diff --git a/.claude-plugin/marketplace.json b/.claude-plugin/marketplace.json index eabed01..2ad0473 100644 --- a/.claude-plugin/marketplace.json +++ b/.claude-plugin/marketplace.json @@ -9,13 +9,13 @@ { "name": "qe", "source": "./qe", - "version": "0.2.1", + "version": "0.2.2", "description": "QuantEcon's author-facing base skills — style checking, lecture editing support, and working through a PR's review feedback" }, { "name": "benchmark", "source": "./benchmark", - "version": "0.3.1", + "version": "0.3.2", "description": "Benchmarking and acceleration-evaluation tools for QuantEcon lecture code" }, { diff --git a/CATALOG.md b/CATALOG.md index 66952be..edb5f7f 100644 --- a/CATALOG.md +++ b/CATALOG.md @@ -8,7 +8,7 @@ Merged-but-not-yet-working scaffolding is deliberately absent. It registers in t |---|---|---|---| | **`qe`** — author-facing skills, from drafting a lecture to merging its PR | `/qe:copilot-review` | Operational, and validated from an installed plugin on 2026-08-03: plugin-root path resolution, cross-repo mode, and running from outside a working tree. The style skills (`check-style` and six per-category siblings) are merged as scaffolding and report that they are not yet operational, so they are not listed here until the rule snapshot and deterministic preflight land. | [#3](https://github.com/QuantEcon/skills/issues/3) | | **`benchmark`** — evaluating accelerated lecture implementations | `/benchmark:review-acceleration` | Operational for workspace runs: rubric v2, a deterministic scoring engine, and two complete worked evaluations as regression baselines. | [#4](https://github.com/QuantEcon/skills/issues/4) | -| **`audit`** — bulk, read-only repository audits | `/audit:issues` | Runbook landed, and executed once end to end against a real repo — **by hand, never yet as a skill**. Treat its method as unvalidated until the first run under [#16](https://github.com/QuantEcon/skills/issues/16) reports. | [#12](https://github.com/QuantEcon/skills/issues/12), [#16](https://github.com/QuantEcon/skills/issues/16) | +| **`audit`** — bulk, read-only repository audits | `/audit:issues` | Run once **as a skill** — a 230-item tracker on 2026-07-28, 22 minutes, seven plugin defects found and recorded ([record](https://github.com/QuantEcon/skills/blob/main/reviews/audit-run-action-translation-2026-07-28.md)). That validates the method as far as one run goes and no further: its central claim, resumability, is still untested, because the run was never interrupted. Further runs: [#16](https://github.com/QuantEcon/skills/issues/16). | [#12](https://github.com/QuantEcon/skills/issues/12), [#16](https://github.com/QuantEcon/skills/issues/16) | Installation and setup are in [README.md](README.md); what it is like to run one is in [docs/using-skills.md](docs/using-skills.md). diff --git a/benchmark/.claude-plugin/plugin.json b/benchmark/.claude-plugin/plugin.json index fa8be63..85712d5 100644 --- a/benchmark/.claude-plugin/plugin.json +++ b/benchmark/.claude-plugin/plugin.json @@ -1,6 +1,6 @@ { "name": "benchmark", "description": "Benchmarking and acceleration-evaluation tools for QuantEcon lecture code", - "version": "0.3.1", + "version": "0.3.2", "author": { "name": "QuantEcon" } } diff --git a/benchmark/CHANGELOG.md b/benchmark/CHANGELOG.md index c0e73b7..77e785a 100644 --- a/benchmark/CHANGELOG.md +++ b/benchmark/CHANGELOG.md @@ -6,6 +6,12 @@ Versions are [semver](https://semver.org) as a user of this plugin experiences i Repository: [QuantEcon/skills](https://github.com/QuantEcon/skills) ([every commit that touched this plugin](https://github.com/QuantEcon/skills/commits/main/benchmark)). How a release is made: [developing-skills § Versioning and releases](https://github.com/QuantEcon/skills/blob/main/docs/developing-skills.md#versioning-and-releases). +## 0.3.2 — 2026-08-03 + +**Fixed** + +- The plugin README's status line said skill wiring was "tracked in skills#4". The wiring shipped in 0.3.0 — it is in that release's entry below — so the line pointed at an open issue for work that had already landed. 0.3.1 corrected the version number in that same sentence and left the stale clause standing, which is how a half-fixed line survives a review. It now describes the plugin as operational for workspace runs since 0.3.0 and points at this changelog for what shipped when. + ## 0.3.1 — 2026-08-03 **Added** diff --git a/benchmark/README.md b/benchmark/README.md index 7d05184..3ecd364 100644 --- a/benchmark/README.md +++ b/benchmark/README.md @@ -9,7 +9,7 @@ One skill, two modes: | **Review** | Did this conversion PR improve the lecture? | baseline + candidate implementations | A scored report with a merge recommendation | | **Triage** | Is this lecture worth converting at all? | the existing lecture only | A predicted verdict band with the binding constraint named | -Status: evaluation system landed (v0.3.0); skill wiring tracked in [skills#4](https://github.com/QuantEcon/skills/issues/4). The system was developed and validated by [@xuanguang-li](https://github.com/xuanguang-li) on [lecture-python.myst#717](https://github.com/QuantEcon/lecture-python.myst/pull/717) and [#654](https://github.com/QuantEcon/lecture-python.myst/pull/654). +Status: operational for workspace runs since v0.3.0, which wired the skill to the scoring engine — what shipped in which release is in [CHANGELOG.md](CHANGELOG.md), and remaining plan items are in [skills#4](https://github.com/QuantEcon/skills/issues/4). The system was developed and validated by [@xuanguang-li](https://github.com/xuanguang-li) on [lecture-python.myst#717](https://github.com/QuantEcon/lecture-python.myst/pull/717) and [#654](https://github.com/QuantEcon/lecture-python.myst/pull/654). ## Using the skill diff --git a/docs/using-skills.md b/docs/using-skills.md index 6b1e132..e059982 100644 --- a/docs/using-skills.md +++ b/docs/using-skills.md @@ -47,9 +47,9 @@ Everything that registers in your slash menu, working or not. That is wider than | Plugin | Skills | What they do | Status | |---|---|---|---| | `qe` | `/qe:check-style` + `check-{writing,math,code,figures,jax,refs}` | Style-guide compliance for lecture source, by rule ID | scaffolding — [skills#3](https://github.com/QuantEcon/skills/issues/3) | -| `qe` | `/qe:copilot-review` | Work through GitHub Copilot's review of a PR: a verdict and recommended fix per comment, then a threaded reply to each one so they can be resolved from the GitHub UI | operational, validated from an installed plugin 2026-08-03 — [skills#3](https://github.com/QuantEcon/skills/issues/3) | -| `benchmark` | `/benchmark:review-acceleration` | Score a NumPy→JAX/Numba conversion (review mode) or assess whether a lecture is worth converting (triage mode) | system landed — [guide](../benchmark/README.md), [skills#4](https://github.com/QuantEcon/skills/issues/4) | -| `audit` | `/audit:issues` | Sweep a whole tracker: verify each issue's status against the code rather than the thread, tier the open set into the repo's plan, deliver a report bundle. Read-only — it recommends, never applies | runbook landed, method not yet validated — [tutorial](tutorial-run-an-audit.md), [guide](../audit/README.md), [skills#16](https://github.com/QuantEcon/skills/issues/16) | +| `qe` | `/qe:copilot-review` | Work through GitHub Copilot's review of a PR: a verdict and recommended fix per comment, then a threaded reply to each one so they can be resolved from the GitHub UI | operational, validated from an installed plugin 2026-08-03 — [#26](https://github.com/QuantEcon/skills/pull/26) | +| `benchmark` | `/benchmark:review-acceleration` | Score a NumPy→JAX/Numba conversion (review mode) or assess whether a lecture is worth converting (triage mode) | operational for workspace runs — [guide](../benchmark/README.md), [skills#4](https://github.com/QuantEcon/skills/issues/4) | +| `audit` | `/audit:issues` | Sweep a whole tracker: verify each issue's status against the code rather than the thread, tier the open set into the repo's plan, deliver a report bundle. Read-only — it recommends, never applies | run once as a skill, method validated only that far — [tutorial](tutorial-run-an-audit.md), [guide](../audit/README.md), [skills#16](https://github.com/QuantEcon/skills/issues/16) | ## Updating and troubleshooting diff --git a/qe/.claude-plugin/plugin.json b/qe/.claude-plugin/plugin.json index a2e3314..17318a6 100644 --- a/qe/.claude-plugin/plugin.json +++ b/qe/.claude-plugin/plugin.json @@ -1,6 +1,6 @@ { "name": "qe", "description": "QuantEcon's author-facing base skills — style checking, lecture editing support, and working through a PR's review feedback", - "version": "0.2.1", + "version": "0.2.2", "author": { "name": "QuantEcon" } } diff --git a/qe/CHANGELOG.md b/qe/CHANGELOG.md index 4bef95c..c5b491d 100644 --- a/qe/CHANGELOG.md +++ b/qe/CHANGELOG.md @@ -6,6 +6,13 @@ Versions are [semver](https://semver.org) as a user of this plugin experiences i Repository: [QuantEcon/skills](https://github.com/QuantEcon/skills) ([every commit that touched this plugin](https://github.com/QuantEcon/skills/commits/main/qe)). How a release is made: [developing-skills § Versioning and releases](https://github.com/QuantEcon/skills/blob/main/docs/developing-skills.md#versioning-and-releases). +## 0.2.2 — 2026-08-03 + +**Fixed** + +- `/qe:check-math`'s description showed `\\top`, `\\tag` and `\\mathbb` where it meant `\top`, `\tag` and `\mathbb`. YAML plain scalars do no escape processing, so the doubled backslashes were literal — the description is what natural-language invocation matches against, so this was wrong in the one string that most needs to be right. (It stays unquoted deliberately: `\t` and `\m` are not valid double-quoted YAML escapes, so quoting it would break the file outright.) +- `/qe:copilot-review`'s status banner sent readers to [issue #3](https://github.com/QuantEcon/skills/issues/3) for "plan and open questions". That issue tracks the style-check surface and says nothing about this skill. The banner now credits the PR the skill shipped in and scopes #3 to the work it actually covers. + ## 0.2.1 — 2026-08-03 **Fixed** diff --git a/qe/skills/check-math/SKILL.md b/qe/skills/check-math/SKILL.md index 2666b11..bee1113 100644 --- a/qe/skills/check-math/SKILL.md +++ b/qe/skills/check-math/SKILL.md @@ -1,6 +1,6 @@ --- name: check-math -description: Check a QuantEcon lecture's mathematical notation against the style guide — \\top transpose, aligned (never align) inside $$, no \\tag, \\mathbb P/E/V, plain-letter distribution names, sequence and matrix conventions. Reports violations by rule ID with an offer to fix. +description: Check a QuantEcon lecture's mathematical notation against the style guide — \top transpose, aligned (never align) inside $$, no \tag, \mathbb P/E/V, plain-letter distribution names, sequence and matrix conventions. Reports violations by rule ID with an offer to fix. --- # check-math diff --git a/qe/skills/copilot-review/SKILL.md b/qe/skills/copilot-review/SKILL.md index d69b456..b4e9a0c 100644 --- a/qe/skills/copilot-review/SKILL.md +++ b/qe/skills/copilot-review/SKILL.md @@ -7,7 +7,7 @@ description: Review GitHub Copilot's feedback on a pull request, assess each com Automates the loop **review Copilot's PR feedback → advise → (fix) → reply to each comment on GitHub**, so the author can then click "Resolve conversation" in the UI. -> **Status: operational.** Promoted from a personal skill that had been in daily use, and validated on 2026-08-03 from an installed plugin: plugin-root path resolution, cross-repo mode, and running from outside a working tree. Plan and open questions: [issue #3](https://github.com/QuantEcon/skills/issues/3). +> **Status: operational.** Promoted from a personal skill that had been in daily use, and validated on 2026-08-03 from an installed plugin: plugin-root path resolution, cross-repo mode, and running from outside a working tree. Shipped in [#26](https://github.com/QuantEcon/skills/pull/26); the `qe` plugin's remaining work — the style surface — is tracked in [#3](https://github.com/QuantEcon/skills/issues/3). Requires `gh`, authenticated. The working tree is only what an omitted repo or PR number is inferred from — name both and it runs from anywhere.