One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
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.
AnthropicSkillanthropics/cwc-workshops/research-desk/skills/edgartools/SKILL.md
How to pull SEC EDGAR data with the edgartools Python package — company lookup, filings, XBRL financial statements, and filing sections like Item 1A risk factors. Use whenever a task involves SEC filings, 10-K/10-Q data, or company financials.
AnthropicSkillanthropics/cwc-workshops/rightmodel/.claude/skills/eval-audit-and-sweep/SKILL.md
This skill is an example exercise for the "Picking the Right Model" workshop during Code with Claude. It is a two-phase playbook for getting trustworthy cost-quality numbers out of an existing LLM eval. Phase 1 audits the eval for common reliability issues. Phase 2 wraps it in a model/parameter sweep and produces a recommendation. The phases are independent: a user may ask for only the audit, only the sweep, or both. The skill contains guidance and example snippets only; it…
AnthropicAGENTS.mdanthropics/cwc-workshops/ship-your-first-managed-agent/AGENTS.md
This directory is a workshop. The person you are working with is here to learn Claude Managed Agents. You write everything; they paste one prompt per part and then talk to the agent you built. Work one part at a time. People type these in their own words. Match the intent, not the wording: One part per request, then stop. Do not start the next part, even if you can see its stubs and it looks easy. Leave the later…
AnthropicCLAUDE.mdanthropics/cwc-workshops/ship-your-first-managed-agent/CLAUDE.md
This directory is a workshop. The person you are working with is here to learn Claude Managed Agents. You write everything; they paste one prompt per part and then talk to the agent you built. Work one part at a time. People type these in their own words. Match the intent, not the wording: One part per request, then stop. Do not start the next part, even if you can see its stubs and it looks easy. Leave the later…
AnthropicSkillanthropics/cwc-workshops/ship-your-first-managed-agent/skills/incident-triage-runbook/SKILL.md
The SRE team's runbook for triaging production latency and error-rate incidents. Use this whenever investigating an incident, a latency spike, elevated error rates, or when asked "what caused X" about a production service.
AnthropicSkillanthropics/cwc-workshops/ship-your-first-managed-agent/skills/postmortem-report/SKILL.md
How the SRE team writes a postmortem PDF. Use this whenever asked for a postmortem, an incident report, a write-up to share, or a PDF of what happened.
AnthropicCLAUDE.mdanthropics/claude-agent-sdk-typescript/CLAUDE.md
Guidance for Claude Code and other coding agents working in this repository. Workflow jobs in this repository that call Claude run with three protections. Keep them when you add or…
No other project uses it yet
AnthropicAGENTS.mdanthropics/FlashProve/AGENTS.md
A provider commits to a model's weights with cp_commit, then proves with cp_prove that each reply passes an acceptance policy. Built from prover/, both run on one GPU. Clients check proofs on a CPU with cp_verify, the C++ verifier in verifier/. README.md, "For agents", has every route with what it needs and how long it takes. Run everything here from an ordinary account, not under sudo or as root. The programs, scripts and tests need no root rights, and as…
AnthropicCLAUDE.mdanthropics/buffa/CLAUDE.md
@CONTRIBUTING.md See DESIGN.md for the architectural overview. If a change to buffa-codegen (notably message.rs, impl_message.rs, view.rs, oneof.rs, enumeration.rs, imports.rs) affects generated output, you must regenerate checked-in code before committing, or CI (check-generated-code) will fail: Most codegen changes don't touch descriptor-specific paths, so gen-wkt-types and gen-option-types are usually sufficient. A quick check: git status after task lint — if buffa-types/src/generated/ or buffa-proto-options/src/generated/ shows as modified, you forgot to commit the regen. Before producing a commit, run both review agents in parallel…
AnthropicCLAUDE.mdanthropics/cwc-long-running-agents/claude-code-config/.claude/CLAUDE.md
The verify-gate hook will deny writes to test-results.json until you have opened evidence. Do not try to work around it.
AnthropicSkillanthropics/life-sciences/binder-gauntlet/SKILL.md
Validation and developability gauntlet for de novo designed protein binders and miniproteins against any protein target. Use this skill when designed binders are scored only by structure-predictor confidence (ipSAE, ipTM, pAE) and you must validate binding with independent re-prediction, pose agreement (DockQ) and controls, profile developability and sequence liabilities, check specificity and cross-reactivity, and write a validation dossier before you rank, filter or finalise binder designs, and at every selection round of a design campaign to steer it. Use when a user says "validate these binder designs", "run the gauntlet on these", "check developability" or "sequence liabilities", asks which designs should go to the lab, or asks for controls, a specificity panel or a validation dossier for designed binders.
AnthropicSkillanthropics/life-sciences/clinical-trial-forecast/SKILL.md
Forecasts one registered clinical trial's probability of success from registry records and documents the user supplies: checked research, a critiqued Monte Carlo model, a cited report and a claim ledger. Runs in Claude Science with Delegation on. Use when the user asks for a trial's probability of success, asks whether a named trial (an NCT id) will meet its primary endpoint, or asks to run the clinical-trial-forecast skill.
AnthropicSkillanthropics/life-sciences/clinical-trial-protocol-skill/SKILL.md
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for investigational products.
AnthropicSkillanthropics/k12-teacher-skills/plugin/skills/k12-check-for-understanding/SKILL.md
Creates a Check for Understanding (CFU) for a math topic or standard: 1–3 targeted formative items whose distractors come from documented student misconceptions, plus a teacher guide routing each likely response to a specific next instructional step. Load BEFORE asking any clarifying question about grade, standard, or topic. This skill is for math; for other subjects, help as you normally would and don't mention the skill to the user. Triggers on asks to create, write, generate, or design a check for understanding, formative check, quick check, or exit ticket for a math concept or standard, and on implicit signals like "I need to see who got it before I move on." Not a quiz, test, or practice set — a CFU is read for what it reveals, not scored, so a numbered quiz or a bare answer key is a different job. Does not create a lesson (k12-lesson-plan-creation, which brings its own exit ticket), tier one (k12-lesson-differentiation), or prepare a teacher to teach one (k12-lesson-prep).
AnthropicSkillanthropics/k12-teacher-skills/plugin/skills/k12-lesson-differentiation/SKILL.md
Adapts an existing K-12 lesson (math, ELA, science, or social studies) for students at different proficiency levels (below / at / above grade level). Load this skill BEFORE asking the teacher any clarifying question about the lesson, tiers, or student levels. Triggers on explicit asks to differentiate, tier, or scaffold a lesson, and on implicit signals like "my students are at different levels". Produces 1 teacher-facing differentiation plan + 3 student-ready tier documents as editable, printable documents in a single output turn (shared content is written once, so tiers cannot drift). Uses the Learning Commons Knowledge Graph when connected; works without it. This skill adapts a lesson the teacher brings or names. Not for creating a new lesson from scratch — a new-lesson request that asks for differentiated or leveled materials is k12-lesson-plan-creation's job, one package. Not for grading, rubrics, assessment feedback, or quizzes.
AnthropicSkillanthropics/k12-teacher-skills/plugin/skills/k12-lesson-plan-creation/SKILL.md
Creates a lesson plan, student-facing materials, and observation template. Load this skill BEFORE asking the teacher any clarifying question about grade, subject, topic, standard, or timing. Use when a K-12 teacher needs a math, ELA, science, or social studies lesson built from scratch — even if grade, subject, or topic isn't yet stated. Do NOT load for grading, a rubric, assessment feedback, a quiz, or a standards lookup — answer those directly. Triggers on explicit requests (lesson plan, mini-lesson, unit plan, daily plan) and implicit teacher intent: "I'm teaching long division to 5th graders," "need to teach photosynthesis tomorrow." Core signal: teacher needs new instructional content created. A new lesson that asks for differentiated, tiered, or leveled materials is still ONE planning request — this skill produces those materials inside the lesson package; do not also invoke k12-lesson-differentiation. Not for differentiating an existing lesson (use k12-lesson-differentiation) or passage rewrites.
AnthropicSkillanthropics/k12-teacher-skills/plugin/skills/k12-lesson-prep/SKILL.md
Helps a teacher prepare to teach an existing K-12 lesson (math / ELA / science / social studies) — a prep partner that thinks through the lesson's key student task with the teacher and leaves a short teacher-only prep note. Triggers on asks to internalize, prepare for, get ready to teach, or understand a lesson, including implicit ones ("help me get ready for tomorrow's lesson"), and right after another skill built a lesson, which it can follow. Not for building or adapting a lesson, grading, rubrics, assessment feedback, or generating quizzes or student-facing material, and not for single-fact lookups a sentence would answer ("what standard is this?", "how long is this lesson?").
AnthropicCLAUDE.mdanthropics/connect-rust/CLAUDE.md
@CONTRIBUTING.md Before producing a commit, run both review agents in parallel (single message, two Agent tool calls): - rust-code-reviewer — correctness, safety, ownership/lifetimes, performance - rust-api-ergonomics-reviewer — downstream-consumer perspective: happy-path friction, lints that fire in user crates, runtime footguns, doc drift, generated-code readability The two are complementary (different lenses on the same diff) and produce largely non-overlapping findings. Address all Critical, High, and Medium findings from both. For Low / advisory findings, flag these to the user to decide. For…
AnthropicCLAUDE.mdanthropics/healthcare/plugins/healthcare/CLAUDE.md
No summary in the file. Open it to read it.
AnthropicSkillanthropics/healthcare/plugins/healthcare/skills/clinical-note-extract/SKILL.md
Extract structured data from clinical notes with span-level provenance and null-safety. Use when users say "extract [variables] from this note", "abstract this chart", "pull structured data from these notes", "what does this note say about [field]", or when building a chart-abstraction, registry, or cohort dataset from unstructured clinical text.
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.
