en un clic
store-evaluation
Evaluate a proposed store for inclusion in Alex_ACT_Plugin_Mall using a quality scorecard
Menu
Evaluate a proposed store for inclusion in Alex_ACT_Plugin_Mall using a quality scorecard
How the Plugin Mall scans, scores, and prunes itself. The Mall is a self-curating repo; this skill is its operational playbook for the weekly catalog refresh and trust scoring. Use when working on the scan pipeline, debugging a stuck weekly PR, or onboarding to Mall internals.
Consolidate session learning into permanent architecture — extract patterns into skills, instructions, prompts, or memory
Maintain the source registry in sources/supported-stores.json — add a new third-party plugin store, retire one, refresh metadata, validate the schema. Use when proposing a registry change, after the weekly cron flags a source as unhealthy, or when a candidate store needs evaluation before adding.
Detect, classify, and prune stale source stores in the Mall — define what stale means and how to remove gracefully without breaking downstream consumers.
Comprehensive brain file review — external freshness, internal consistency, semantic accuracy — stamp only after full assessment
This skill should be used when building agent evaluation systems: deterministic checks, regression suites, multi-dimensional rubrics, quality gates, production monitoring, baseline comparison, and outcome measurement for agent pipelines.
| name | store-evaluation |
| description | Evaluate a proposed store for inclusion in Alex_ACT_Plugin_Mall using a quality scorecard |
| lastReviewed | "2026-05-05T00:00:00.000Z" |
Score a proposed source store against five dimensions. Stores below the threshold are rejected. Stores above are added to sources/supported-stores.json via source-inventory.
/add-source with a candidate storeScore 0–2 per dimension. Maximum score is 10. Threshold for inclusion: ≥ 7.
| Score | Criterion |
|---|---|
| 0 | Repo archived, no commits in 12+ months, last release > 2 years old |
| 1 | Active but low velocity — commits in last 6 months, no recent release |
| 2 | Active maintenance — commits in last 90 days OR active issue triage OR recent release |
| Score | Criterion |
|---|---|
| 0 | Solo project, < 50 stars, no external contributors |
| 1 | Some adoption — 50–500 stars, occasional external contributors |
| 2 | Real adoption — > 500 stars OR multiple maintainers OR sustained external contribution |
(Stars are noisy; weight them with maintenance + license signal.)
| Score | Criterion |
|---|---|
| 0 | No license, custom restrictive license, or unclear terms |
| 1 | Permissive license but with vendor-specific restrictions |
| 2 | Clean OSI-approved license (MIT, Apache 2.0, BSD, ISC, etc.) |
| Score | Criterion |
|---|---|
| 0 | Off-topic — no clear use case for an AI agent that consumes plugins from this Mall |
| 1 | Tangential — useful in narrow scenarios |
| 2 | Direct fit — agents that use this Mall would install plugins from this source in normal workflows |
| Score | Criterion |
|---|---|
| 0 | No README, broken docs, or installation steps unclear |
| 1 | Basic README, install instructions present, examples sparse |
| 2 | Quality README + examples + clear installation + troubleshooting |
| Total score | Verdict |
|---|---|
| 9–10 | Strong accept — add to the registry |
| 7–8 | Accept — add with a note of any caveats |
| 5–6 | Defer — request more signal (stars, contributors, time) and re-evaluate in 90 days |
| 0–4 | Reject — document the rationale in docs/curation-log.md |
On accept: add the entry to sources/supported-stores.json per source-inventory. The Mall does NOT clone or modify the upstream repo — it scores it and surfaces it in the catalog; agents install directly from upstream at a pinned ref.
# Store Evaluation — <store name>
**URL**: <repo URL>
**Date**: YYYY-MM-DD
**Evaluator**: <name>
## Scores
| Dimension | Score | Notes |
|---|---|---|
| Maintenance Health | x/2 | ... |
| Adoption Signal | x/2 | ... |
| License Clarity | x/2 | ... |
| Catalog Fit | x/2 | ... |
| Documentation Quality | x/2 | ... |
| **Total** | **x/10** | |
## Verdict
Strong accept | Accept | Defer | Reject
## Rationale
<2-3 sentences>
## Proposed registry entry (if accepted)
```jsonc
{
"name": "<kebab-name>",
"remote": "https://github.com/<org>/<repo>",
"pluginDir": "<plugins | skills | . | other>",
"quality": "<official | community-curated | community | domain | reference>",
"provenance": false,
"license": "<SPDX-id or null>",
"added_at": "YYYY-MM-DD"
}
| Anti-pattern | Correction |
|---|---|
| Scoring on stars alone | Stars are one signal of five; weight with maintenance and fit |
| "I like it" override | The scorecard is the contract. Document overrides as ADRs |
| Rejecting without recording | Every rejection sets precedent; document or future similar proposals will repeat the cycle |
This scorecard needs revision if any of the following occur within 90 days:
Track these in docs/curation-log.md tagged [STORE-SCORING].
/add-source prompt