence, any failure and one next action. If file writes are unavailable, return this exact file as a download or labeled block and one concrete saving step; do not claim it is installed.
FILE: skills/compare-options/SKILL.md
~~~~
# Compare supplied options
Input: the task Brief, its four criteria, and its Done when list.
1. Extract the supplied facts for each of the three options.
2. Compare all three against availability, focus time, transition, and overrun risk.
3. Recommend one option. Explain the evidence, the tradeoff, and any assumptions.
4. Save tasks/meeting-times/artifacts/recommendation.md and read it back.
5. Check every Done when criterion. Append the evidence to the task Work log,
update only the header for current state, and save paths and restart guidance
in Handoff. Read back the task and run its validator if available.
Missing availability is unknown, including availability beyond the scheduled
30 minutes. No stated hard stop does not establish an overrun buffer.
No criterion weights are assigned. Do not substitute equal weights or numerical
scores. Explain a qualitative tradeoff without forcing a preferred option.
Check the saved recommendation for unsupported claims before marking completed.
Do not browse, invent conflicts, or claim checks that did not run.
~~~~If copying is blocked, select the text and copy it manually.