Install any skill in seconds. Free to start, no credit card required.
Get Started Free →List and filter documents and units in the Knowledge base. Use when the user wants to see what is indexed ('what's in space X', 'list the last 10 indexed docs', 'which documents have error status', 'show Academy units').
.claude/skills/evolution-foundation-knowledge-browse/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-11 | ✗→✓ | ▲ Improved | 155% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 1% | 0% |
| case-05 | ✗→✓ | ▲ Improved | 149% | 0% |
| case-07 | ✗→✓ | ▲ Improved | 16% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -21% | 0% |
Group: Curation. List/filter documents + units.
| Name | Type | Default | Description | |---|---|---|---| | scope | str | "documents" | "documents" OR "units" | | connection | str | first ready | Target connection | | space | str | null | Filter by space slug | | unit_id | str | null | Filter by unit | | content_type | str | null | lesson/tutorial/faq/reference/... | | difficulty | str | null | beginner/intermediate/advanced | | topics | liststr] | null | Filter by tags | | status | str | null | pending/processing/ready/error | | q | str | null | Text search on title | | limit | int | 20 | How many to return |
pythonfrom dashboard.backend.sdk_client import evo if scope == "documents": params = {k: v for k, v in { "space": space, "unit_id": unit_id, "content_type": content_type, "difficulty": difficulty, "topics": ",".join(topics or []), "status": status, "q": q, "limit": limit, }.items() if v is not None} items = evo.get("/api/knowledge/v1/documents", params=params, headers={"X-Knowledge-Connection": connection}) elif scope == "units": params = {"space": space, "limit": limit} items = evo.get("/api/knowledge/v1/units", params=params, headers={"X-Knowledge-Connection": connection})
Documents:
| Title | Type | Difficulty | Topics | Chunks | Status | Added |
|---|---|---|---|---|---|---|
| ... | lesson | beginner | [whatsapp, auth] | 14 | ready | 2026-04-20 |Units:
| Title | Slug | Space | Seq | Docs | Created |
|---|---|---|---|---|---|
| ... | ... | academy | 1 | 5 | 2026-04-15 |Showing {len(items)} of {total} {scope} in {connection}{/space if filtered}.
Filters applied: {filters_summary}.knowledge-admin action=health"| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-11 | fail→pass | 3,052 | 2,975 | -3% | 1 | 1 | 0% | 461 | 1,175 | +155% | 0 | 0 | — |
case-01 | fail→fail | 14,417 | 4,284 | -70% | 1 | 1 | 0% | 2,229 | 1,390 | -38% | 0 | 0 | — |
case-02 | fail→fail | 7,921 | 6,780 | -14% | 1 | 1 | 0% | 704 | 1,066 | +51% | 0 | 0 | — |
case-03 | fail→pass | 6,301 | 2,956 | -53% | 1 | 1 | 0% | 1,143 | 1,149 | +1% | 0 | 0 | — |
case-04 | fail→fail | 7,442 | 12,482 | +68% | 1 | 1 | 0% | 561 | 2,854 | +409% | 0 | 0 | — |
case-05 | fail→pass | 6,512 | 13,048 | +100% | 1 | 1 | 0% | 1,130 | 2,815 | +149% | 0 | 0 | — |
case-06 | fail→fail | 5,998 | 7,998 | +33% | 1 | 1 | 0% | 948 | 2,078 | +119% | 0 | 0 | — |
case-07 | fail→pass | 6,026 | 4,096 | -32% | 1 | 1 | 0% | 1,100 | 1,275 | +16% | 0 | 0 | — |
case-08 | fail→pass | 7,136 | 1,865 | -74% | 1 | 1 | 0% | 1,195 | 941 | -21% | 0 | 0 | — |
case-09 | fail→pass | 8,322 | 9,124 | +10% | 1 | 1 | 0% | 1,353 | 2,260 | +67% | 0 | 0 | — |
case-10 | fail→pass | 7,485 | 3,001 | -60% | 1 | 1 | 0% | 1,607 | 1,218 | -24% | 0 | 0 | — |
case-12 | pass→pass | 9,730 | 3,292 | -66% | 1 | 1 | 0% | 1,615 | 1,217 | -25% | 0 | 0 | — |
case-13 | fail→pass | 3,248 | 3,566 | +10% | 1 | 1 | 0% | 452 | 1,307 | +189% | 0 | 0 | — |
case-14 | pass→pass | 8,142 | 2,088 | -74% | 1 | 1 | 0% | 1,304 | 966 | -26% | 0 | 0 | — |
case-15 | fail→pass | 7,593 | 2,734 | -64% | 1 | 1 | 0% | 1,344 | 1,054 | -22% | 0 | 0 | — |
case-16 | fail→pass | 9,377 | 1,640 | -83% | 1 | 1 | 0% | 1,646 | 880 | -47% | 0 | 0 | — |
case-17 | fail→pass | 9,091 | 5,239 | -42% | 1 | 1 | 0% | 1,470 | 1,573 | +7% | 0 | 0 | — |
case-18 | fail→pass | 4,260 | 2,053 | -52% | 1 | 1 | 0% | 812 | 1,017 | +25% | 0 | 0 | — |
case-19 | fail→pass | 9,526 | 1,535 | -84% | 1 | 1 | 0% | 1,706 | 848 | -50% | 0 | 0 | — |
case-20 | fail→pass | 10,093 | 1,622 | -84% | 1 | 1 | 0% | 1,673 | 863 | -48% | 0 | 0 | — |
case-21 | pass→pass | 6,967 | 10,032 | +44% | 1 | 1 | 0% | 1,279 | 1,351 | +6% | 0 | 0 | — |
case-22 | fail→pass | 7,677 | 3,431 | -55% | 1 | 1 | 0% | 1,277 | 1,245 | -3% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted, and 21 counted toward the lift figure. The other 1 produced results that are not comparable between the two arms, so they are excluded from the headline rather than averaged into it. The headline lift of +68 percentage points is the difference between those two pass rates over the 21 comparable cases.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.