AGENT SKILL
vard-traction
Check post-launch traction for a shipped VARD app and recommend iterate, graduate, or archive
- License 许可
- MIT
- 最近更新
- 2026-11-10
- Stars
- ★ 1
- Forks
- 0
01 前言 Front Matter
- name
- vard-traction
- type
- ops
- version
- v0.0
- description
- Check post-launch traction for a shipped VARD app and recommend iterate, graduate, or archive
- context_intake
- artifact_only
03 SKILL.md 正文
VARD Traction
Invoke as /vard-traction.
Post-launch traction check for shipped VARD experiments. Reads the ship log and current signals, compares them against the VARD graduation thresholds, and recommends exactly one of: iterate, graduate to Business AFPS, or archive. This is the semi-automatic graduation gate — the skill recommends, you confirm before anything happens.
Process
- Resolve target: Use
$ARGUMENTSto name the shipped concept. If omitted, use the most recentlaunchedentry inresearch/vard-ship-log.md. - Confirm timing: Traction is meaningful after 1-2 weeks live. If the ship date is more recent, note the signal is early and mark the recommendation provisional.
- Gather signals: Collect the available distribution and engagement signals for the app:
- Users / unique visitors
- Shares and social engagement (is the viral mechanic working?)
- Core-action completion (the one thing the app does)
- Revenue or revenue-intent signals
- Inbound interest (enterprise inquiries, feature requests, press)
Use the analytics wired at ship time. Where a signal is unavailable, mark it
unknownrather than guessing.
- Compare to graduation thresholds: Evaluate against the VARD graduation triggers:
- Enterprise inquiry or clear revenue potential → strong graduate signal (Business AFPS)
- User base large enough to justify deep customer discovery → graduate signal
- Sustained engagement or sharing growth → iterate-and-grow signal
- Flat or no traction after 1-2 weeks → archive signal
- Recommend (semi-auto gate): Produce exactly one recommendation with its rationale and the signals that drove it:
- Graduate → enter Business AFPS at
/idea-scope-brief, linking the VARD scan, align, and ship-log entries as evidence. - Iterate → keep it in VARD; run another build and distribution cycle.
- Archive → record the outcome and move on to the next experiment. State explicitly that the user confirms before any graduation, archive, or further action happens.
- Graduate → enter Business AFPS at
- Log the check: Append a traction entry under the concept in
research/vard-ship-log.md:- Date of check, weeks since launch
- Each signal and its value (or
unknown) - Threshold comparison result
- Recommendation and rationale
- Status:
iterating,graduating, orarchived
Output
End with:
**Traction:** <concept name> — <one-line signal summary>
**Recommendation:** iterate | graduate to Business AFPS | archive
**Next work:** <the confirming action for the recommendation>
**Recommended next command:** /idea-scope-brief (graduate) | /vard-scan (next experiment) | none (archived)
Constraints
- Do not run paid API calls or external account actions to gather signals.
- Do not graduate, archive, or delete anything automatically — recommend and let the user confirm.
- Mark unavailable signals as
unknown; do not fabricate metrics. - If no ship-log entry exists for the target, report that and stop.
- Create
research/vard-ship-log.mdwith a header only if it is missing and a shipped app clearly exists.
Default Shipping Contract
Follow the shared shipping contract convention.
04 同仓库更多 Skills
source-checkout-allowed
Valid source-checkout-only fixture.
★ 1
deck-install-valid
Valid deck install fixture.
★ 1
codex-pack-guard-valid
Valid Codex Pack Availability Guard fixture.
★ 1
codex-missing-skill-valid
Valid Codex missing skill fallback fixture.
★ 1
codex-base-skill-fallback-valid
Valid Codex base skill fallback fixture.
★ 1
claude-pack-guard-valid
Valid Claude Pack Availability Guard fixture.
★ 1