Store Evaluation
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.
When to Use
- A user invokes
/add-source with a candidate store
- Periodic re-evaluation of borderline entries (every 6 months)
The Five Dimensions
Score 0–2 per dimension. Maximum score is 10. Threshold for inclusion: ≥ 7.
1. Maintenance Health (0–2)
| 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 |
2. Adoption Signal (0–2)
| 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.)
3. License Clarity (0–2)
| 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.) |
4. Catalog Fit (0–2)
| 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 |
5. Documentation Quality (0–2)
| 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 |
Decision
| 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.
Output Template
# 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"
}
ACT Pass Trail
Anti-Patterns
| 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 |
Falsifiability
This scorecard needs revision if any of the following occur within 90 days:
- Accepted stores (score >= 7) are repeatedly pruned for quality or maintenance failures
- Deferred stores (score 5-6) consistently pass later without new evidence, indicating scoring too strict
- Reviewers produce materially different scores for the same store with no documented rationale
Track these in docs/curation-log.md tagged [STORE-SCORING].
Related
1---2name: store-evaluation3description: Evaluate a proposed store for inclusion in Alex_ACT_Plugin_Mall using a quality scorecard4---5
6# Store Evaluation
7
8Score 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](../source-inventory/SKILL.md).
9
10## When to Use
11
12- A user invokes `/add-source` with a candidate store
13- Periodic re-evaluation of borderline entries (every 6 months)
14
15## The Five Dimensions
16
17Score 0–2 per dimension. Maximum score is 10. **Threshold for inclusion: ≥ 7**.
18
19### 1. Maintenance Health (0–2)
20
21| Score | Criterion |
22|---|---|
23| 0 | Repo archived, no commits in 12+ months, last release > 2 years old |
24| 1 | Active but low velocity — commits in last 6 months, no recent release |
25| 2 | Active maintenance — commits in last 90 days OR active issue triage OR recent release |
26
27### 2. Adoption Signal (0–2)
28
29| Score | Criterion |
30|---|---|
31| 0 | Solo project, < 50 stars, no external contributors |
32| 1 | Some adoption — 50–500 stars, occasional external contributors |
33| 2 | Real adoption — > 500 stars OR multiple maintainers OR sustained external contribution |
34
35(Stars are noisy; weight them with maintenance + license signal.)
36
37### 3. License Clarity (0–2)
38
39| Score | Criterion |
40|---|---|
41| 0 | No license, custom restrictive license, or unclear terms |
42| 1 | Permissive license but with vendor-specific restrictions |
43| 2 | Clean OSI-approved license (MIT, Apache 2.0, BSD, ISC, etc.) |
44
45### 4. Catalog Fit (0–2)
46
47| Score | Criterion |
48|---|---|
49| 0 | Off-topic — no clear use case for an AI agent that consumes plugins from this Mall |
50| 1 | Tangential — useful in narrow scenarios |
51| 2 | Direct fit — agents that use this Mall would install plugins from this source in normal workflows |
52
53### 5. Documentation Quality (0–2)
54
55| Score | Criterion |
56|---|---|
57| 0 | No README, broken docs, or installation steps unclear |
58| 1 | Basic README, install instructions present, examples sparse |
59| 2 | Quality README + examples + clear installation + troubleshooting |
60
61## Decision
62
63| Total score | Verdict |
64|---|---|
65| 9–10 | **Strong accept** — add to the registry |
66| 7–8 | **Accept** — add with a note of any caveats |
67| 5–6 | **Defer** — request more signal (stars, contributors, time) and re-evaluate in 90 days |
68| 0–4 | **Reject** — document the rationale in `docs/curation-log.md` |
69
70**On accept**: add the entry to `sources/supported-stores.json` per [source-inventory](../source-inventory/SKILL.md). 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.
71
72## Output Template
73
74```markdown
75# Store Evaluation — <store name>
76
77**URL**: <repo URL>
78**Date**: YYYY-MM-DD
79**Evaluator**: <name>
80
81## Scores
82
83| Dimension | Score | Notes |
84|---|---|---|
85| Maintenance Health | x/2 | ... |
86| Adoption Signal | x/2 | ... |
87| License Clarity | x/2 | ... |
88| Catalog Fit | x/2 | ... |
89| Documentation Quality | x/2 | ... |
90| **Total** | **x/10** | |
91
92## Verdict
93
94Strong accept | Accept | Defer | Reject
95
96## Rationale
97
98<2-3 sentences>
99
100## Proposed registry entry (if accepted)
101
102```jsonc
103{
104 "name": "<kebab-name>",
105 "remote": "https://github.com/<org>/<repo>",
106 "pluginDir": "<plugins | skills | . | other>",
107 "quality": "<official | community-curated | community | domain | reference>",
108 "provenance": false,
109 "license": "<SPDX-id or null>",
110 "added_at": "YYYY-MM-DD"
111}
112```
113
114## ACT Pass Trail
115
116<markers>
117```
118
119## Anti-Patterns
120
121| Anti-pattern | Correction |
122|---|---|
123| Scoring on stars alone | Stars are one signal of five; weight with maintenance and fit |
124| "I like it" override | The scorecard is the contract. Document overrides as ADRs |
125| Rejecting without recording | Every rejection sets precedent; document or future similar proposals will repeat the cycle |
126
127## Falsifiability
128
129This scorecard needs revision if any of the following occur within 90 days:
130
131- Accepted stores (score >= 7) are repeatedly pruned for quality or maintenance failures
132- Deferred stores (score 5-6) consistently pass later without new evidence, indicating scoring too strict
133- Reviewers produce materially different scores for the same store with no documented rationale
134
135Track these in `docs/curation-log.md` tagged `[STORE-SCORING]`.
136
137## Related
138
139- [source-inventory](../source-inventory/SKILL.md) — adding accepted stores to the registry
140- [staleness-discipline](../staleness-discipline/SKILL.md) — pruning gates
141- `/add-source` prompt
gabrielmoreira