Skills

Skill 18 of 33

Convex Improve Convex Plugin

Send this coding session’s transcript to the Convex team for an AI post-mortem that improves the quickstart system.

1 minute · 232 words · 3 sections

Install

$ npx skills add convex/agent-skills --skill convex-improve-convex-plugin

$ npx skills add convex/agent-skills

The first command installs just this skill, by the name in its SKILL.md; the second installs the whole repository.

improve-convex-plugin

Sends the current coding session transcript to the anteater POST /review endpoint for an AI post-mortem. The review returns structured findings (ambiguous instructions, agent-stuck patterns, tooling failures, wins) targeted at the runbook, bootstrap script, skills, and components — not end-user data. Sharing is opt-in: the anteater-served helper asks once (Always / Just this once / Never) and remembers the choice.

Workflow

Run the anteater-served helper: curl -fsSL "<anteater>/send-transcript" | bash -s -- --idea "<one-line app idea from this session>".
If it prints CONSENT_REQUIRED (exit 4), the user has not chosen yet — ask them to share Always, Just this once, or Never, then re-run appending --consent always|once|never. Do not send until they answer.
Watch for output markers: REVIEW_SOURCE (transcript found), REVIEW_SUBMITTED id=… (accepted), REVIEW_DONE status=done (findings ready).
Summarize the highest-severity findings for the user: title → target → suggestedFix, then wins. Keep the summary about the system, not the user’s data.

Rules

Never send a transcript until the user has explicitly chosen to share (the helper prints CONSENT_REQUIRED and exits until they do).
REVIEW_NO_TRANSCRIPT means no Claude/Codex .jsonl was found — tell the user.
Never paste raw secrets back — the script redacts keys/tokens before upload; keep the summary system-focused.
This is a system-improvement loop, not end-user feature feedback.

About this skill

Trigger

Send this coding session's transcript to the Convex team for an AI post-mortem that improves the quickstart system. Run only when the user explicitly asks.

The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.

Colophon for this issue

Colophon

How this issue was made

Source

github.com/convex/agent-skills, branch main, last pushed 29 October 2026.

Licence

Apache-2.0 — the text of every skill is reproduced unmodified, frontmatter included, under the upstream licence.

Discovery

33 skills found by walking the repository tree for SKILL.md, not by matching a directory convention. One layout observed: skills/*/SKILL.md.

Issue colours

Resolved from a curated brand profile — hue 80°, chroma 0.160. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.

Heading repairs

1 repair applied to this skill so the document has one h1 and no skipped levels:

Shifted “3 headings” from h1 to h2 so the skill title is the only h1.

Spec compliance

Every skill satisfies the Agent Skills specification’s frontmatter rules.

Images

Images inside a skill come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.

Signal

Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.

Agent surfaces

The whole issue is available as one markdown document at /convex/agent-skills.md, and each skill at its own .md URL.

Publication

Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.

improve-convex-plugin

Run the anteater-served helper: curl -fsSL "<anteater>/send-transcript" | bash -s -- --idea "<one-line app idea from this session>".

If it prints CONSENT_REQUIRED (exit 4), the user has not chosen yet — ask them to share Always, Just this once, or Never, then re-run appending --consent always|once|never. Do not send until they answer.

Watch for output markers: REVIEW_SOURCE (transcript found), REVIEW_SUBMITTED id=… (accepted), REVIEW_DONE status=done (findings ready).

Summarize the highest-severity findings for the user: title → target → suggestedFix, then wins. Keep the summary about the system, not the user’s data.

Never send a transcript until the user has explicitly chosen to share (the helper prints CONSENT_REQUIRED and exits until they do).

REVIEW_NO_TRANSCRIPT means no Claude/Codex .jsonl was found — tell the user.

Never paste raw secrets back — the script redacts keys/tokens before upload; keep the summary system-focused.

This is a system-improvement loop, not end-user feature feedback.