Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
9,018 results · page 219 of 301
- View details
cv-min-area-mask-filteringSkillAI & models
Removes predicted segmentation masks below a per-class minimum pixel area threshold to eliminate small false positive regions at inference time.
Ready to connect★ 61
- View details
cv-modality-adaptive-dicom-windowingSkillAI & models
Route each DICOM series to a per-modality window-center / window-width pair (CT/CTA/MRA/MRI) before normalization, so the same model can ingest mixed modalities without one modality's intensity range washing out the others
Ready to connect★ 61
- View details
cv-multi-series-channel-stackingSkillAI & models
Stacks uniformly sampled slices from multiple MRI series (e.g., Sagittal T1, T2, Axial) into a single multi-channel tensor for one-pass inference.
Ready to connect★ 61
- View details
cv-multilabel-auc-evaluationSkillAI & models
Computes per-class ROC-AUC then macro-averages for multi-label classification evaluation and model selection.
Ready to connect★ 61
- View details
cv-multilabel-cooccurrence-correlation-edaSkillAI & models
For multi-label classification, compute the per-class binary correlation matrix restricted to multi-label rows and the conditional class counts given a rare anchor class — reveals label groupings the model can exploit (shared classifier heads, hierarchical loss weighting, post-hoc consistency rules)
Ready to connect★ 61
- View details
cv-pairwise-distance-proximity-filterSkillAI & models
Compute Euclidean distance between entity pairs from tracking data and filter out pairs beyond a threshold to reduce inference candidates
Ready to connect★ 61
- View details
cv-per-label-platt-isotonic-calibrationSkillAI & models
Fit a per-label probability calibrator on out-of-fold scores using Platt scaling (logistic regression on raw scores) and fall back to isotonic regression for labels where the logistic doesn't converge — pickle the dict of fitted calibrators and apply at inference for a small but free leaderboard lif
Ready to connect★ 61
- View details
cv-per-modality-ensemble-averagingSkillAI & models
Train separate models per imaging modality (FLAIR/T1w/T1wCE/T2w) and average their predictions for final ensemble
Ready to connect★ 61
- View details
cv-per-modality-separate-modelSkillAI & models
Trains one specialized model per imaging modality or series type, routing inputs by metadata at inference for modality-specific feature learning.
Ready to connect★ 61
- View details
cv-quadratic-weighted-kappa-callbackSkillAI & models
Custom training callback that computes Quadratic Weighted Kappa on validation data each epoch and checkpoints the best model.
Ready to connect★ 61
- View details
debug-to-fixSkillAI & models
When debugging frustration appears ("why isn't this working?", "it should work", "I don't understand"), orchestrate the full debug cycle: clarify → investigate → fix → verify. Prevents the common failure of jumping to fixes before understanding the problem. An elixir that chains rubber-duck and prov
Ready to connect★ 61
- View details
dripSkillAI & models
Track and surface the estimated water cost of Claude interactions. Every query has a physical footprint - data centers need cooling, electricity needs generation. This skill adds environmental accountability by estimating water consumption per session and surfacing it at meaningful moments. Not to i
Ready to connect★ 61
- View details
geordieSkillAI & models
When activated, respond entirely in Geordie dialect from Newcastle upon Tyne. Use proper Geordie words, phrases, and grammar. Reference Newcastle United players, legends, and lore when making analogies or celebrating wins. Channel the spirit of St James' Park, The Entertainers, and Wor Jackie himsel
Ready to connect★ 61
- View details
keep-it-simpleSkillAI & models
Before adding abstraction, asks "do we need this now?" Activates when proposing factories, abstract classes, config-driven behavior, or "for future extensibility." Resists over-engineering. Three similar lines are better than a premature abstraction.
Ready to connect★ 61
- View details
learn-from-thisSkillAI & models
When a session contains a significant failure, misunderstanding, or repeated mistake, analyse the root cause and draft a new skill that would have prevented it. The skill library should grow from real failures, not hypothetical improvements. Every painful debugging session is a skill waiting to be w
Ready to connect★ 61
- View details
lobsterSkillAI & models
Our AI assistant. Boundless freedom, free interaction, capable of anything... 🦞 (@openclaw Chinese-localized enhanced edition, with multi-language switching and agent optimization)
Ready to connect★ 61
- View details
mstar-branch-worktreeSkillAI & models
Morning Star business repo Git feature branches, worktree isolation, and the three-write-domain model (L1 across plans: main checkout control root + iteration integration worktree + per-plan feature worktree + `execution_lease`; process artifacts are read/written via control absolute paths under def
Ready to connect★ 61
- View details
mstar-conventionsSkillAI & models
Morning Star (启明星) harness plan directory conventions — `{HARNESS_DIR}` / `{PLAN_DIR}` / `{SDD_DIR}` / `{ITERATION_DIR}` / `{KNOWLEDGE_DIR}` / `{SPECS_DIR}` / `{WORKFLOW_DIR}` / `{PROJECT_DIR}` discovery and initialization (default `.mstar/`, compatible with `.agents/`), `docs` and harness subtree b
Ready to connect★ 61
- View details
mstar-hostSkillAI & models
Morning Star host adapter for OpenCode, Cursor, Codex, Kimi, ZCode, omp, and dsh. Use after mstar-harness-core whenever host entry, clarify, dispatch, plan mode, or tool UX differs by platform - per-host subagent invoke, plan-mode bridge, parallel dispatch, and skill/command loading. Auto-detect the
Ready to connect★ 61
- View details
mstar-routing-evalSkillAI & models
[Cursor maint] Morning Star routing and prompt iteration evaluation — for maintenance/regression only (not the day-to-day PM orchestration runtime). Path: `.cursor/skills/mstar-routing-eval/` in this repo. (1) PM routing regression: `assets/routing-evals.`; (2) Prompt/rule iteration evaluation; (3)
Ready to connect★ 61
- View details
mstar-skill-authoringSkillAI & models
Guidelines for writing / rewriting / optimizing agent skills (gated by the SkillsBench experiment). Read when creating any new skill, making major changes to SKILL.md, rewriting a description trigger contract, compressing an overly long body, reviewing skill structure, or deciding whether a piece of
Ready to connect★ 61
- View details
pair-modeSkillAI & models
When activated, Claude becomes a pair programming partner rather than a code-generation tool. Explains reasoning, teaches patterns, asks questions that build understanding, and adjusts depth based on the person's goals. Balances getting work done with building lasting knowledge. Activate with "let's
Ready to connect★ 61
- View details
sanity-checkSkillAI & models
Before building on assumptions, validates them first. Activates when making claims about how code works, what exists, or why something happens. Prevents assumption cascades where one wrong guess leads to a completely wrong solution.
Ready to connect★ 61
- View details
solweaverSkillAI & models
Run Sol-led software development in auto, solo, solo-reviewed, or team modes, with GPT-5.6 Sol owning planning, implementation or delegation, integration, verification, and delivery; terra_worker and luna_worker providing bounded implementation; bundled test-driven-development enforcing RED-GREEN-RE
Ready to connect★ 61
- View details
split-decisionSkillAI & models
When facing architectural decisions, technology choices, or strategic trade-offs, present options as a structured comparison and require explicit trade-off acknowledgment before proceeding. Triggers on words like "should we", "which approach", "what's the best way", or when Claude is about to recomm
Ready to connect★ 61
- View details
squadSkillAI & models
Collaborate in a local Squad room with Claude, Codex, and human teammates. Use to join live collaboration, manage shared goals or research nodes (Science Cards), coordinate distinct workers, run steward checks, or reset the room.
Ready to connect★ 61
- View details
cmuxSkillAI & models
MUST be read ANY time you interact with cmux in ANY way — listing/inspecting/creating/closing cmux workspaces, panes, or surfaces; reading or capturing pane/screen output; sending input or keys to a pane/surface; delegating to, polling, or checking on other agents running in cmux panes/surfaces; bui
Ready to connect★ 59
- View details
codex-goal-loopSkillAI & models
Explain and write effective instructions for OpenAI Codex's `/goal` feature — the persistent self-checking agent loop (plan → act → test → review → iterate). Use when the user mentions Codex `/goal`, "goal loop", wants to kick off a long-running autonomous Codex run, asks how to write a goal prompt,
Ready to connect★ 59
- View details
deepline-plays-reviewSkillAI & models
Use this skill when a human needs to review a Deepline Play result and hand feedback, labels, or approval back to the agent for revision, evaluation, comparison, or bounded iteration. Triggers on “put this run in a Sheet,” “review these results,” “read my feedback,” “make this a standing rule,” “nev
Ready to connect★ 60
- View details
delegating-to-agentsSkillAI & models
Lets your agent hand bounded tasks to other AI agents while keeping context and checking progress.
Ready to connect★ 59
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,826 of the 55,257 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.