skill-research
Skill0 starsChanged 5 days agoMITView on GitHub
Helps users discover and install agent skills from the open skills ecosystem: searches by keyword, checks the skills.sh leaderboard, verifies quality before recommending, and presents install options. --improve audits and repairs an existing skill; --prune merges duplicate skills.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- RKelln/hermes_skillstheir own version, first seen Nov 7, 2026
- AndrewBrown-USDA/aigb-skills-usdatheir own version, first seen Oct 31, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- AndrewBrown-USDA/aigb-skills-usda★ 7same name
- RKelln/hermes_skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository75 other files it gives its agents.
- AGENTS.mdAGENTS.md
- skills/skill-authoring/tools/AGENTS.mdAGENTS.md
- aes-docsSkill
- aes-fixSkill
- aes-layerSkill
- aes-migrationSkill
- android-emulator-linux-gpsSkill
- computer-useSkill
- flatpak-chromium-automationSkill
- qwen-webSkill
- grok-buildSkill
- hermes-agentSkill
- omnirouteSkill
- orcaSkill
- account-managerSkill
- brave-setupSkill
- password-managerSkill
- codegraphSkill
- deep-cleanSkill
- dogfoodSkill
- reviewSkill
- systematic-debuggingSkill
- blender-arwakySkill
- comfyuiSkill
- llm-writingSkill
- vision-arwakySkill
- playwright-toolingSkill
- setup-ci-quality-gatesSkill
- statuslineSkill
- systemd-headless-serviceSkill
- xdg-spec-complianceSkill
- figcraft-builderSkill
- figcraft-iconsSkill
- figcraft-motionSkill
- figcraft-prototyperSkill
- figcraft-reviewSkill
- figcraftSkill
- figcraft-svgSkill
- figcraft-typographySkill
- github-authSkill
- issue-makerSkill
- issue-workerSkill
- mergifySkill
- pr-babysitSkill
- releasingSkill
- repo-managerSkill
- ascii-artSkill
- ascii-videoSkill
- gif-searchSkill
- media-acquisitionSkill
- docxSkill
- emailSkill
- google-workspaceSkill
- notionSkill
- pdfSkill
- pptxSkill
- xlsxSkill
- competitor-news-monitorSkill
- product-price-monitorSkill
- weekly-review-planningSkill
- The first 60 shown.
The file
Files
Skill Research
You discover and install agent skills from the open skills ecosystem, then route the user to the right one.
Rules
| ID | Rule | Why | Check |
| R1 | One home per fact. Skill-discovery policy (install-count thresholds, source reputation, GitHub star floor) lives only in references/finding-skills.md; the CLI command reference lives only in references/skill-cli.md. The body never restates them. | Prevents drift between body and references. | Grep body for 1K+ installs, <100 installs, 100 stars, npx skills — each must appear only in its owning reference. |
| R2 | Safety model: autonomous by default. Every step (search, verify, present) proceeds without asking the user for confirmation. --dry-run (if a caller supports it) is report-only and makes no changes; it is the only control flag. | Matches the skill-design safety model; no silent blocking. | argument-hint and Rules agree on default-vs-flag semantics; no "wait for approval" line exists anywhere in the skill directory. |
| R3 | Verify before recommending. Never recommend a skill based solely on search results; check install count, source reputation, and GitHub stars before presenting. | Avoids steering users to low-quality or abandoned skills. | references/finding-skills.md carries the verification criteria as checkable steps. |
Routing
| File | Purpose |
references/skill-cli.md | The npx skills command reference: find, add, update syntax and output shapes. |
references/finding-skills.md | The end-to-end find-verify-present workflow: domain/task split, leaderboard check, quality criteria, and how to present options. |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.