Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Run the complete llmwiki pipeline from scratch — init, sync, graph, build, lint, and serve. Use when the user says "run everything", "full pipeline", "wiki-all", or wants to rebuild the entire wiki from session history.
.claude/skills/pratiyush-wiki-all/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | -9% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -32% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -56% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -17% | 0% |
| case-09 | ✗→✓ | ▲ Improved | -40% | 0% |
Runs the complete llmwiki pipeline in the correct sequence:
raw/, wiki/, site/ directories.jsonl sessions to markdownwiki/ markdown into site/ HTMLRun each step in order. Report the result of each before proceeding to the next.
bashpython3 -m llmwiki init
Report what was created or confirmed.
bashpython3 -m llmwiki sync --no-auto-build --no-auto-lint
Report: how many sessions converted, how many unchanged, any errors.
If new sessions were converted, follow the Ingest Workflow from CLAUDE.md for each new file (create/update entity + concept pages, cross-link, update index).
bashpython3 -m llmwiki graph
Report: node count, edge count, community count, top 5 connected nodes.
Ask the user: "Export graph to Obsidian vault?" If yes:
pythonpython3 -c " from llmwiki.graphify_bridge import export_to_obsidian from pathlib import Path export_to_obsidian(Path.home() / 'Documents/Obsidian Vault/Temp/Graph') "
bashpython3 -m llmwiki build
Report: HTML file count, total size, export formats written.
bashpython3 -m llmwiki lint
Report: total issues by severity (errors, warnings, info). Highlight any errors that need immediate attention.
Ask the user: "Start the local server?" If yes:
bashpython3 -m llmwiki serve --open
Report the URL: http://127.0.0.1:8765
Report a summary table:
| Step | Result | |------|--------| | init | N dirs, M seed files | | sync | N converted, M unchanged | | graph | N nodes, M edges, K communities | | build | N HTML files, M MB | | lint | N issues (E errors, W warnings) | | serve | http://127.0.0.1:8765 |
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 7,850 | 25,949 | +231% | 1 | 1 | 0% | 1,264 | 1,001 | -21% | 0 | 0 | — |
case-02 | fail→fail | 10,596 | 2,954 | -72% | 1 | 1 | 0% | 1,712 | 943 | -45% | 0 | 0 | — |
case-03 | fail→fail | 13,604 | 3,165 | -77% | 1 | 1 | 0% | 1,754 | 922 | -47% | 0 | 0 | — |
case-04 | fail→pass | 5,261 | 1,322 | -75% | 1 | 1 | 0% | 913 | 830 | -9% | 0 | 0 | — |
case-05 | fail→pass | 8,338 | 2,011 | -76% | 1 | 1 | 0% | 1,318 | 893 | -32% | 0 | 0 | — |
case-06 | fail→fail | 9,785 | 2,970 | -70% | 1 | 1 | 0% | 1,551 | 1,056 | -32% | 0 | 0 | — |
case-07 | fail→pass | 14,687 | 2,416 | -84% | 1 | 1 | 0% | 2,376 | 1,037 | -56% | 0 | 0 | — |
case-08 | fail→pass | 7,750 | 2,782 | -64% | 1 | 1 | 0% | 1,299 | 1,076 | -17% | 0 | 0 | — |
case-09 | fail→pass | 11,630 | 2,812 | -76% | 1 | 1 | 0% | 1,772 | 1,055 | -40% | 0 | 0 | — |
case-10 | fail→pass | 10,344 | 2,352 | -77% | 1 | 1 | 0% | 1,703 | 982 | -42% | 0 | 0 | — |
case-11 | fail→pass | 8,343 | 1,651 | -80% | 1 | 1 | 0% | 1,407 | 857 | -39% | 0 | 0 | — |
case-12 | fail→fail | 10,712 | 2,599 | -76% | 1 | 1 | 0% | 1,721 | 1,076 | -37% | 0 | 0 | — |
case-13 | pass→pass | 10,617 | 4,519 | -57% | 1 | 1 | 0% | 1,500 | 1,381 | -8% | 0 | 0 | — |
case-14 | fail→fail | 9,733 | 2,057 | -79% | 1 | 1 | 0% | 1,389 | 915 | -34% | 0 | 0 | — |
case-15 | pass→pass | 10,520 | 2,667 | -75% | 1 | 1 | 0% | 1,474 | 1,032 | -30% | 0 | 0 | — |
case-16 | fail→pass | 9,538 | 2,932 | -69% | 1 | 1 | 0% | 1,477 | 1,084 | -27% | 0 | 0 | — |
case-17 | fail→pass | 8,522 | 2,770 | -67% | 1 | 1 | 0% | 1,266 | 1,040 | -18% | 0 | 0 | — |
case-18 | pass→pass | 14,750 | 3,445 | -77% | 1 | 1 | 0% | 2,280 | 1,191 | -48% | 0 | 0 | — |
case-19 | fail→pass | 7,082 | 2,376 | -66% | 1 | 1 | 0% | 1,067 | 977 | -8% | 0 | 0 | — |
case-20 | pass→pass | 2,754 | 3,160 | +15% | 1 | 1 | 0% | 358 | 1,104 | +208% | 0 | 0 | — |
case-21 | pass→pass | 3,099 | 2,993 | -3% | 1 | 1 | 0% | 514 | 1,107 | +115% | 0 | 0 | — |
case-22 | pass→pass | 2,517 | 3,161 | +26% | 1 | 1 | 0% | 385 | 1,043 | +171% | 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. The headline lift of +45 percentage points is the difference between those two pass rates over the 22 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.