A Claude Code skill is a folder containing a SKILL.md file with instructions, plus optional scripts and reference files, that Claude Code loads only when a task matches its description. Skills let you add a workflow or capability without filling the context window on every session.
What are the best Claude Code skills in 2026?
Few of the best Claude Code skills in 2026 are Superpowers for workflow, Graft for codebase context, grill-me for planning, frontend-design for UI and skill-creator for building your own.
| # | Skill | Use case | Best for | Grade |
|---|---|---|---|---|
| 1 | Superpowers | Workflow | Developers who want an enforced plan, test and review loop | ★★★★☆ |
| 2 | gstack (selective) | Workflow | Founders who want review, QA and ship commands | ★★★★☆ |
| 3 | GSD | Workflow | Spec-first builders of multi-phase features | ★★★★☆ |
| 4 | Compound Engineering | Workflow | Teams that want lessons written down after each change | ★★★★☆ |
| 5 | planning-with-files | Workflow | Multi-day tasks that outlive one session | ★★★★☆ |
| 6 | Karpathy guidelines | Workflow | Developers who want four behaviour rules at almost no cost | ★★★★☆ |
| 7 | handoff | Workflow | Passing a session to a fresh context | ★★★★☆ |
| 8 | grill-me / grill-with-docs | Planning | Anyone whose agent builds the wrong thing from a vague request | ★★★★☆ |
| 9 | Graft | Codebase context | Teams on large repos where Claude re-explores code every task | ★★★★☆ |
| 10 | Graphify | Codebase context | Mixed corpora of code, docs and papers | ★★★☆☆ |
| 11 | claude-mem | Memory | Carrying decisions across sessions | ★★★★☆ |
| 12 | Context7 | Library docs | Code written against fast-changing libraries | ★★★★☆ |
| 13 | /review (bundled) | Code review | Every branch before a pull request | ★★★★☆ |
| 14 | /simplify (bundled) | Code review | Cleaning up after a fast build | ★★★★☆ |
| 15 | /debug (bundled) | Debugging | Structured bug hunts | ★★★★☆ |
| 16 | /batch (bundled) | Parallel changes | The same change across many files | ★★★★☆ |
| 17 | tdd | Testing | Red, green, refactor discipline | ★★★★☆ |
| 18 | agent-browser | Verification | Long browser sessions on a tight context budget | ★★★★★ |
| 19 | webapp-testing | Verification | Checking a local web app really works | ★★★★☆ |
| 20 | playwright-cli | Verification | Teams already on Playwright | ★★★★☆ |
| 21 | Trail of Bits skills | Security | Security-sensitive code audits | ★★★★☆ |
| 22 | /security-review (bundled) | Security | A default security pass on a diff | ★★★★☆ |
| 23 | git-guardrails-claude-code | Security | Blocking destructive git commands | ★★★★☆ |
| 24 | frontend-design | Frontend | UI that does not look machine-made | ★★★★☆ |
| 25 | impeccable | Frontend | Design audit and polish passes | ★★★★☆ |
| 26 | ui-ux-pro-max | Frontend | Generating a design system | ★★★★☆ |
| 27 | vercel-react-best-practices | Frontend | React and Next.js performance | ★★★★☆ |
| 28 | web-design-guidelines | Frontend | Accessibility and UX review of existing UI | ★★★★☆ |
| 29 | supabase-postgres-best-practices | Stack | Postgres queries and schemas | ★★★★☆ |
| 30 | cloudflare/skills | Stack | Workers and edge deployments | ★★★★☆ |
| 31 | stripe-best-practices | Stack | Payment and webhook integrations | ★★★★☆ |
| 32 | terraform-style-guide | Stack | Infrastructure as code | ★★★★☆ |
| 33 | Expo skills | Stack | React Native apps | ★★★★☆ |
| 34 | Remotion best practices | Stack | Programmatic video | ★★★★☆ |
| 35 | SwiftUI Agent Skill | Stack | iOS apps | ★★★★☆ |
| 36 | skill-creator | Building skills | Anyone writing their own skill | ★★★★☆ |
| 37 | mcp-builder | Building MCP | Building an MCP server | ★★★★☆ |
| 38 | find-skills | Discovery | Finding a skill for a task | ★★★★☆ |
| 39 | claude-api | Building on the API | Apps built on the Claude API | ★★★★☆ |
| 40 | Document skills | Documents | Creating Word, PDF, PowerPoint and Excel files | ★★★★★ |
| 41 | claude-scientific-skills | Research | Scientific databases and literature | ★★★★☆ |
| 42 | obsidian-skills | Notes | Obsidian vaults | ★★★★☆ |
| 43 | Caveman | Token cost | Cutting output tokens | ★★★★★ |
| 44 | humanizer | Writing | Removing machine-sounding phrasing | ★★★★☆ |
| 45 | marketingskills | Marketing | CRO, SEO and copy tasks | ★★★★☆ |
Most entries score four stars because stars and installs show adoption, not results. Only three have independent measurements, and one relies on its maintainer's own benchmark.
How were these 45 Claude Code skills chosen and graded?
These 45 Claude Code skills were chosen from independent developer blogs, GitHub repositories, install data from skills.sh, and posts by the Claude Code team. Each skill then received a star rating of five, four or three, based on who measured it and how. Popularity alone never earns the top grade.
| Grade | What it means | Example in this guide |
|---|---|---|
| ★★★★★ | A third party measured the skill against a baseline | agent-browser, Caveman, Document skills |
| ★★★★☆ | Adoption data only: stars or installs | Superpowers, frontend-design |
| ★★★☆☆ | The maintainer's own benchmark, not yet replicated | Graphify |
Which Claude Code skills should you install first?
Install Superpowers, Graft, grill-me, frontend-design and skill-creator first. Together these five Claude Code skills cover the plan-and-test loop, codebase context, requirement gathering, UI quality and building your own skills. Drop frontend-design if you never touch UI, and drop skill-creator if you never write skills.
| Skill | What it replaces | Install | Evidence | Skip if |
|---|---|---|---|---|
| Superpowers | Your own plan, test and review discipline | /plugin install superpowers@claude-plugins-official | 291k stars on 24 Sep 2026 (source) | You mostly make one-line fixes |
| Graft | Claude re-reading the repo at the start of every task | npm install -g @nanonets/graft then graft init | Resolved 33 of 50 SWE-bench Verified instances against 27 without it, self-reported (source) | Your repo is small enough to read in one pass |
| grill-me | Explaining a feature three times | npx skills@latest add mattpocock/skills/grill-me | 956,585 installs on 25 Aug 2026 (source) | The task is already fully specified |
| frontend-design | Your paragraph of design instructions | /plugin install frontend-design@claude-plugins-official | 827,809 installs (source) | You never build UI |
| skill-creator | Guessing whether your skill triggers | /plugin install skill-creator@claude-plugins-official | Runs each test prompt with and without the skill (source) | You only use other people's skills |
The carrying cost of this set is low. One measurement on 24 September 2026 put Superpowers at about 550 tokens per session plus 750 at startup, frontend-design at about 50, and skill-creator at about 80 (Build This Now).
What are the best Claude Code skills for workflow and planning?
The best Claude Code skill for workflow is Superpowers, and the best for planning is grill-me. Superpowers enforces a brainstorm, plan, test and review sequence automatically. grill-me interviews you until the requirements are clear. Pick one workflow layer only, because two will compete for the same request.
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| Superpowers | Chains brainstorming, planning, test-driven development and review | /plugin install superpowers@claude-plugins-official | 291k stars on 24 Sep 2026 (source) | You mostly make quick edits |
| grill-me / grill-with-docs | Interviews you on every branch of a design before code is written | npx skills@latest add mattpocock/skills/grill-me | 273k repo stars on 1 Oct 2026; 956,585 installs (source) | The spec is already written |
| gstack | Adds role-based commands such as /review, /qa and /ship | git clone the repo into ~/.claude/skills/gstack, then ./setup | 82,700 stars in April 2026 (source) | You already run Superpowers |
| GSD | Breaks work into specs and gives each task a fresh subagent | npx get-shit-done-cc@latest | 64.4k stars (source) | The change is a one-file fix |
| Compound Engineering | Runs a plan, build, review loop and records what was learned | /plugin install compound-engineering@compound-engineering-plugin | 25.3k stars; 36 skills (source) | You want a small, unopinionated setup |
| planning-with-files | Keeps the plan, findings and progress in markdown files on disk | See the OthmanAdi/planning-with-files README | 17,700+ stars in March 2026 (source) | Your tasks finish in one short session |
| Karpathy guidelines | Applies four rules: think first, keep it simple, change little, work to a goal | /plugin install andrej-karpathy-skills@karpathy-skills | 215.1k stars on 25 Sep 2026 (source) | The four rules do not match how you work |
| handoff | Writes a summary so a fresh session can continue the work | npx skills@latest add mattpocock/skills and pick handoff | Listed as a situational pick by an independent reviewer (source) | Your sessions rarely run long |
Superpowers suits developers who want the process to trigger on its own. gstack suits those who prefer to call each step by hand. A single gstack command can load roughly 18,000 to 33,000 tokens, so keep only the commands you use (Build This Now).
What are the best Claude Code skills for codebase context and memory?
The best Claude Code skill for codebase context is Graft. Graft builds a graph of your code once, then feeds Claude Code the relevant parts on each prompt, so the agent stops re-exploring the repo. For memory across sessions use claude-mem, and for current library documentation use Context7.
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| Graft | Builds a tree-sitter code graph and injects matching nodes into each prompt | npm install -g @nanonets/graft then graft init | 9.4k stars on 1 Oct 2026; 42% fewer tokens in a 162-run test, self-reported (source) | Your repo is small |
| Graphify | Turns code, docs, papers and images into one queryable graph | graphify install after installing the package | 110,152 stars on 25 Aug 2026 (source) | You only need code, not documents |
| claude-mem | Captures each session and feeds relevant parts into the next | npx claude-mem install | 94.7k stars on 25 Sep 2026 (source) | You prefer plain notes in the repo |
| Context7 | Fetches current, version-matched library documentation | See the upstash/context7 README | 62.4k stars on 25 Sep 2026 (source) | Your stack is stable and well known |
What does Graft change in a Claude Code session?
Graft makes Claude Code cheaper and more accurate on multi-file fixes, according to its maintainers' benchmark. They ran 50 SWE-bench Verified instances with Claude Sonnet 5, using the official grader, with and without Graft (Graft README).
| Measure | Claude Code alone | Claude Code with Graft |
|---|---|---|
| Instances resolved | 27 of 50 (54%) | 33 of 50 (66%) |
| Tokens | 142.0M | 109.4M |
| Cost | $52.34 | $42.43 |
| Tool calls | 1,370 | 1,031 |
| Wall-clock time | 13,094 s | 8,922 s |
- Why the gap appears: the maintainers report that the baseline tends to patch one file and miss related files the fix needs.
- What it installs: a skill file, hooks, a statusline and an MCP server, with the graph stored as local files.
- What it costs to run: the structural graph uses tree-sitter only, so it needs no model and no API key.
- Read the rating: no third party has replicated these figures yet.
Graft and Graphify differ in scope. Graft is built for code and refreshes its graph before every query. Graphify covers documents and images too, and one review found its 71x token saving is the upper bound of a 6x to 49x normal range (source).
What are the best Claude Code skills for code review, testing and verification?
The best Claude Code skills for code review are the bundled ones, starting with /review, because they need no install. For verification, use webapp-testing on local apps and agent-browser for long browser sessions. Anthropic says verification skills have had the most measurable effect on Claude's output quality inside the company (Anthropic).
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| /review | Reviews a diff before a pull request | Bundled with Claude Code | Ships by default (source) | Never; it costs nothing to keep |
| /simplify | Cleans up code after a fast build | Bundled with Claude Code | Ships by default (same source) | You already review for simplicity by hand |
| /debug | Runs a structured debugging pass | Bundled with Claude Code | Ships by default (same source) | The bug is a typo |
| /batch | Applies one change across many files in parallel | Bundled with Claude Code | Ships by default (same source) | The change touches one file |
| tdd | Enforces a red, green, refactor loop one slice at a time | npx skills@latest add mattpocock/skills/tdd | Part of a repo with 273k stars on 1 Oct 2026 | You run Superpowers, which includes its own |
| webapp-testing | Writes Playwright scripts to check a local web app | Copy the webapp-testing folder into ~/.claude/skills/ | About 50 tokens idle, 900 when used (source) | You already run the Playwright MCP server |
| agent-browser | Drives a browser through a command-line tool with compact page snapshots | npx skills add vercel-labs/agent-browser --skill agent-browser | 1,364 tokens against 7,779 for Playwright MCP on a six-step test, measured independently (source) | Speed matters more than context size |
| playwright-cli | Gives Claude Code Playwright commands without the MCP tool schemas | /plugin install playwright-cli after adding the microsoft/playwright-cli marketplace | Described by Microsoft as more token-efficient than its MCP server; no figure published | You do not use Playwright |
Start with the bundled commands and add one browser tool. webapp-testing and the Playwright MCP server solve the same problem, so keep only one of them.
What are the best Claude Code skills for security?
The best Claude Code skills for security are the Trail of Bits skills, which wrap real static analysis tools such as CodeQL and Semgrep. Pair them with the bundled /security-review command for everyday diffs. Add git-guardrails-claude-code to block destructive git commands before Claude Code can run them.
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| Trail of Bits skills | Runs static analysis, differential review and variant analysis | npx skills add trailofbits/skills | 7.3k stars in September 2026; maintained by a security research firm (source) | Your code is not security sensitive |
| /security-review | Reviews a diff for security problems | Bundled with Claude Code | Ships by default (source) | Never; it is already installed |
| git-guardrails-claude-code | Uses hooks to block push, hard reset, clean and branch deletion | npx skills@latest add mattpocock/skills and pick git-guardrails-claude-code | Blocks the command before it executes (source) | You already enforce this with your own hooks |
A skill is an instruction the model can ignore, while a hook is code that always runs. For anything that must never happen, such as a force push, rely on a hook.
What are the best Claude Code skills for frontend and design?
The best Claude Code skill for frontend work is Anthropic's frontend-design, which steers Claude Code away from generic layouts, fonts and colour schemes. Use impeccable to audit and polish an existing interface. React and Next.js teams should add vercel-react-best-practices for performance rules.
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| frontend-design | Makes Claude commit to a design direction and avoid common machine-made tells | /plugin install frontend-design@claude-plugins-official | 827,809 installs (source); about 2,300 tokens when used (source) | You never build UI |
| impeccable | Audits and polishes UI with 24 commands and 61 detector rules | npx skills add https://github.com/pbakaus/impeccable --skill impeccable | 72.9k stars in September 2026 (source) | frontend-design already gives you enough |
| ui-ux-pro-max | Generates a design system with styles and palettes | npx skills add ui-ux-pro-max | 333,889 installs and 122,064 stars (source) | You already have a design system |
| vercel-react-best-practices | Applies 57 React and Next.js performance rules | npx skills add https://github.com/vercel-labs/agent-skills --skill vercel-react-best-practices | 208K installs in March 2026 (source) | You do not use React |
| web-design-guidelines | Reviews existing UI against 100+ accessibility and UX rules | npx skills add https://github.com/vercel-labs/agent-skills --skill web-design-guidelines | 164K installs in March 2026 (same source) | You have a dedicated accessibility review |
frontend-design improves what Claude generates. web-design-guidelines and impeccable review what already exists. Most teams need one from each side, not all five.
What are the best Claude Code skills for specific stacks?
The best Claude Code skills for a specific stack are the official ones published by the vendor, such as Supabase for Postgres, Cloudflare for Workers and Stripe for payments. Vendor skills encode rules the model often gets wrong. Install only the ones that match what your project actually runs.
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| supabase-postgres-best-practices | Applies 30 Postgres rules on queries, indexes and row-level security | npx skills add supabase/agent-skills --skill supabase-postgres-best-practices | Published by Supabase (source) | You do not use Postgres |
| cloudflare/skills | Covers Workers, Pages, D1, R2 and about 40 other services | npx skills add cloudflare/skills | Official Cloudflare repository (same source) | You deploy elsewhere |
| stripe-best-practices | Guides checkout, subscription and webhook integrations | See Stripe's skills repository | Official Stripe skill; no install figure found | You do not take payments |
| terraform-style-guide | Writes Terraform in HashiCorp's official style | See HashiCorp's skills repository | Official HashiCorp skill; no install figure found | You do not use Terraform |
| Expo skills | Guides React Native builds and deployment | See Expo's skills repository | 283,306 installs across Expo's skills on 25 Aug 2026 (source) | You do not build mobile apps |
| Remotion best practices | Teaches programmatic video with React | npx skills add remotion-dev/skills | 305,359 installs across Remotion's skills on 25 Aug 2026 (same source) | You do not generate video |
| SwiftUI Agent Skill | Applies SwiftUI best practices | See the AvdLee/SwiftUI-Agent-Skill README | Listed among repositories with 1,000+ stars (source) | You do not write Swift |
Vendor skills are the safest third-party installs because the publisher is known. They still add to your skill listing, so remove them when a project ends.
What are the best Claude Code skills for building skills and MCP servers?
The best Claude Code skill for building your own skills is skill-creator from Anthropic. It tests a skill against a no-skill baseline and rewrites the description so the skill triggers. For MCP servers use mcp-builder, and for work on the Claude API use the claude-api skill.
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| skill-creator | Runs evals with a baseline, blind comparisons and description tuning | /plugin install skill-creator@claude-plugins-official | About 80 tokens idle, 8,200 when used (source) | You never write skills |
| mcp-builder | Guides an MCP server through research, build, review and evaluation | Copy the mcp-builder folder into ~/.claude/skills/ | About 70 tokens idle, 2,200 when used (same source) | You only consume MCP servers |
| find-skills | Searches the skills.sh directory for a skill that fits a task | npx skills add vercel-labs/skills --skill find-skills | 3,093,773 installs on 25 Aug 2026 (source) | You already know which skills you want |
| claude-api | Gives Claude current API and SDK reference material | Bundled with Claude Code | Body is roughly 21,000 tokens when loaded (source) | You do not build on the Claude API |
skill-creator is the one skill that improves every other skill you write. find-skills is the most installed skill on skills.sh, but treat what it finds as untested until you have read it.
What are the best Claude Code skills for documents, research and notes?
The best Claude Code skills for documents are Anthropic's document skills, which create Word, PDF, PowerPoint and Excel files. For scientific research use claude-scientific-skills from K-Dense. For personal notes use obsidian-skills, written by the chief executive of Obsidian.
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| Document skills | Creates and edits docx, pdf, pptx and xlsx files | /plugin install document-skills@anthropic-agent-skills | Practitioner testing found docx clearly improved output while xlsx made no significant difference (source) | Your repo never produces Office files |
| claude-scientific-skills | Connects Claude to 250+ scientific databases through 148+ skills | See the K-Dense-AI/claude-scientific-skills README | 11.5K+ stars (source) | You do not do research work |
| obsidian-skills | Teaches Claude Obsidian Markdown, Bases, JSON Canvas and the Obsidian CLI | npx skills add kepano/obsidian-skills | 49k stars (source); 360.8K installs in June 2026 (source) | You do not use Obsidian |
The document skills earn five stars only for Word output. Install the bundle if you generate documents often, and leave it out of coding-only projects.
Which Claude Code skill cuts token costs the most?
Caveman is the best-known Claude Code skill for cutting token costs. It makes Claude answer in terse, stripped-down language while leaving code unchanged. Expect a modest saving on real coding work: an independent JetBrains test found 8.5% fewer output tokens, far below the 65% in the project's own benchmark.
| Test | Who ran it | Result |
|---|---|---|
| 10 prompts against default verbose replies | Caveman maintainers | 65% fewer output tokens on average, range 22% to 87% |
| 86 real coding tasks, paired A/B, skill only | JetBrains | 8.5% fewer output tokens, quality unchanged |
- Install:
claude plugin marketplace add JuliusBrussee/caveman && claude plugin install caveman@caveman - Adoption: 108.7k stars on 1 October 2026 (Caveman repository).
- Hidden cost: the skill only shortens output, and its own rules add about 1,000 to 1,500 input tokens per turn.
- Skip if: most of your output is already code, where there is little prose to cut.
Both results come from the Caveman repository, which publishes the JetBrains figure alongside its own. Savings are largest when Claude would have written long explanations.
What are the best Claude Code skills for writing and marketing?
The best Claude Code skills for writing and marketing are humanizer and marketingskills. humanizer removes phrasing patterns that make text read as machine-written. marketingskills is a pack of 32 skills by Corey Haines covering conversion optimisation, SEO, copywriting and growth tasks.
| Skill | What it does | Install | Evidence | Skip if |
|---|---|---|---|---|
| humanizer | Rewrites text to remove common machine-writing patterns | See the blader/humanizer README | 11,700+ stars in March 2026 (source) | You only write code |
| marketingskills | Adds 32 procedures for CRO, SEO, copy and growth work | npx skills add coreyhaines31/marketingskills | 281.9K installs across 32 skills in 2026 (source) | You have no marketing tasks |
Both are procedure skills, so they encode a method, not new abilities. Install single skills from the marketing pack instead of all 32.
How many Claude Code skills should you install at once?
Install three to five public Claude Code skills at a time. Every installed skill adds its description to a listing with a fixed budget, and Claude Code shortens or drops descriptions once the budget is full. Skills also help only on the tasks they cover and add noise everywhere else.
| Finding | Number | Source |
|---|---|---|
| Skills from one popular collection that made output worse | 40 of 47 | Mikhail Shcheglov, via Kyle Redelinghuys |
| Task success with a skill that covers the task | 89.4% against 55.9% baseline | MacAgentBench, same article |
| Models that did worse with skills on uncovered tasks | 5 of 8 | MacAgentBench, same article |
| Skill listing budget in current Claude Code | 1% of the context window | Build This Now, citing the Claude Code docs |
Check your own setup in three steps:
- Run
/contextto see how much of the window the skill listing uses. - Run
/doctorto see whether descriptions are being cut and which skills cost the most. - Remove or disable any skill you have not invoked in the last two weeks.
When the budget overflows, Claude Code trims the skills you use least first. A skill that stops firing may have lost the keywords that triggered it.
Do Claude Code skills actually fire when needed?
Claude Code skills often fail to fire. In Vercel's agent evals, the skill was never invoked in 56% of cases, and nothing in the session reported the miss. Skills fire far more reliably when the description is written as a direct instruction that names when to use the skill.
| Setup in Vercel's eval | Pass rate |
|---|---|
| No documentation | 53% |
| Skill installed, default behaviour | 53% |
| Skill plus explicit instructions to use it | 79% |
| Compressed 8KB docs index in AGENTS.md | 100% |
Source: Vercel, AGENTS.md outperforms skills in our agent evals.
A separate 650-sample study by Ivan Seleznov found directive descriptions reached 100% activation, against 37% for passive ones (source).
- Put always-needed rules in CLAUDE.md, because that file loads on every turn.
- Write the description as a trigger, for example: use when writing a git commit message for staged changes.
- Invoke important skills by name with
/skill-namewhen the result matters. - Use a hook for anything that must happen every time.
Are third-party Claude Code skills safe to install?
Third-party Claude Code skills are not safe by default. A skill runs with the same permissions as Claude Code, including shell access, file access and any credentials in your environment. Snyk audited 3,984 public skills in February 2026 and found critical security issues in 13.4% of them.
| Finding from Snyk's audit | Number |
|---|---|
| Skills audited across public hubs | 3,984 |
| Skills with at least one flaw | 36.82% |
| Skills with a critical issue | 534 (13.4%) |
| Skills with a confirmed malicious payload | 76 |
Source: Snyk, ToxicSkills, as summarised by Kyle Redelinghuys.
Vet a skill before you install it:
- Read every file in the folder, not only
SKILL.md, because scripts hold the real behaviour. - Search for red flags such as instructions to hide actions from the user, or
curl | bashin an install step. - Check the publisher: a known vendor or a long-standing maintainer is lower risk than a week-old account.
- Limit what the skill can touch with
allowed-toolsand a deny list that includes.env. - Review it again on every update, since a safe skill can change.
Which popular Claude Code skills should you skip or use selectively?
Skip any Claude Code skill that duplicates one you already run, and use large packs selectively. The clearest case is Superpowers and gstack together: both try to own the plan, build, review and ship loop, so a single request triggers two competing processes. Choose one workflow layer.
| Skill or pack | Verdict | Reason |
|---|---|---|
| Superpowers plus gstack | Pick one | Both claim the same workflow |
| gstack, whole pack | Keep two or three commands | About 60 skill files, with single commands of 18,000 to 33,000 tokens |
| Anthropic's example-skills bundle | Take single skills | Eight of the twelve are demonstrations, not coding tools |
| Document skills | Skip in coding-only repos | Long descriptions use listing budget for nothing |
| claude-api | Skip unless you build on the API | Roughly 21,000 tokens when it loads |
| Caveman | Try, then measure | Independent saving was 8.5%, not 65% |
| Any persona-only skill | Skip | A line in CLAUDE.md does the same job |
Pack sizes and token figures come from a measurement on 24 September 2026 (Build This Now).
One more test helps: ask whether the skill teaches Claude something a newer model will learn anyway. Skills that encode your own preferences last, while skills that patch a model gap stop paying off after the next release.
When should you write your own Claude Code skill?
Write your own Claude Code skill when Claude repeats a mistake that is specific to your codebase, or when you paste the same instructions for the third time. Custom skills that encode your team's checks outlast public ones. Anthropic reports that verification skills have had the most measurable effect on Claude's output quality internally.
- List the failures Claude made in your repo this week that a generic reviewer would not catch.
- Write three test scenarios and record how Claude performs without any skill.
- Write the shortest instructions that fix those failures, and put long detail in reference files.
- Write the description as a trigger in the third person, stating what the skill does and when to use it.
- Add a gotchas section from real failures, since no model already knows them.
- Measure against the baseline with skill-creator, then keep the skill only if it wins.