mcpbeat Sign in

Claude Skills

The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.

Every Agent Skill we could find on GitHub, deduplicated by content. 79 354 files from 1 739 authors, of which 61 713 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.

61 713
unique skills
out of 79 354 files found on GitHub
17 641
are copies
same content, someone else's repository
1 738
tokens, median
what a typical skill costs you in context
7 879
name collisions
two skills with one name cannot sit side by side

58 441–58 500 of 61 713

page 975 of 1 029
Frappe Web Forms
by lubusIN

Build public-facing web forms for data collection without Desk access. Use when creating customer submission forms, feedback forms, or self-service portals with Frappe Web Forms.

2k tokens
Frappe UI Patterns
by lubusIN

UI/UX patterns and guidelines derived from official Frappe apps (CRM, Helpdesk, HRMS). Use when designing interfaces for custom Frappe applications to ensure consistency with the ecosystem.

14k tokens
Break Even Calc
by openaccountant

> Calculate break-even revenue by separating fixed and variable costs.

968 tokens
Paypal Import
by openaccountant

> Import PayPal CSV exports with fee, refund, and currency handling.

1k tokens
Contractor Tracking
by openaccountant

> Monitor 1099 contractor payments and flag $600 threshold.

931 tokens
Cash Flow Forecast
by openaccountant

> Project future cash flow using historical trends and recurring patterns.

1k tokens
Multi Entity
by openaccountant

> Manage finances across multiple businesses or legal entities.

1k tokens
Invoice Aging
by openaccountant

> Track unpaid invoices by age bucket and flag overdue payments.

884 tokens
Client Profitability
by openaccountant

> Analyze revenue and costs per client to find your most profitable accounts.

979 tokens
Month End Close
by openaccountant

> Run a monthly bookkeeping close checklist with reconciliation.

1k tokens
Profit Loss
by openaccountant

> Generate a profit and loss statement for any date range.

966 tokens
Pricing Optimizer
by openaccountant

> Analyze pricing against costs and margins to optimize profitability.

985 tokens
Rental Property
by openaccountant

> Track rental income, expenses, ROI, and cap rate per property.

1k tokens
Runway Calculator
by openaccountant

> Calculate months of cash runway at current burn rate.

922 tokens
Revenue Concentration
by openaccountant

> Assess client concentration risk using revenue share and Herfindahl index.

949 tokens
Stripe Import
by openaccountant

> Import Stripe payment CSV exports with charges, fees, and refund handling.

1k tokens
Seasonal Patterns
by openaccountant

> Detect seasonal revenue and expense patterns across 12+ months of data.

1k tokens
Square Import
by openaccountant

> Import Square sales CSV exports with tips, refunds, and fee handling.

1k tokens
Venmo Reconciler
by openaccountant

> Reconcile Venmo business transactions and separate personal from business.

1k tokens
Charitable Giving
by openaccountant

> Track charitable donations and estimate their tax deduction value.

1k tokens
Wise Import
by openaccountant

> Import Wise (TransferWise) CSV exports with multi-currency handling.

1k tokens
Emergency Fund
by openaccountant

> Calculate emergency fund target and track savings progress toward it.

923 tokens
Debt Payoff
by openaccountant

> Build avalanche or snowball debt payoff plans with payment schedules.

1k tokens
Financial Goals
by openaccountant

> Set savings goals with timelines and track monthly progress toward them.

1k tokens
Insurance Audit
by openaccountant

> Find insurance payments, total annual premiums, and compare to benchmarks.

1k tokens
Lifestyle Creep
by openaccountant

> Detect spending increases across categories over 6-12 months.

987 tokens
Net Worth
by openaccountant

> Calculate net worth from assets and liabilities with a formatted statement.

1k tokens
Spending Review
by openaccountant

> Generate a categorized spending breakdown with month-over-month trends.

713 tokens
State Tax Estimator
by openaccountant

> Estimate state income tax liability based on income and state of residence.

1k tokens
Subscription Audit
by openaccountant

> Find recurring subscriptions, calculate total cost, and flag unused ones.

755 tokens
Bank Sync
by openaccountant

> Connect bank accounts for automatic transaction import via Plaid.

784 tokens
Zero Based Budget
by openaccountant

> Allocate every dollar of income to a category using zero-based budgeting.

1k tokens
Tax Penalty Calc
by openaccountant

> Estimate IRS underpayment penalties for missed quarterly tax payments.

973 tokens
Custom Report
by openaccountant

> Build custom financial reports with user-defined date ranges and categories.

741 tokens
Import Transactions
by openaccountant

> Import transactions from CSV, OFX, or QIF bank exports and deduplicate.

984 tokens
Mileage Tracker
by openaccountant

> Track business mileage and calculate IRS standard mileage deduction.

847 tokens
Home Office Deduction
by openaccountant

> Calculate home office deduction using simplified or actual expense method.

917 tokens
Depreciation Schedule
by openaccountant

> Track asset depreciation using MACRS schedules and Section 179 expensing.

1k tokens
Expense Optimizer
by openaccountant

> Find recurring expenses and subscriptions to cut or reduce.

1k tokens
Monthly Digest
by openaccountant

> Generate a monthly financial summary with metrics, trends, and anomalies.

828 tokens
Quarterly Taxes
by openaccountant

> Estimate quarterly tax payments using income totals and safe harbor rules.

857 tokens
Sales Tax Nexus
by openaccountant

> Determine sales tax obligations by state based on economic nexus thresholds.

925 tokens
Smart Categorize
by openaccountant

> Auto-categorize uncategorized transactions using vendor pattern matching.

820 tokens
Year End Summary
by openaccountant

> Generate an annual financial review with totals, trends, and highlights.

1k tokens
Smart Split
by openaccountant

> Split a single transaction across multiple categories with custom amounts.

656 tokens
Tax Prep
by openaccountant

> Organize business expenses by IRS Schedule C categories for tax filing.

913 tokens
Comic Author
by wanshuiyin

Phase 1 ORCHESTRATOR of a movie/comic — turn a fuzzy story idea into the Authored Source of Truth (a schema-valid comic.json + its locked asset library) by driving the detailed author skills in order (intent → style → outline → storyboard → assets → blueprints → prompts → comic.json), each gated by comic-cross-layer-gate, so comic-director (Phase 2/3) can bake + cross-model-verify it. You don't hand-write comic.json; this is the workflow your agent runs to author it. Use when the user says "做个漫画/电影", "from this idea make a comic", "author the comic.json", "run the comic pipeline".

8k tokens
Comic Director
by wanshuiyin

Phase 2/3 of a movie — bake + cross-model-verify a movie from an authored comic.json. Per frame: render the content-SVG blueprint, bake via the agent mcp__codex__codex sidecar, gate with a 3-reviewer cross-model panel (narrative [currently the codex CLI] ‖ Gemini visual ‖ Codex visual, deterministic fuse), keep/retry/assemble, write the wiki trace, project to the viewer. The movie-side twin of method-figure's render half. (Author the comic.json first with the comic-author skill.)

18k tokens scripts
Comic Asset Ref Generator
by wanshuiyin

Phase-1 (S4) of a comic movie — PRODUCE the canonical reusable references the whole spiral conditions on. Per asset it bakes ONE canonical 1:1 white-bg identity ref via the agent mcp__codex__codex sidecar bake (Codex native image_gen — conditioned, never hand-pasted) OR, for a deterministic motif (clock/chart/stamp/star-map), emits a single-source parametric SVG from a python generator (asset_lib.py). Hashes + base64-encodes the bake into the asset node's output_ref (all 6 fields or it's a schema violation), versions every ref _v{NNN} with a supersedes self-edge, and runs a single-source collision gate. GENERATES ONLY — it NEVER self-locks/approves (that is the cross-model asset-review-loop's job, a different model family). Identity is BRING-YOUR-OWN; the ARIS chibi duo is only the worked example.

9k tokens
Comic Continuity Audit
by wanshuiyin

The authoring-side DIEGETIC continuity AUDIT — it produces the world-state evidence that comic-cross-layer-gate `--gate continuity` adjudicates against the storyboard's MOTIF STATE TABLE (motif_ledger). It checks each baked panel STRICTLY against the pre-committed table row, then emits a continuity review-node the gate fuses (it does NOT own a bake-time KEEP). Gemini auto-gemini-3 is the per-panel FACT extractor (one analyzeFile per panel image, fact-only); Claude is the deterministic JUDGE against the table row + the global invariants (DDL countdown monotonic never-rewind, bounce S02 = the film's ONLY MAX, the two metric columns never co-mingle, the non-adjacent MIRROR LOCKS). CAST-AWARE: a panel simply NOT containing a character is design, NEVER a drift penalty (absence≠drift). On a same-panel miss it requests `retry_panel`; a cross-frame motif break is routed into the page assembly_gate's drift set (seed-anchored comic panels are independent — no cross-panel rollback). Use when the user says "查连续性", "continuity audit", "连戏检查", "world-state drift", "motif table check", "对一下分镜表", or a panel has been baked and you need to verify it realized its motif-table row.

10k tokens
Comic Blueprint Author
by wanshuiyin

Phase-1 (S7 of the comic-author suite) — turn ONE locked panel_spec into a deterministic content-SVG blueprint that becomes the bake condition (reference #1 of the agent mcp__codex__codex sidecar bake), by WRITING A PYTHON GENERATOR (never raw SVG in chat — LLMs botch coordinates). The HEADLINE comic-pivot rule: the image bakes NO bubbles at all — draw only characters + scene + leave negative-space SAFE ZONES; HTML/CSS owns the entire bubble. Every panel gets a content_svg (a figure OR a layout blueprint); a baked figure-panel must declare expected_literals verbatim. Single-source collision check is mandatory. Gated by comic-cross-layer-gate --gate blueprint. Use when the storyboard is locked and you need each panel's deterministic generation condition; do NOT use to bake the panel (that is comic-director) or to write the verdict-stamp/curve assets (that is comic-asset-ref-generator).

8k tokens
Comic Asset Review Loop
by wanshuiyin

Phase-1 (S5) UPSTREAM ref-asset gate — the bounded cross-model adversarial loop that LOCKS one reusable identity-locked asset (character sheet / location plate / prop cutout / text-panel / logo-free symbol) BEFORE it can be composited into any panel. This is NOT the panel_gate (composed-output) or the assembly_gate (cross-panel) — it gates the refs that FEED both, so identity drift is caught at the source, not downstream. Two layers: (1) a MANDATORY static single-source collision check (check_asset_collisions.py — 'one visual dialect, never two', enforced by tool) + zero-text/literal build-asserts; (2) a per-round 3-reviewer panel (Claude narrative ‖ Gemini visual ‖ Codex synth) that blind-scores 5 dims and LOCKS only at 准×3 unanimity (prior_lock_count>=3 approvals in the SAME round) — else regenerate (route to comic-asset-ref-generator) or, at MAX_REVIEW_ROUNDS, escalate the asset REQUIREMENT back to outline/storyboard. Hard IP veto. Use when you say 'lock this character ref', 'asset gate', 'ref review', 'is this sheet reusable', '锁角色 ref', before any metered panel bake.

10k tokens
Comic Cross Layer Gate
by wanshuiyin

The ONE parameterized score-fuser for EVERY comic-author authoring gate — `--gate intent|outline|asset|storyboard|blueprint|continuity|p0_proof|compile`. A single fuser (not a per-layer split) prevents drift. It NEVER re-runs a reviewer; it collects the reviewer score-nodes already on the wiki (via `reviews` edges), fuses them deterministically (min-fuse per dim, max for inverted dims, SKIP missing dims — never substitute 0), then a Codex xhigh adjudicator (NO model pin — follows the local codex config) that sees ONLY structured inputs (scores + tags + raw artifact PATHS + verbatim source context + verbatim rubric — NEVER reviewer prose) makes an asymmetric call (threshold HARD-vetoes "advance"; Codex SOFT-vetoes everything else). The `--gate p0_proof` mode is the zero-credit pre-production proof: a text-only cross-model adversarial review of the pipeline's CODE + IR-CONTRACT + ENGINE state-machine that MUST clear all blockers in BOTH non-author families and then MINT the digest-bound decision:p0_proof certificate via scripts/run_p0_proof.py BEFORE a single metered image-generation credit is spent. Use when a sibling step (intent-parser, outline-creator, asset-review-loop, storyboard-creator, blueprint-author, continuity-audit, json-compiler) defers its acquittal to "the gate", or the user says "过 gate", "cross-layer gate", "审这一层", "p0 proof", "证明流水线再花钱".

14k tokens scripts
Comic Blind Comparison Review
by wanshuiyin

Phase-1 comic-author step (post-final eval) — a DOUBLE-BLIND A/B of two FINAL whole comics: our cross-model-audited progressive render (the comic-author + comic-director output) vs a naive single-shot baseline. A single sealed coin-flip hides which is which; two cross-model reviewers (Codex + Gemini) score both on a fixed rubric reading only a SHARED blind spec (intent + ART_BIBLE); only AFTER both reviews land do we unseal, re-label, and write a Chinese comparison.md + the A/B verdict nodes. editability/traceability is the structural wedge that can win even when the baseline looks prettier. Use when the user says "和 baseline 比", "blind comparison", "A/B 评测", "对比 baseline", "盲评", "whole-comic vs one-shot", or a finished comic needs a baseline-relative honest verdict. NOT an authoring skill and NOT the per-panel panel_gate / assembly_gate — those run DURING production; this runs AFTER, on two complete works.

11k tokens
Comic Intent Parser
by wanshuiyin

Phase-1 Layer-0 of the comic-author suite — turn ANY raw idea / a locked video skeleton / an audience note into ONE schema-valid intent_spec node that fixes the logline (an editorial climax), the tagline, and the named DUAL-IDENTITY design constraint the whole comic optimizes against. Codex-as-parser (raw bytes + schema, never Claude's gloss) + reviewer-independence + banned-vocab lint + confidence-gated under_review routing + a HARD user-approval gate. It NEVER invents panels, assets, or storyboard detail, and NEVER silently defaults — every assumption becomes an uncertainties[] entry. Use it whenever a comic starts from a fuzzy brief and you need a locked, auditable premise before outlining.

6k tokens
Comic JSON Compiler
by wanshuiyin

Phase-1 (S9, the FINAL comic-author step) — assemble the LOCKED storyboard + locked per-panel blueprints into ONE schema-valid `comic.json` (the comic-ir/1.0 contract boundary handed to comic-director / run_comic.py). Project the page_order + each panel's condition{} + render fields into `pages[]` + keyed `panels{}` per schemas/comic.schema.json; author ONLY authored fields and leave image_path/active_attempt_id/wiki_node_id EMPTY for the engine. THE step where page-count integrity is reconciled and the orphan-panel class of bug is caught (a panel defined in panels{} that no page references — ship that and the finale silently vanishes) — caught by an INLINE whole-comic reconcile this skill runs (page_refs vs panels{} keys vs the storyboard page_order), because the deterministic scripts are per-page and the schema leaves condition/content_svg OPTIONAL. Gated by comic-cross-layer-gate --gate compile (the DETERMINISTIC gate: both run_comic.py --dry-run AND cli/validate_wiki.py must exit 0). Use when the user says '编译 comic.json', 'compile the comic', 'assemble comic.json', '出 comic.json', or the storyboard + all blueprints are locked and you need the single IR to hand to Phase 2/3. Do NOT use to author the page order (that is comic-storyboard-creator) or to bake panels (that is comic-director).

11k tokens
Comic Panel Prompt Builder
by wanshuiyin

Phase-1 step of comic-author — the DETERMINISTIC compiler (搬运工原則) that turns ONE gate-approved panel_spec + its status:locked blueprint into the EXACT fixed-section bake string for the spiral engine via the shipped scripts/build_prompt.py (+ the canonical scripts/_validate.py vetoes). No Codex call in the happy path; it only emits, the engine bakes. Composes style_prefix + condition_string, injects the active failure_mode repair note on retry, and hard-REJECTS banned vocab (camera/lens/lighting/quality padding). Routes html_bubbles[] to the JSON viewer overlay, NEVER into the bake string (no baked bubbles unless the panel is text_mode:baked). Refuses unless the upstream blueprint is status==locked (the cross-layer gate's hand-off token) and every ref is a REAL locked asset path. Use when a panel_spec is locked and you need its prompt_bundle, just before comic-director's panel_gate.

14k tokens scripts
Comic Style Bible Lock
by wanshuiyin

Phase-1 (S2) of the comic-author suite — compile the project's ART_BIBLE.md into an EXECUTABLE convergence target, not aesthetic prose. The bible is the ONE visual dialect read verbatim into every bake prompt AND into every visual reviewer's rubric (`style_consistency`/`identity_consistency` literally = 'conforms to this file'). A `bootstrap` parses the bible into immutable per-dimension `style_anchor` wiki nodes (palette / line / shading / two-world warm-vs-cyber lighting / identity-lock / per-world STYLE_PREFIX / text-mode / forbidden / by-design exceptions); a deterministic `validate` lints candidate authoring text against the FORBIDDEN list + identity-lock + world-mismatch; an append-only `update` Gemini-harvests recurring drift from KEEP panels into by-design exceptions. Auto-bootstrap if the bible is missing; otherwise LEAVE LOCKED. Locked anchors are immutable — pivoting the style = a fresh project, never an in-place edit.

8k tokens
Comic Outline Creator
by wanshuiyin

Phase-1 Layer-2 of a comic — turn a LOCKED skeleton (intent_spec + the pre-locked beat/shot list) into an approved outline_spec: a 6-column beat table that binds every ARIS capability to a STORY COST, plus the continuity-motif contract the storyboard layer will be held to. NOT free creation — editorial adaptation of a pre-locked skeleton via 3 parallel lenses → cross-model (Codex) synthesis → a density/restructure pass → a USER-approval HARD GATE. Cross-model synthesis is part of authoring here, not post-review. Author the comic.json downstream with comic-storyboard-creator + comic-blueprint-author; this skill only produces the outline + motif contract.

10k tokens
Comic Storyboard Creator
by wanshuiyin

Phase-1 comic-author step — turn a LOCKED, user-approved outline into the page-first storyboard that IS the authoring source of truth: a fixed page order BEFORE any prose, the MOTIF STATE TABLE (the master per-panel continuity ledger), a fixed 9-field per-panel spec, and one deduped canonical asset contract. Decompose beats→pages→panels, 抽卡 K page/panel-order lineages by feasibility, then fill every panel one unit at a time. Writes a storyboard_spec + a motif_ledger (read by comic-continuity-audit) + N panel_spec nodes. Use when the user says "做分镜", "storyboard", "排页", "panel spec", "分镜稿", or the outline layer is locked and approved and you need the per-panel authoring layer the thin comic-author SOP defers to. Two-stage under the N1 contract: a PROVISIONAL structural gate pass on draft assets now, the FINAL asset-resolution validation after the asset layer locks.

9k tokens

Claude Skills — questions

Answers built from the skills we actually parsed.

What is a Claude Skill?
A folder with a SKILL.md file: instructions that teach an agent to do one thing well, optionally with scripts and reference files alongside. The format is open and called Agent Skills — Claude Code, Codex and other agents read the same files. It is not a program you run; it is knowledge the agent loads when the task calls for it.
How is a skill different from an MCP server?
A server gives the agent new abilities — it connects to something and exposes tools. A skill gives the agent knowledge: how to use what it already has. They combine, and often literally: 11 329 of the skills here declare which MCP servers they need to work.
Why are there fewer skills here than in other catalogues?
Because we deduplicate by content. Of 79 354 files found on GitHub, 61 713 are unique — the rest is the same skill copied into someone else's repository, word for word. Catalogues that count files rather than skills show every copy as a separate entry.
What does the token count mean?
A skill is loaded into the model's context when it is used, so its size is a running cost on every request that touches it. We measure the whole folder, not just SKILL.md: one official skill is 377 tokens, another drags 83 files of fonts behind it.
How do I install a skill?
Copy the skill folder into ~/.claude/skills for personal use, or into .claude/skills inside a project. The agent picks it up by the name in the SKILL.md header — which is worth checking: 7 879 skills here share a name with another skill, and two of them cannot sit side by side.