Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →Scans for project documentation files (AGENTS.md, CLAUDE.md, GEMINI.md, COPILOT.md, CURSOR.md, WARP.md, and 15+ other formats) and synthesizes guidance. Auto-activates when user asks to review, understand, or explore a codebase, when starting work in a new project, when asking about conventions or agents, or when documentation context would help. Can consolidate multiple platform docs into unified AGENTS.md.
.claude/skills/aiskillstore-doc-scanner/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-04 | ✗→✓ | ▲ Improved | 46% | 0% |
| case-05 | ✗→✓ | ▲ Improved | -53% | 0% |
| case-07 | ✗→✓ | ▲ Improved | -54% | 0% |
| case-08 | ✗→✓ | ▲ Improved | -29% | 0% |
| case-10 | ✗→✓ | ▲ Improved | -19% | 0% |
Scan for and synthesize project documentation.
Use Glob to search project root:
AGENTS.md, CLAUDE.md, AI.md, ASSISTANT.md,
GEMINI.md, COPILOT.md, CHATGPT.md, CODEIUM.md,
CURSOR.md, WINDSURF.md, VSCODE.md, JETBRAINS.md,
WARP.md, FIG.md, DEVCONTAINER.md, GITPOD.mdRead complete contents of every documentation file found.
Combine information into unified summary:
PROJECT DOCUMENTATION
Sources: [list files found]
RECOMMENDED AGENTS
Primary: [agents for core work]
Secondary: [agents for specific tasks]
KEY WORKFLOWS
[consolidated workflows]
CONVENTIONS
[code style, patterns]
QUICK COMMANDS
[common commands]If 2+ documentation files exist, offer to consolidate:
.doc-archive/ directoryIf none found, offer to generate AGENTS.md based on:
For detailed patterns, load:
./references/file-patterns.md - Complete list of files to scan./references/templates.md - AGENTS.md generation templatesWhen generating a NEW AGENTS.md, follow the entry-doc standard in rules/agentic-quality.md (Landmines section mandatory, ~150-line budget) — skeleton at the repo-doctor skill's assets/AGENTS-template.md. To AUDIT an existing doc set rather than generate one, hand off to repo-doctor.
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→fail | 5,138 | 5,912 | +15% | 1 | 1 | 0% | 262 | 836 | +219% | 0 | 0 | — |
case-02 | fail→fail | 1,849 | 11,715 | +534% | 1 | 1 | 0% | 236 | 983 | +317% | 0 | 0 | — |
case-03 | fail→fail | 2,271 | 15,081 | +564% | 1 | 1 | 0% | 319 | 881 | +176% | 0 | 0 | — |
case-04 | fail→pass | 4,488 | 3,452 | -23% | 1 | 1 | 0% | 788 | 1,147 | +46% | 0 | 0 | — |
case-05 | fail→pass | 9,837 | 1,270 | -87% | 1 | 1 | 0% | 1,491 | 697 | -53% | 0 | 0 | — |
case-06 | pass→pass | 10,539 | 2,080 | -80% | 1 | 1 | 0% | 1,648 | 820 | -50% | 0 | 0 | — |
case-07 | fail→pass | 10,814 | 1,884 | -83% | 1 | 1 | 0% | 1,769 | 813 | -54% | 0 | 0 | — |
case-08 | fail→pass | 9,853 | 3,679 | -63% | 1 | 1 | 0% | 1,610 | 1,151 | -29% | 0 | 0 | — |
case-09 | pass→pass | 10,169 | 2,162 | -79% | 1 | 1 | 0% | 1,569 | 854 | -46% | 0 | 0 | — |
case-10 | fail→pass | 12,370 | 2,026 | -84% | 1 | 1 | 0% | 1,058 | 854 | -19% | 0 | 0 | — |
case-11 | fail→pass | 14,140 | 2,060 | -85% | 1 | 1 | 0% | 2,178 | 852 | -61% | 0 | 0 | — |
case-12 | pass→pass | 8,326 | 2,823 | -66% | 1 | 1 | 0% | 1,305 | 1,010 | -23% | 0 | 0 | — |
case-13 | pass→pass | 26,665 | 3,110 | -88% | 1 | 1 | 0% | 2,086 | 1,036 | -50% | 0 | 0 | — |
case-14 | fail→pass | 6,297 | 1,858 | -70% | 1 | 1 | 0% | 1,028 | 815 | -21% | 0 | 0 | — |
case-15 | fail→pass | 5,055 | 2,609 | -48% | 1 | 1 | 0% | 716 | 928 | +30% | 0 | 0 | — |
case-16 | fail→pass | 10,862 | 1,865 | -83% | 1 | 1 | 0% | 1,892 | 809 | -57% | 0 | 0 | — |
case-17 | fail→pass | 4,039 | 2,828 | -30% | 1 | 1 | 0% | 620 | 899 | +45% | 0 | 0 | — |
case-18 | fail→pass | 5,130 | 2,548 | -50% | 1 | 1 | 0% | 748 | 870 | +16% | 0 | 0 | — |
case-19 | fail→fail | 6,288 | 4,236 | -33% | 1 | 1 | 0% | 994 | 1,031 | +4% | 0 | 0 | — |
case-20 | pass→fail | 5,272 | 8,410 | +60% | 1 | 1 | 0% | 1,059 | 931 | -12% | 0 | 0 | — |
case-21 | pass→fail | 4,315 | 5,089 | +18% | 1 | 1 | 0% | 780 | 865 | +11% | 0 | 0 | — |
case-22 | fail→fail | 6,084 | 2,579 | -58% | 1 | 1 | 0% | 937 | 919 | -2% | 0 | 0 | — |
case-23 | pass→pass | 11,457 | 1,415 | -88% | 1 | 1 | 0% | 1,773 | 751 | -58% | 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. 23 cases were attempted, and 18 counted toward the lift figure. The other 5 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 +39 percentage points is the difference between those two pass rates over the 18 comparable cases. 2 cases got worse with the skill loaded, and they are included in that figure.
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.