* pstack: build-the-lever defaults to building the tool for any non-trivial work
* pstack: plain wording in build-the-lever Balance
* pstack: add gold-plating to unslop abstract-metaphor list
The skill and agent originally landed in cursor-team-kit via PR #70
and were unintentionally removed when the Thermos plugin (PR #92)
relocated them. Restoring here so they remain available in team-kit
alongside the standalone Thermos plugin.
- Restore cursor-team-kit/skills/thermo-nuclear-code-quality-review/SKILL.md
using the cleaned-up version (no internal-only references) that
Thermos already ships.
- Restore cursor-team-kit/agents/thermo-nuclear-code-quality-review.md
verbatim from the original PR (points at the cursor-team-kit plugin
for skill lookup).
- Add the skill + agent rows back to cursor-team-kit/README.md and
remove the now-misleading "moved to Thermos" pointer.
Users installing both plugins will see the same skill name in two
places; this is a known overlap and is fine for now.
Co-authored-by: Cursor <cursoragent@cursor.com>
- Remove provenance sentence referencing Sualeh, the lukas-pr-review
internal skill, and the "Improve code quality" IDE feature name from
thermo-nuclear-code-quality-review.
- Rephrase thermo-nuclear-review description and intro to drop the
"web Deep review quick action" framing; describe the audit on its
own terms.
- Fix typo: memdium-to-high -> medium-to-high.
- Generalize the "Delete the database" example: drop the company name.
Co-authored-by: Cursor <cursoragent@cursor.com>
Thermos is a new plugin that packages thermo-nuclear branch review:
- thermo-nuclear-review (skill) — deep security/correctness audit
- thermo-nuclear-code-quality-review (skill) — harsh maintainability audit
- thermos (skill) — orchestrator that runs both reviews in parallel
with shared diff context and synthesizes findings
- Two Task subagents (one per review skill) for diff-scoped audits
The code-quality review previously lived in cursor-team-kit. Moved it
into Thermos alongside the new deep-review rubric so the two reviewers
sit together with their orchestrator. cursor-team-kit bumped to 1.2.0
with a pointer to the new plugin.
Marketplace and root README updated with the new entry.
Co-authored-by: Cursor <cursoragent@cursor.com>
* pstack: add usage examples to README
* pstack: condense README examples into a one-line bullet list
* pstack: drop trailing gloss from README examples, keep label + prompt
* pstack: wrap README examples in a single code block
the skills table listed every shipped non-principle skill except
typescript-best-practices. add a row for it in the README's existing
voice. the principles section already enumerates all eighteen principle
skills, including type-system-discipline, so it needs no change.
lauren tan's working style as a Cursor plugin. Bundles the poteto-mode
routing skill plus the workflow skills it routes through (how, why,
architect, arena, unslop, interrogate, automate-me, reflect, tdd) and
the full seventeen-skill set of first principles. Ships the poteto-agent
subagent that runs the same workflow end-to-end.
The why skill discovers available MCPs at run time and maps each to an
evidence category (source control, issue tracker, long-form docs,
real-time chat, infra observability, error tracking, analytics
warehouse). No third-party service integrations required.
cursor-team-kit's control-cli, control-ui, and deslop are referenced as
sibling-plugin dependencies for surfaces and commit cleanup; the kit
works standalone otherwise.
Marketplace entry registered at the root .cursor-plugin/marketplace.json.
Ports an unusually strict code-quality review rubric into cursor-team-kit:
ambitious "code-judo" simplifications, 1k-line file rule, spaghetti
detection, type/boundary cleanliness, and a hard approval bar. Adds a
matching Task subagent that loads the skill and applies it against a
collected diff.
Co-authored-by: Cursor <cursoragent@cursor.com>
lauren