anthropics/skills

Public scan — anyone with this URL can view this analysis. Sign up to track your own repos privately, run scheduled re-scans, and get AI fix prompts via your dashboard.

70 of your 103 findings came from Repobility's proprietary detections. ✓ Repobility tags below mark them.

Scan timing: clone 4.85s · analysis 6.22s · 10.3 MB · GitHub preflight 424ms

https://github.com/anthropics/skills · scanned 2026-06-05 04:46 UTC (12 hours, 47 minutes ago) · 10 languages

240 findings (96 legacy + 144 scanner) 26th percentile · Python · small (2-20K LoC) Scanner says 97 (lower by 38)

File as issue Image

UNIFIED Repobility · multi-layer engine · AI coders

Complete repo analysis

Last scanned 12 hours, 47 minutes ago · v2 · 168 findings from 2 sources. Findings combine the legacy security pipeline AND the multi-layer engine (atlas, wiring, flows, ranked) AND verified AI agent contributions.

JSON

Score breakdown â 2026-05-18-v5

Component	Sub-score	Weight	Contribution
`structure_score`	40.0	0.15	6.00
`security_score`	52.9	0.25	13.22
`testing_score`	70.0	0.20	14.00
`documentation_score`	62.0	0.15	9.30
`practices_score`	70.0	0.15	10.50
`code_quality`	60.0	0.10	6.00
Overall		1.00	59.0

Severity distribution — click a segment to filter

Active filters: excluding tests × Reset all

Severity: Critical 1 High 66 Medium 23 Low 62 9-Layer: Software Security Quality Integrity Frontend Hardware Data Network Cicd Source: Legacy 96 9-layer 72 Crowd 0 Layer: Software 41 Security 8 Quality 116 Api 1 Frontend 1 Cicd 1

Exclude dismissed / FP Exclude test files

All 670 nodes from the latest scan, grouped by kind. Each node is a unit the engine identified (file, function, endpoint, table…). Most users won't need this view — it's primarily for debugging the engine's graph extraction or for AI agents that want to enumerate the project structure.

Label	Layer	Status	Path
`_call_claude`	software	healthy	`skills/skill-creator/scripts/improve_description.py:20`
`improve_description`	software	healthy	`skills/skill-creator/scripts/improve_description.py:50`
`main`	software	healthy	`skills/skill-creator/scripts/improve_description.py:194`
`split_eval_set`	software	healthy	`skills/skill-creator/scripts/run_loop.py:24`
`run_loop`	software	healthy	`skills/skill-creator/scripts/run_loop.py:47`
`print_eval_stats`	software	healthy	`skills/skill-creator/scripts/run_loop.py:154`
`main`	software	healthy	`skills/skill-creator/scripts/run_loop.py:244`
`should_exclude`	software	healthy	`skills/skill-creator/scripts/package_skill.py:27`
`package_skill`	software	healthy	`skills/skill-creator/scripts/package_skill.py:42`
`main`	software	healthy	`skills/skill-creator/scripts/package_skill.py:111`
`generate_html`	software	healthy	`skills/skill-creator/scripts/generate_report.py:16`
`aggregate_runs`	software	healthy	`skills/skill-creator/scripts/generate_report.py:227`
`score_class`	software	healthy	`skills/skill-creator/scripts/generate_report.py:244`
`main`	software	healthy	`skills/skill-creator/scripts/generate_report.py:304`
`parse_skill_md`	software	healthy	`skills/skill-creator/scripts/utils.py:7`
`validate_skill`	software	healthy	`skills/skill-creator/scripts/quick_validate.py:12`
`calculate_stats`	software	healthy	`skills/skill-creator/scripts/aggregate_benchmark.py:45`
`load_run_results`	software	healthy	`skills/skill-creator/scripts/aggregate_benchmark.py:67`
`aggregate_results`	software	healthy	`skills/skill-creator/scripts/aggregate_benchmark.py:176`
`generate_benchmark`	software	healthy	`skills/skill-creator/scripts/aggregate_benchmark.py:227`
`generate_markdown`	software	healthy	`skills/skill-creator/scripts/aggregate_benchmark.py:281`
`main`	software	healthy	`skills/skill-creator/scripts/aggregate_benchmark.py:338`
`find_project_root`	software	healthy	`skills/skill-creator/scripts/run_eval.py:22`
`run_single_query`	software	dead	`skills/skill-creator/scripts/run_eval.py:35`
`run_eval`	software	healthy	`skills/skill-creator/scripts/run_eval.py:184`
`main`	software	healthy	`skills/skill-creator/scripts/run_eval.py:259`
`get_mime_type`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:52`
`find_runs`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:60`
`_find_runs_recursive`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:68`
`build_run`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:85`
`embed_file`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:149`
`load_previous_iteration`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:213`
`generate_html`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:250`
`_kill_port`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:288`
`__init__`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:315`
`do_GET`	software	dead	`skills/skill-creator/eval-viewer/generate_review.py:332`
`do_POST`	software	dead	`skills/skill-creator/eval-viewer/generate_review.py:361`
`log_message`	software	dead	`skills/skill-creator/eval-viewer/generate_review.py:382`
`main`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:387`
`linear`	software	dead	`skills/slack-gif-creator/core/easing.py:12`
`ease_in_quad`	software	dead	`skills/slack-gif-creator/core/easing.py:17`
`ease_out_quad`	software	dead	`skills/slack-gif-creator/core/easing.py:22`
`ease_in_out_quad`	software	dead	`skills/slack-gif-creator/core/easing.py:27`
`ease_in_cubic`	software	dead	`skills/slack-gif-creator/core/easing.py:34`
`ease_out_cubic`	software	dead	`skills/slack-gif-creator/core/easing.py:39`
`ease_in_out_cubic`	software	dead	`skills/slack-gif-creator/core/easing.py:44`
`ease_in_bounce`	software	healthy	`skills/slack-gif-creator/core/easing.py:51`
`ease_out_bounce`	software	healthy	`skills/slack-gif-creator/core/easing.py:56`
`ease_in_out_bounce`	software	dead	`skills/slack-gif-creator/core/easing.py:71`
`ease_in_elastic`	software	dead	`skills/slack-gif-creator/core/easing.py:78`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`README.md`	software	healthy	`README.md`
`THIRD_PARTY_NOTICES.md`	software	healthy	`THIRD_PARTY_NOTICES.md`
`agent-skills-spec.md`	software	healthy	`spec/agent-skills-spec.md`
`SKILL.md`	software	healthy	`template/SKILL.md`
`SKILL.md`	software	healthy	`skills/claude-api/SKILL.md`
`claude-api.md`	software	healthy	`skills/claude-api/php/claude-api.md`
`README.md`	software	healthy	`skills/claude-api/php/managed-agents/README.md`
`managed-agents.md`	software	healthy	`skills/claude-api/curl/managed-agents.md`
`examples.md`	software	healthy	`skills/claude-api/curl/examples.md`
`claude-api.md`	software	healthy	`skills/claude-api/ruby/claude-api.md`
`README.md`	software	healthy	`skills/claude-api/ruby/managed-agents/README.md`
`models.md`	software	healthy	`skills/claude-api/shared/models.md`
`model-migration.md`	software	healthy	`skills/claude-api/shared/model-migration.md`
`agent-design.md`	software	healthy	`skills/claude-api/shared/agent-design.md`
`managed-agents-tools.md`	software	healthy	`skills/claude-api/shared/managed-agents-tools.md`
`tool-use-concepts.md`	software	healthy	`skills/claude-api/shared/tool-use-concepts.md`
`managed-agents-events.md`	software	healthy	`skills/claude-api/shared/managed-agents-events.md`
`error-codes.md`	software	healthy	`skills/claude-api/shared/error-codes.md`
`managed-agents-outcomes.md`	software	healthy	`skills/claude-api/shared/managed-agents-outcomes.md`
`managed-agents-api-reference.md`	software	healthy	`skills/claude-api/shared/managed-agents-api-reference.md`
`prompt-caching.md`	software	healthy	`skills/claude-api/shared/prompt-caching.md`
`managed-agents-memory.md`	software	healthy	`skills/claude-api/shared/managed-agents-memory.md`
`managed-agents-environments.md`	software	healthy	`skills/claude-api/shared/managed-agents-environments.md`
`managed-agents-onboarding.md`	software	healthy	`skills/claude-api/shared/managed-agents-onboarding.md`
`managed-agents-self-hosted-sandboxes.md`	software	healthy	`skills/claude-api/shared/managed-agents-self-hosted-sandbox…`
`managed-agents-overview.md`	software	healthy	`skills/claude-api/shared/managed-agents-overview.md`
`managed-agents-multiagent.md`	software	healthy	`skills/claude-api/shared/managed-agents-multiagent.md`
`live-sources.md`	software	healthy	`skills/claude-api/shared/live-sources.md`
`managed-agents-client-patterns.md`	software	healthy	`skills/claude-api/shared/managed-agents-client-patterns.md`
`managed-agents-core.md`	software	healthy	`skills/claude-api/shared/managed-agents-core.md`
`managed-agents-webhooks.md`	software	healthy	`skills/claude-api/shared/managed-agents-webhooks.md`
`batches.md`	software	healthy	`skills/claude-api/typescript/claude-api/batches.md`
`README.md`	software	healthy	`skills/claude-api/typescript/claude-api/README.md`
`tool-use.md`	software	healthy	`skills/claude-api/typescript/claude-api/tool-use.md`
`streaming.md`	software	healthy	`skills/claude-api/typescript/claude-api/streaming.md`
`files-api.md`	software	healthy	`skills/claude-api/typescript/claude-api/files-api.md`
`README.md`	software	healthy	`skills/claude-api/typescript/managed-agents/README.md`
`claude-api.md`	software	healthy	`skills/claude-api/csharp/claude-api.md`
`batches.md`	software	healthy	`skills/claude-api/python/claude-api/batches.md`
`README.md`	software	healthy	`skills/claude-api/python/claude-api/README.md`
`tool-use.md`	software	healthy	`skills/claude-api/python/claude-api/tool-use.md`
`streaming.md`	software	healthy	`skills/claude-api/python/claude-api/streaming.md`
`files-api.md`	software	healthy	`skills/claude-api/python/claude-api/files-api.md`
`README.md`	software	healthy	`skills/claude-api/python/managed-agents/README.md`
`claude-api.md`	software	healthy	`skills/claude-api/java/claude-api.md`
`README.md`	software	healthy	`skills/claude-api/java/managed-agents/README.md`
`claude-api.md`	software	healthy	`skills/claude-api/go/claude-api.md`
`README.md`	software	healthy	`skills/claude-api/go/managed-agents/README.md`
`SKILL.md`	software	healthy	`skills/skill-creator/SKILL.md`
`improve_description.py`	software	healthy	`skills/skill-creator/scripts/improve_description.py`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`spec`	software	healthy	`spec`
`template`	software	healthy	`template`
`skills`	software	healthy	`skills`
`claude-api`	software	healthy	`skills/claude-api`
`php`	software	healthy	`skills/claude-api/php`
`managed-agents`	software	healthy	`skills/claude-api/php/managed-agents`
`curl`	software	healthy	`skills/claude-api/curl`
`ruby`	software	healthy	`skills/claude-api/ruby`
`managed-agents`	software	healthy	`skills/claude-api/ruby/managed-agents`
`shared`	software	healthy	`skills/claude-api/shared`
`typescript`	software	healthy	`skills/claude-api/typescript`
`claude-api`	software	healthy	`skills/claude-api/typescript/claude-api`
`managed-agents`	software	healthy	`skills/claude-api/typescript/managed-agents`
`csharp`	software	healthy	`skills/claude-api/csharp`
`python`	software	healthy	`skills/claude-api/python`
`claude-api`	software	healthy	`skills/claude-api/python/claude-api`
`managed-agents`	software	healthy	`skills/claude-api/python/managed-agents`
`java`	software	healthy	`skills/claude-api/java`
`managed-agents`	software	healthy	`skills/claude-api/java/managed-agents`
`go`	software	healthy	`skills/claude-api/go`
`managed-agents`	software	healthy	`skills/claude-api/go/managed-agents`
`skill-creator`	software	healthy	`skills/skill-creator`
`scripts`	software	healthy	`skills/skill-creator/scripts`
`references`	software	healthy	`skills/skill-creator/references`
`assets`	software	healthy	`skills/skill-creator/assets`
`agents`	software	healthy	`skills/skill-creator/agents`
`eval-viewer`	software	healthy	`skills/skill-creator/eval-viewer`
`slack-gif-creator`	software	healthy	`skills/slack-gif-creator`
`core`	software	healthy	`skills/slack-gif-creator/core`
`theme-factory`	software	healthy	`skills/theme-factory`
`themes`	software	healthy	`skills/theme-factory/themes`
`frontend-design`	software	healthy	`skills/frontend-design`
`internal-comms`	software	healthy	`skills/internal-comms`
`examples`	software	healthy	`skills/internal-comms/examples`
`doc-coauthoring`	software	healthy	`skills/doc-coauthoring`
`webapp-testing`	software	healthy	`skills/webapp-testing`
`scripts`	software	healthy	`skills/webapp-testing/scripts`
`examples`	software	healthy	`skills/webapp-testing/examples`
`mcp-builder`	software	healthy	`skills/mcp-builder`
`reference`	software	healthy	`skills/mcp-builder/reference`
`scripts`	software	healthy	`skills/mcp-builder/scripts`
`docx`	software	healthy	`skills/docx`
`scripts`	software	healthy	`skills/docx/scripts`
`office`	software	healthy	`skills/docx/scripts/office`
`helpers`	software	healthy	`skills/docx/scripts/office/helpers`
`validators`	software	healthy	`skills/docx/scripts/office/validators`
`pptx`	software	healthy	`skills/pptx`
`scripts`	software	healthy	`skills/pptx/scripts`
`office`	software	healthy	`skills/pptx/scripts/office`
`helpers`	software	healthy	`skills/pptx/scripts/office/helpers`

Showing first 50 of this kind. Full payload available via the JSON button at the top of the page.

Label	Layer	Status	Path
`ReviewHandler`	software	healthy	`skills/skill-creator/eval-viewer/generate_review.py:308`
`GIFBuilder`	software	healthy	`skills/slack-gif-creator/core/gif_builder.py:17`
`MCPConnection`	software	healthy	`skills/mcp-builder/scripts/connections.py:13`
`MCPConnectionStdio`	software	healthy	`skills/mcp-builder/scripts/connections.py:73`
`MCPConnectionSSE`	software	healthy	`skills/mcp-builder/scripts/connections.py:88`
`MCPConnectionHTTP`	software	healthy	`skills/mcp-builder/scripts/connections.py:100`
`PPTXSchemaValidator`	software	healthy	`skills/docx/scripts/office/validators/pptx.py:10`
`RedliningValidator`	software	healthy	`skills/docx/scripts/office/validators/redlining.py:11`
`BaseSchemaValidator`	software	healthy	`skills/docx/scripts/office/validators/base.py:12`
`DOCXSchemaValidator`	software	healthy	`skills/docx/scripts/office/validators/docx.py:16`
`PPTXSchemaValidator`	software	healthy	`skills/pptx/scripts/office/validators/pptx.py:10`
`RedliningValidator`	software	healthy	`skills/pptx/scripts/office/validators/redlining.py:11`
`BaseSchemaValidator`	software	healthy	`skills/pptx/scripts/office/validators/base.py:12`
`DOCXSchemaValidator`	software	healthy	`skills/pptx/scripts/office/validators/docx.py:16`
`PPTXSchemaValidator`	software	healthy	`skills/xlsx/scripts/office/validators/pptx.py:10`
`RedliningValidator`	software	healthy	`skills/xlsx/scripts/office/validators/redlining.py:11`
`BaseSchemaValidator`	software	healthy	`skills/xlsx/scripts/office/validators/base.py:12`
`DOCXSchemaValidator`	software	healthy	`skills/xlsx/scripts/office/validators/docx.py:16`
`RectAndField`	software	healthy	`skills/pdf/scripts/check_bounding_boxes.py:9`
`Entity`	software	healthy	`skills/algorithmic-art/templates/generator_template.js:Enti…`

Label	Layer	Status	Path
`repobility-clone-5_4xhf8w`	software	healthy	`/tmp/repobility-clone-5_4xhf8w`

Label	Layer	Status	Path
`127.0.0.1`	network	healthy	`skills/skill-creator/eval-viewer/generate_review.py`

For AI agents: Voting guide (TP/FP) MCP manifest Stdio wrapper SARIF Integrate Findings queue Vote TP/FP on findings to calibrate the engine.

For AI agents + API integrations

Email me when this repo regresses

Free. We re-scan periodically; new criticals → your inbox. No signup required for the scan itself.

API access

This page is publicly accessible at: https://repobility.com/scan/3b3babf3-493f-481f-8ce6-856823dae1a3/

To check status programmatically (no auth required):

curl -s https://repobility.com/api/v1/public/scan/3b3babf3-493f-481f-8ce6-856823dae1a3/

Important — please don't re-submit the same URL repeatedly. The submission endpoint is idempotent: re-submitting the same git URL returns this same scan_token, not a new one. To re-scan this repo, sign up free and use the dashboard.

anthropics/skills

Complete repo analysis

function 50+

file 50+

directory 50+

class 20

repo 1

service 1