Menu
Skills dans ce dépôt
SkillsMP a collecté 67 skills depuis shalomb/agent-skills. Ouvrez un skill pour examiner sa source et ses détails.
shalomb/agent-skillsAffichage de 27 skills collectés sur 67.
Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used…
Langue du texte source : anglais
Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user wants to: open, read, edit, or fix an existing .xlsx, .xlsm, .csv, or .tsv file (e.g., adding columns, computing formulas, formatting, charting,…
Langue du texte source : anglais
Configure and tune .codemap/config.json. Trigger this skill ONLY when codemap CLI output is overwhelmed by irrelevant files (like assets, generated code, or vendor folders), or when the prompt-submit hook explicitly suggests config-setup.
Langue du texte source : anglais
Systematic codebase exploration. Trigger this skill when you need to understand how a specific subsystem works, trace the downstream impact of a feature, find where a function is defined, or onboard to an entirely new area of the codebase.
Langue du texte source : anglais
Create and read cross-agent handoff artifacts. Trigger this skill when the conversation context window is full and you need to resume work in a new session, or when you are asked to pass your current progress to another autonomous agent (e.g., Claude, Cursor,…
Langue du texte source : anglais
Strict safety protocol for modifying hub files. Trigger this skill immediately when you discover a file is imported by 3 or more other files, when the codemap hook surfaces 'hub-safety', or when making structural changes to core architecture files.
Langue du texte source : anglais
Analyze codebase structure, dependencies, changes, and multi-agent handoffs using codemap. Use this skill as the primary entry point when a task requires understanding project architecture, mapping dependencies, tracing logic, or generating cross-agent…
Langue du texte source : anglais
Use this skill to orchestrate deep codebase exploration and complex structural refactoring by chaining Codemap, LSP Code Analysis, and AST Grep. Trigger this when asked to "safely refactor across the codebase", "trace this bug to its source", "explore the…
Langue du texte source : anglais
Launch Kiro CLI as a headless sub-agent in a tmux pane and monitor its completion. Use when delegating a well-defined coding task to a Kiro agent subprocess. Triggers include "run kiro agent", "delegate to kiro", "kiro sub-agent", or any request to run…
Langue du texte source : anglais
AWS CLI safety guardrails and account/role management for AI agents. Read before running any AWS CLI command. Covers environment setup, credential checking, account switching, pagination, and account-guard patterns. Triggers on any aws CLI invocation, account…
Langue du texte source : anglais
Diagnose and fix GitHub Actions workflow failures caused by Actions permissions policies — startup_failure with no jobs, third-party actions blocked, allowed_actions misconfiguration. Use when workflows fail immediately with no logs, or when actions from…
Langue du texte source : anglais
Create well-formed justfiles with test ladder patterns, standard recipes (install, build, test, clean, lint, dev, docs), and Makefile compatibility wrappers. Detects project type and generates appropriate recipes for Node.js, Python, Rust, Go, Terraform, and…
Langue du texte source : anglais
Set up and validate a modern Python publish pipeline — hatchling build backend, uv, twine token validation, PyPI/TestPyPI publishing via GitHub Actions. Use when packaging a Python project for PyPI, wiring a CI publish workflow, or diagnosing publish…
Langue du texte source : anglais
Set up and operate Google release-please for automated changelog, version bumping, and GitHub Release creation driven by Conventional Commits. Use when adding release automation to a repo, diagnosing release-please failures, or understanding why a Release PR…
Langue du texte source : anglais
Use this skill to upgrade and enforce the use of modern Rust/Go CLI equivalents over traditional POSIX coreutils. Trigger this whenever you are about to use grep, find, sed, awk, or ls in a shell command. You MUST read this skill to learn the syntax for rg…
Langue du texte source : anglais
Use this skill for structural code search, analysis, and automated refactoring using AST patterns (via sg/ast-grep). Trigger this whenever the user asks to "find all usages of", "rename this pattern", "refactor all X to Y", "extract all functions that", or…
Langue du texte source : anglais
Use this skill to diagnose codebase health, identify risk areas, and perform code archaeology via git history. Trigger this when onboarding to a new project, assessing technical debt, searching for lost code or deleted files, tracing function evolution, or…
Langue du texte source : anglais
Use this skill to extract full transcripts from video content for analysis, summarization, note-taking, or research. Trigger this whenever the user shares a YouTube URL, a video ID, or explicitly asks to "transcribe this", "get the text from this video", or…
Langue du texte source : anglais
Semantic code analysis via LSP. Navigate code (definitions, references, implementations), search symbols, get file outlines, and safely rename symbols. Use when exploring unfamiliar codebases, tracing call chains, or performing structural code changes. Prefer…
Langue du texte source : anglais
Use when developing, maintaining, or running API test plans with ATAC (Arguably a Terminal API Client). Covers creating collections, writing post-request assertion scripts, running tests headlessly, managing environments, and storing test plans in a git repo.…
Langue du texte source : anglais
Create, update, and review Architecture Decision Records (ADRs) using the Y-Statement format. Use when making a significant architectural decision, choosing between implementation approaches, or documenting a trade-off that future maintainers should…
Langue du texte source : anglais
Continuous validation during Terraform module development. Use when actively developing Terraform code and needing fast feedback loops — runs format, validate, lint, and plan automatically. Covers inner loop (fast, local) and outer loop (TFC deployment)…
Langue du texte source : anglais
Parse and analyse terraform plan plain-text output to classify resource changes, detect unintended mutations, and produce structured reports. Use when reviewing terraform plan output for import safety, drift detection, or plan validation. Triggers on "parse…
Langue du texte source : anglais
Manage the "Elastic Loop" of development by expanding and contracting test scope. Use when (1) coding in a "Fast-Fail" inner loop (3-5s), (2) graduating to a "Full-Validation" outer loop (2-3m), or (3) performing "Diagnostic Contraction" to a specific Unit…
Langue du texte source : anglais
Execute Harness.io IDP Scaffolder templates and workflows programmatically. Use this skill to list/discover workflows, components, APIs, query the service catalog, and launch infrastructure/deployment configurations. It can manage and audit API keys, track…
Langue du texte source : anglais
Refactor bloated AGENTS.md, CLAUDE.md, or similar agent instruction files to follow progressive disclosure principles. Splits monolithic files into organized, linked documentation. Use when asked to organize agent instruction files, improve documentation…
Langue du texte source : anglais
Analyze recent code changes via git history and extract software engineering lessons. Use when the user asks 'what is the lesson here?', 'what can I learn from this?', 'engineering takeaway', 'what did I just learn?', 'reflect on this code', or wants to…
Langue du texte source : anglais