# โšก Ultra-Sharp Agent Skills ### A research-first skill-authoring system + 72 production-ready skills for AI agents [![Skills](https://img.shields.io/badge/skills-72-blueviolet?style=for-the-badge)](#-the-collections) [![Collections](https://img.shields.io/badge/collections-7-blue?style=for-the-badge)](#-the-collections) [![Lint](https://img.shields.io/badge/sharp--skill--lint-passing-brightgreen?style=for-the-badge)](#-quality-gate) [![Standard](https://img.shields.io/badge/Agent%20Skills-SKILL.md-orange?style=for-the-badge)](https://agentskills.io) [![Research First](https://img.shields.io/badge/method-research--first-8A2BE2)](RESEARCH-SYNTHESIS.md) [![Validated](https://img.shields.io/badge/validation-real%20execution%20evidence-success)](VALIDATION-REPORT.md) [![Python](https://img.shields.io/badge/tooling-python3%20stdlib%20only-3776AB?logo=python&logoColor=white)](tools/validate_skills.py) [![Claude Code](https://img.shields.io/badge/works%20with-Claude%20Code-D97757)](https://code.claude.com) [![Author](https://img.shields.io/badge/author-Simon--Pierre%20Boucher-informational)](mailto:contact@spboucher.ai) *Every skill: a trigger-optimized description, one default per decision, a validation-loop workflow,* *and pairwise-exclusive boundaries so no request ever fires two skills.*
--- ## ๐Ÿงญ What is this? **Skills** are folders of instructions (`SKILL.md` + resources) that AI agents load on demand. This repository was built in two phases, per [CLAUDE.md](CLAUDE.md): 1. ๐Ÿ”ฌ **Research** โ€” 20+ primary-source searches & fetches (Anthropic docs, `anthropics/skills`, engineering blogs, eval guides) distilled into **[RESEARCH-SYNTHESIS.md](RESEARCH-SYNTHESIS.md)**: 15 core principles, the **Sharp Skill Checklist**, and the ideal SKILL.md template. 2. ๐Ÿ—ก๏ธ **Build** โ€” 72 skills across 7 collections, each mechanically verified by a custom linter and validated with positive **and negative** trigger tests ([VALIDATION-REPORT.md](VALIDATION-REPORT.md)). ## ๐Ÿš€ Quickstart ```bash # install any skill into Claude Code (personal scope) cp -r doc-skills/processing-pdf ~/.claude/skills/ # or project scope cp -r backend-skills/designing-rest-apis .claude/skills/ # verify the whole repo (stdlib only, no dependencies) python3 tools/validate_skills.py . # checked 72 skill(s) # all checks passed ``` --- ## ๐Ÿ“š The Collections ### ๐Ÿ“„ doc-skills โ€” Document Processing ![10 skills](https://img.shields.io/badge/skills-10-blue) Create / read / modify every major document type. One default library per operation, re-parse validation after every write. | Skill | What it does | |---|---| | ๐Ÿ“Š [`processing-xlsx`](doc-skills/processing-xlsx/) | Excel workbooks with openpyxl โ€” values, formulas, formatting, multi-sheet | | ๐Ÿ“ [`processing-docx`](doc-skills/processing-docx/) | Word documents with python-docx โ€” paragraphs, tables, styles + pandoc reading | | ๐ŸŽž๏ธ [`processing-pptx`](doc-skills/processing-pptx/) | PowerPoint decks with python-pptx โ€” slides, layouts, tables, charts | | ๐Ÿ“• [`processing-pdf`](doc-skills/processing-pdf/) | Extract text/tables, create, merge, split, watermark, encrypt, fill forms | | ๐Ÿงพ [`processing-json`](doc-skills/processing-json/) | Create, modify, validate, and query JSON / JSON Lines | | ๐Ÿ—‚๏ธ [`processing-csv`](doc-skills/processing-csv/) | CSV/TSV create, edit, convert to/from JSON | | ๐Ÿท๏ธ [`processing-xml`](doc-skills/processing-xml/) | XML create, edit, validate, XPath queries โ€” namespace-safe | | โš™๏ธ [`processing-yaml`](doc-skills/processing-yaml/) | YAML configs โ€” safe_load discipline, round-trip edits, Norway-problem proof | | โœ๏ธ [`processing-markdown`](doc-skills/processing-markdown/) | Markdown create, restructure, convert via pandoc | | ๐ŸŒ [`processing-html`](doc-skills/processing-html/) | Local HTML โ€” extract text/tables/links, edit with BeautifulSoup | ### ๐ŸŽจ frontend-skills โ€” Frontend Design ![10 skills](https://img.shields.io/badge/skills-10-ff69b4) Grounded in Anthropic's `frontend-design` skill + 2026 standards (WCAG 2.2 AA ยท LCP โ‰ค2.5s ยท INP โ‰ค200ms ยท CLS โ‰ค0.1). | Skill | What it does | |---|---| | ๐Ÿ—๏ธ [`structuring-semantic-html`](frontend-skills/structuring-semantic-html/) | Landmarks, heading hierarchy, meaning-bearing markup, SEO/OG meta | | ๐Ÿ“ [`designing-responsive-layouts`](frontend-skills/designing-responsive-layouts/) | Mobile-first flexbox/grid, container queries, clamp() fluid sizing | | ๐ŸŽจ [`theming-design-tokens`](frontend-skills/theming-design-tokens/) | Token tiers, dark mode, spacing scales, contrast-safe palettes | | ๐Ÿ”ค [`choosing-typography`](frontend-skills/choosing-typography/) | Typeface pairing per brief, modular scales, font loading | | โ™ฟ [`ensuring-accessibility`](frontend-skills/ensuring-accessibility/) | WCAG 2.2 AA audits โ€” keyboard, focus, ARIA, contrast, targets | | โœจ [`crafting-ui-animations`](frontend-skills/crafting-ui-animations/) | Purposeful motion, transform/opacity only, reduced-motion always | | ๐Ÿงพ [`designing-forms`](frontend-skills/designing-forms/) | Labels, validation timing, error states, multi-step patterns | | โš›๏ธ [`building-react-components`](frontend-skills/building-react-components/) | Props APIs, composition, state placement, hooks | | ๐Ÿš€ [`optimizing-web-performance`](frontend-skills/optimizing-web-performance/) | Core Web Vitals budgets โ€” images, fonts, splitting, measurement | | ๐ŸŽฏ [`creating-landing-pages`](frontend-skills/creating-landing-pages/) | Hero thesis, CTA rhythm, one signature element, benefit-first copy | ### ๐Ÿ—„๏ธ db-skills โ€” Database Management ![10 skills](https://img.shields.io/badge/skills-10-336791) PostgreSQL-first with MySQL/SQLite deviations noted. Measure before changing anything. | Skill | What it does | |---|---| | ๐Ÿ” [`writing-sql-queries`](db-skills/writing-sql-queries/) | Correct, readable, injection-safe SQL โ€” CTEs, window functions, NULL traps | | ๐Ÿ“‹ [`designing-database-schemas`](db-skills/designing-database-schemas/) | 3NF-first modeling, keys, types, constraints, naming | | โšก [`optimizing-sql-performance`](db-skills/optimizing-sql-performance/) | EXPLAIN ANALYZE, indexing strategy, N+1, keyset pagination | | ๐Ÿ”€ [`managing-database-migrations`](db-skills/managing-database-migrations/) | Versioned, immutable, reversible; zero-downtime expandโ†’contract | | ๐Ÿ’พ [`backing-up-databases`](db-skills/backing-up-databases/) | Scheduled backups, PITR, 3-2-1 rule, restore drills | | ๐Ÿ” [`securing-databases`](db-skills/securing-databases/) | Least-privilege roles, parameterized-only queries, TLS, RLS, auditing | | ๐Ÿ˜ [`administering-postgresql`](db-skills/administering-postgresql/) | Roles, config knobs with starting values, autovacuum, monitoring | | ๐Ÿชถ [`managing-sqlite`](db-skills/managing-sqlite/) | WAL mode, pragmas, bulk-insert transactions, safe backups | | ๐Ÿ“ฆ [`modeling-nosql-data`](db-skills/modeling-nosql-data/) | Access-pattern-first design, embed vs reference, Redis key design | | ๐Ÿšจ [`troubleshooting-databases`](db-skills/troubleshooting-databases/) | 5-stage incident triage runbook with the exact query per stage | ### ๐Ÿ”ง backend-skills โ€” Backend Development ![20 skills](https://img.shields.io/badge/skills-20-success) | Skill | What it does | |---|---| | ๐Ÿ›ฃ๏ธ [`designing-rest-apis`](backend-skills/designing-rest-apis/) | Resources, status codes, pagination, versioning, problem+json, OpenAPI | | ๐Ÿ•ธ๏ธ [`designing-graphql-apis`](backend-skills/designing-graphql-apis/) | Schema-first, DataLoader vs N+1, cursor connections, complexity limits | | ๐Ÿ“ก [`designing-webhooks`](backend-skills/designing-webhooks/) | HMAC signing, backoff retries, idempotent delivery, DLQ | | ๐Ÿ“ค [`handling-file-uploads`](backend-skills/handling-file-uploads/) | Presigned URLs, magic-byte validation, streaming, resumable uploads | | ๐Ÿ”‘ [`implementing-authentication`](backend-skills/implementing-authentication/) | argon2id, sessions vs JWT, OAuth2/OIDC + PKCE, MFA, safe resets | | ๐Ÿ›‚ [`implementing-authorization`](backend-skills/implementing-authorization/) | RBAC/ABAC, deny-by-default, IDOR prevention, tenant isolation | | ๐Ÿงฐ [`validating-input`](backend-skills/validating-input/) | Boundary schemas, allowlists, canonicalization, structured 422s | | ๐Ÿ›ก๏ธ [`securing-backend-services`](backend-skills/securing-backend-services/) | Security headers, TLS, secrets, SSRF/CSRF defenses, safe errors | | ๐Ÿ’ฅ [`handling-errors`](backend-skills/handling-errors/) | Error taxonomy, problem+json, retries with jitter, circuit breakers | | ๐Ÿ”ญ [`instrumenting-observability`](backend-skills/instrumenting-observability/) | Structured logs, correlation IDs, RED metrics, OpenTelemetry | | ๐Ÿงช [`testing-backend-services`](backend-skills/testing-backend-services/) | Test pyramid, testcontainers, contract tests, zero flake | | ๐ŸŽ›๏ธ [`managing-configuration`](backend-skills/managing-configuration/) | 12-factor env config, typed startup validation, secret separation | | โณ [`writing-background-jobs`](backend-skills/writing-background-jobs/) | Idempotent jobs, backoff, DLQ, timeouts, queue observability | | ๐Ÿ“จ [`handling-async-messaging`](backend-skills/handling-async-messaging/) | Transactional outbox, idempotent consumers, schema versioning | | ๐Ÿ—ƒ๏ธ [`caching-strategies`](backend-skills/caching-strategies/) | Cache-aside, TTL discipline, invalidation, stampede protection | | ๐Ÿšฆ [`limiting-request-rates`](backend-skills/limiting-request-rates/) | Token bucket, 429 + Retry-After, tiered limits, load shedding | | ๐Ÿณ [`containerizing-services`](backend-skills/containerizing-services/) | Multi-stage builds, non-root, pinned images, healthchecks | | ๐Ÿšข [`shipping-with-ci-cd`](backend-skills/shipping-with-ci-cd/) | Build-once promotion, canary/blue-green, automated rollback | | ๐Ÿงฉ [`architecting-service-boundaries`](backend-skills/architecting-service-boundaries/) | Modular monolith default, data ownership, sagas, strangler | | ๐Ÿ“ˆ [`scaling-backend-services`](backend-skills/scaling-backend-services/) | Statelessness, pooling, load balancing, autoscaling on the right metric | ### โœ’๏ธ writing-skills โ€” Writing ![10 skills](https://img.shields.io/badge/skills-10-yellow) Stylistic skills: every rule ships with a โœ…/โŒ pair; every workflow ends in a self-review pass. | Skill | What it does | |---|---| | ๐Ÿ“– [`writing-technical-documentation`](writing-skills/writing-technical-documentation/) | READMEs, architecture docs, runbooks โ€” quickstart first, scannable | | ๐Ÿ”Œ [`writing-api-documentation`](writing-skills/writing-api-documentation/) | Endpoint reference with runnable examples, errors documented like successes | | ๐Ÿง‘โ€๐Ÿซ [`writing-tutorials`](writing-skills/writing-tutorials/) | Step-by-step guides โ€” every step has a verifiable checkpoint | | ๐Ÿ“ฐ [`writing-blog-posts`](writing-skills/writing-blog-posts/) | One specific claim, a real hook, real code and numbers | | ๐Ÿค– [`writing-agent-skills`](writing-skills/writing-agent-skills/) | **The meta-skill** โ€” author SKILL.md files with the Sharp Skill method | | ๐Ÿ“ง [`writing-professional-emails`](writing-skills/writing-professional-emails/) | Ask-first structure, decision-ready subject lines | | ๐Ÿ“Š [`writing-executive-summaries`](writing-skills/writing-executive-summaries/) | BLUF, one page, numbers over adjectives, a clear pick | | ๐Ÿค [`writing-proposals`](writing-skills/writing-proposals/) | Their problem first, scope exclusions, tiered pricing | | ๐Ÿ—’๏ธ [`writing-meeting-notes`](writing-skills/writing-meeting-notes/) | Decisions & actions first, every action has owner + deadline | | ๐Ÿช„ [`editing-and-proofreading`](writing-skills/editing-and-proofreading/) | Four fixed passes: structure โ†’ paragraphs โ†’ sentences โ†’ mechanics | ### ๐Ÿ’ฐ finance-skills โ€” US/Canada Tax & Accounting ![10 skills](https://img.shields.io/badge/skills-10-gold) ๐Ÿ‡บ๐Ÿ‡ธ ๐Ÿ‡จ๐Ÿ‡ฆ Tax-year-2026 figures with official verification sources. **Educational, legal planning only** โ€” every skill refuses evasion and refers complex cases to a CPA. | Skill | What it does | |---|---| | ๐Ÿงพ [`preparing-us-personal-tax-returns`](finance-skills/preparing-us-personal-tax-returns/) | Form 1040 โ€” documents, schedules, deadlines, safe harbors | | ๐Ÿ [`preparing-canadian-personal-tax-returns`](finance-skills/preparing-canadian-personal-tax-returns/) | T1 โ€” slips, deductions vs credits, NETFILE, instalments | | ๐Ÿ’ธ [`optimizing-us-personal-taxes`](finance-skills/optimizing-us-personal-taxes/) | 401(k)/IRA/HSA priority, Roth decisions, loss harvesting, bunching | | ๐Ÿ‡จ๐Ÿ‡ฆ [`optimizing-canadian-personal-taxes`](finance-skills/optimizing-canadian-personal-taxes/) | RRSP vs TFSA vs FHSA, legal splitting, superficial-loss rule | | ๐ŸŒ‰ [`handling-cross-border-taxation`](finance-skills/handling-cross-border-taxation/) | Residency tests, treaty tie-breakers, FBAR/8938, TFSA-for-US-persons trap | | ๐Ÿ“’ [`bookkeeping-for-small-businesses`](finance-skills/bookkeeping-for-small-businesses/) | Double-entry, chart of accounts, monthly close, reconciliation | | ๐Ÿ“‘ [`preparing-financial-statements`](finance-skills/preparing-financial-statements/) | Income statement, balance sheet, cash flow โ€” with cross-statement ties | | ๐Ÿข [`filing-us-business-taxes`](finance-skills/filing-us-business-taxes/) | Schedule C / 1065 / 1120-S / 1120, estimated taxes, payroll, 1099s | | ๐Ÿฌ [`filing-canadian-business-taxes`](finance-skills/filing-canadian-business-taxes/) | T2125, T2, GST/HST, payroll remittances, T4/T5 | | ๐Ÿงฎ [`optimizing-business-taxes`](finance-skills/optimizing-business-taxes/) | S-corp analysis (US) ยท SBD protection, salary vs dividends (Canada) | ### ๐Ÿ… The founding examples ![2 skills](https://img.shields.io/badge/skills-2-lightgrey) | Skill | What it does | |---|---| | ๐Ÿ”ฌ [`skill-1-profiling-csv-data`](skill-1-profiling-csv-data/) | Deterministic domain โ€” CSV data-quality reports via a bundled stdlib script (executed & verified) | | ๐Ÿ“ฃ [`skill-2-writing-release-notes`](skill-2-writing-release-notes/) | Stylistic domain โ€” benefit-first release notes with do/never examples | --- ## โœ… Quality Gate ![frontmatter](https://img.shields.io/badge/frontmatter-validated-brightgreen) ![descriptions](https://img.shields.io/badge/descriptions-Use%20when%20%2B%20Do%20not%20use-brightgreen) ![headers](https://img.shields.io/badge/author%20headers-100%25-brightgreen) ![links](https://img.shields.io/badge/reference%20links-0%20broken-brightgreen) ![budget](https://img.shields.io/badge/SKILL.md%20bodies-%E2%89%A4500%20lines-brightgreen) [`tools/validate_skills.py`](tools/validate_skills.py) (stdlib-only) mechanically enforces the Sharp Skill Checklist on every skill: valid frontmatter ยท name rules (โ‰ค64 chars, charset, reserved words, folder match) ยท description rules (โ‰ค1024 chars, literal "Use when โ€ฆ" trigger clause, "Do not use โ€ฆ" boundary, third person, no XML tags) ยท author header in every file ยท body โ‰ค500 lines ยท zero broken reference links ยท forward-slash paths only. ## ๐Ÿงฌ Design invariants (all 72 skills) 1. ๐ŸŽฏ **Description = trigger** โ€” WHAT + literal "Use when โ€ฆ" phrases + "Do not use โ€ฆ" boundary 2. ๐Ÿงฑ **Pairwise-exclusive boundaries** per collection โ€” no request can plausibly fire two skills 3. 1๏ธโƒฃ **One default per decision**, escape hatch named with its install command 4. ๐Ÿ” **Every workflow ends with a validation step** โ€” malformed input is reported, never guessed around 5. ๐Ÿชœ **Progressive disclosure** โ€” lean SKILL.md, depth one level deep in `references/` with a TOC ## ๐Ÿ“ Repository map ```text . โ”œโ”€โ”€ RESEARCH-SYNTHESIS.md # the method: 15 principles + Sharp Skill Checklist + template โ”œโ”€โ”€ VALIDATION-REPORT.md # trigger tests, execution evidence, checklist results โ”œโ”€โ”€ skill-1-profiling-csv-data/ skill-2-writing-release-notes/ โ”œโ”€โ”€ doc-skills/ (10) โ”œโ”€โ”€ frontend-skills/ (10) โ”œโ”€โ”€ db-skills/ (10) โ”œโ”€โ”€ backend-skills/ (20) โ”œโ”€โ”€ writing-skills/ (10) โ”œโ”€โ”€ finance-skills/ (10) โ”œโ”€โ”€ tools/validate_skills.py # the quality gate โ””โ”€โ”€ validation/ # fixtures + real outputs ```
**Author:** Simon-Pierre Boucher ยท **Contact:** [contact@spboucher.ai](mailto:contact@spboucher.ai) *Built research-first with [Claude Code](https://claude.com/claude-code) โ€” every figure sourced, every skill linted, every trigger tested.*