Showing 35041–35070 of 45928 skills
Produce an implementation-ready, caller-first structural design for a sufficiently understood engineering problem. Manual invocation only; use when the user explicitly asks to architect a change or define its types, signatures, data structures, and module boundaries. Use brainstorm for unresolved future behavior and explain-code for a neutral current-code walkthrough.
drafael/coding-harness
Produce and compare at least two independent attempts at the same concrete artifact, then return one coherent synthesis with its verification result. Manual invocation only for direct use; an explicitly invoked workflow whose instructions permit arena delegation may run a bounded phase while retaining final judgment. Do not use to split a larger task into different work slices.
drafael/coding-harness
Analyze a concrete code change for credible breakage beyond the obvious diff and seek executable proof for the assumptions that make it safe. Manual invocation only; use for an explicitly requested blast-radius analysis of a local diff, commit range, branch comparison, or local patch.
drafael/coding-harness
Explore unresolved future behavior, architecture, ownership, features, or substantive alternatives through collaborative dialogue before implementation. Use when the user explicitly asks to brainstorm, explore options, or think through a future change, or when another active skill identifies consequential decisions that still need exploration. Use explain-code for neutral current-code walkthroughs, architect when explicitly invoked for implementation-ready structural design, and technical-writing when available to structure an agreed design.
drafael/coding-harness
Investigate expected-versus-actual behavior, suspected defects, and historical design rationale. Use when someone asks why observed behavior differs from expectations, whether behavior is wrong, or why a design decision exists. Use explain-code for neutral questions about what code does or how it works, and wrong when the user rejects the assistant's current approach.
drafael/coding-harness
Find actionable defects and risks through a focused, evidence-based review of correctness, regressions, security, performance, architecture, and testing. Use for requests to review, audit, critique, or identify improvements. Use blast-radius, when explicitly invoked and available, for cross-boundary consequence tracing and executable safety proof of a concrete change. Use explain-code when the user only wants to understand current behavior or architecture.
drafael/coding-harness
Systematically debug and fix errors using structured investigation. Use when the user asks to "debug", "fix an error", "troubleshoot", "investigate a bug", or shares an error message or stack trace.
drafael/coding-harness
Discover the OS, available CLI tools, and suitable execution environments to verify material migration, transaction, concurrency, API, service-integration, or runtime claims during planning, implementation, or review. Prefer isolated local verification; support explicitly user-approved endpoint discovery and invocation through OpenAPI/Swagger, CI/CD, and cloud tests. Recommend missing tools with OS-appropriate installation instructions tied to the claim. Own cleanup and report evidence, blockers, and limits. Not a general workstation-setup or deployment skill.
drafael/coding-harness
Explain current code behavior, structure, runtime flow, data flow, and component ownership. Use for ordinary walkthroughs, line-by-line explanations, subsystem mental models, and questions about what code does or how it works. Use teach, when explicitly invoked and available, for progressive learning; technical-writing, when available, for substantial standalone documentation; clarify for expectation mismatches or historical intent; code-review for finding problems; refactor-code for structural changes; brainstorm for unresolved future design; and architect, when explicitly invoked and available, for implementation-ready structural design.
drafael/coding-harness
Catch the user up on changes in the current chat and every decision or action still waiting on them. Manual invocation only; use when the user explicitly invokes ketchup or requests this catch-up workflow. Read-only; distinguish verified state from reports and unknowns.
drafael/coding-harness
Change existing code through narrow, behavior-preserving, test-backed simplification without speculative architecture or scope growth. Use for requests to refactor, clean up, restructure, or simplify code. Use explain-code instead when the user only wants an explanation of the current structure.
drafael/coding-harness
Review the current session for durable, evidence-backed improvements to existing local skills. Manual invocation only; use when the user explicitly asks to reflect or run a session retrospective. Never edit skills or perform external actions without individual approval.
drafael/coding-harness
Deepen a task without broadening its scope, then rewrite its prompt. Manual invocation only; use when the user explicitly invokes sharpen or requests this prompt-sharpening workflow. Do not execute the rewritten task or decide choices the user owns.
drafael/coding-harness
Use when the user wants to find NEW external skills for a project, build a skill stack from external registries, or compare external options against project needs. Do not use for questions about how to use already-installed/local skills.
drafael/coding-harness
Fix a bug by proving a focused regression check fails before the fix and passes after it. Manual invocation only; use when the user explicitly invokes tdd or requests this test-first bug-fix workflow. Do not force broad test infrastructure or claim unobserved red/green evidence.
drafael/coding-harness
Teach repository-backed code and engineering work through a progressive, evidence-grounded conversation. Manual invocation only; use when the user explicitly invokes teach to understand a change, subsystem, architecture, runtime behavior, or evidenced rationale. Read-only; do not modify files.
drafael/coding-harness
Write, revise, or review substantial technical documentation and design artifacts for a defined reader and task. Use for READMEs, guides, tutorials, how-to documentation, reference material, runbooks, RFCs, ADRs, technical specifications, and implementation plans. Use a design workflow first when future behavior or architecture needs exploration. Use unslop, when available, for small style-only edits. Do not use for code-only work, routine messages, release notes, PR descriptions, commit messages, or verbatim text.
drafael/coding-harness
Mandatory for every task in a TypeScript or mixed TypeScript codebase, including planning, implementation, debugging, refactoring, review, testing, dependency and build changes, CI, security analysis, and TypeScript-related documentation. Detect projects from tsconfig files, .ts/.tsx sources, TypeScript dependencies, or TypeScript framework configuration. Load before inspecting or changing such repositories. Covers Node.js, Bun, existing Deno projects, backend, frontend, CLI/TUI, Electron, Electrobun, Tauri, AWS CDK, and modern tooling.
drafael/coding-harness
Edit or review prose to remove formulaic AI-writing patterns while preserving facts, meaning, and the author's existing voice. Use for small style-only edits, articles, reports, messages, release notes, and other prose, or as the final pass after substantial technical writing. When technical-writing is available, use it first for substantial technical documentation and design artifacts. Do not use for code-only tasks or text that must remain verbatim.
drafael/coding-harness
Write unit, integration, component, and end-to-end tests for code. Use when the user asks to "write tests", "add tests", "add test coverage", or "create test cases" for functions, services, components, CLIs, or user flows.
drafael/coding-harness
Reset after the user rejects the assistant's current answer, plan, implementation, or problem-solving direction. Use for "your approach is wrong", "start over", "try a different approach", or when the attempted solution has demonstrably failed. Use clarify for incorrect system behavior and brainstorm when the user wants multiple new designs or alternatives.
drafael/coding-harness
Push branch and open a PR (assigned to @me, labeled, Closes
phel-lang/phel-pdo
Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.
nota-america/forgecat-agent-profiles
Run nf-core bioinformatics pipelines (rnaseq, sarek, atacseq) on sequencing data. Use when analyzing RNA-seq, WGS/WES, or ATAC-seq data—either local FASTQs or public datasets from GEO/SRA. Triggers on nf-core, Nextflow, FASTQ analysis, variant calling, gene expression, differential expression, GEO reanalysis, GSE/GSM/SRR accessions, or samplesheet creation.
nota-america/forgecat-agent-profiles
General-purpose visual-verification tool wrapping the plugin-bundled Playwright MCP server — navigate a URL, screenshot, check console errors, verify a page/component renders correctly. Usable standalone by any agent/skill in this plugin, any time — not tied to a production-track stage.
m3dcodie/eng-flow
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserve technical substance, code, URLs, and structure. Do compression directly with model judgment. Compressed version overwrites original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"
BumpyClock/agent-templates
Interactive longform-to-shortform video creator. Extracts viral-ready short clips from long videos using Claude as the orchestrator. Transcribes with faster-whisper (GPU), Claude scores and presents candidate segments interactively, user picks and adjusts, Remotion renders premium animated captions (Bold/Bounce/Clean styles), FFmpeg exports platform-optimized files (YouTube Shorts, TikTok, Instagram Reels). Use when user says "shorts", "short clips", "shortform", "extract clips", "tiktok from video", "reels from video", "vertical clips", or "create shorts".
AgriciDaniel/claude-shorts
Structure a conf-app bug report or incident write-up with User-First Trace — user journey first, then runtime evidence, then code path. Use when writing up a customer-reported bug, a production incident, a regression report, or a postmortem for the ZenUML Confluence app. Triggers on "write up this bug", "incident report", "bug report", "postmortem", "how should I frame this issue".
ZenUml/conf-app
Implement a piece of work based on a spec or set of tickets.
ZenUml/conf-app
Designing Campaign Hierarchy for program-level ROI tracking, configuring Customizable Campaign Influence (CCI) attribution models, and interpreting multi-touch attribution from MCAE B2B Marketing Analytics. Trigger keywords: campaign ROI, attribution model, campaign hierarchy, first-touch, last-touch, multi-touch, CCI, campaign influence, revenue attribution, campaign member status. NOT for deciding which attribution model and KPIs to adopt before any config - use admin/marketing-reporting-requirements. NOT for MCAE connector setup or the campaign sync that writes Campaign Member records - use admin/mcae-pardot-setup. Also covers: CampaignSettings, enableCampaignInfluence2, enableAutoCampInfluenceDisabled, enableB2bmaCampaignInfluence2, enableAccountsAsCM, CampaignInfluenceModel metadata, isDefaultModel, isModelLocked, recordPreference, AllRecords, RecordsWithAttribution, CampaignInfluence.RevenueShare, ModelType, CampaignMemberStatus IsDefault HasResponded SortOrder, HierarchyActualCost, HierarchyAmountWonOpportunities, TotalNumberofResponses, Opportunity.CampaignId primary campaign source.
PranavNagrecha/AwesomeSalesforceSkills