bostonaholic · Agent Skills
43 Skills con documentación sustancial y fuentes verificadas. Abre una tarjeta para leer las instrucciones originales y revisar el paquete y la instalación.
writing-system-prompts
Writes and reviews system prompts for AI tools, agents, chatbots, and LLM products using a fixed section order and a quality checklist. Use when the user says "write a system prompt", or when drafting a system prompt or auditing one for missing stop criteria, tool rules, constraints, or examples. Not for compressing an existing prompt; use improving-prompts.
- Instalaciones / 1h
- 4
- GitHub Stars
- 2
- Actualizado
- 29 oct
addressing-pr-comments
Triages open PR feedback, verifying each review thread, review summary, and comment against the code, auto-applying fixes above 90% verified confidence, and recommending one option for the rest. Use when the user explicitly asks to address or fix PR comments. Never infer from unresolved comments.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 20 oct
auditing-agent-token-usage
Audits recent Claude Code and Codex session logs for token and context cost: model routing, inherited subagent models, long sessions, compactions, oversized tool results, and unused MCP servers. Use when the user says \"audit token usage\", or when asked about agent token usage, context costs, session length, model routing, or cost efficiency.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
auditing-complexity
Ranks where code complexity concentrates in a git repository (cyclomatic complexity, nesting, fan-out, mutable state) and scores CRAP change risk from a coverage file. Read-only. Use when the user says "find complexity hotspots", or when asked for complexity hotspots or change risk. Not for test value; use auditing-tests.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
auditing-tests
Audits a test suite, or a named part, for low-value tests and marks each retain, fix, consolidate, or delete with verified removal evidence. Read-only. Use when the user says "audit the tests", or when asked to audit tests for redundant, junk, or low-value tests. Not for code complexity; use auditing-complexity.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
capturing-screenshots
Captures deterministic, visually verified screenshots of a running web or native app (named screens, states, viewports, dark mode) with a manifest. Use when the user says "take screenshots", or when asked for screenshots of an app or its screens. Not for attaching images to a PR; use attaching-pr-screenshots.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
composing-agent-prompts
Composes a self-contained, source-cited task prompt for another coding agent to execute in a target repository, without running the task. Use when the user says "write a prompt for another agent", or when the user asks to write, draft, or hand off a prompt, brief, or task spec for another agent. Not for system prompts; use writing-system-prompts.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
conducting-deep-research
Conducts source-backed, goal-directed research that combines a scholarly evidence review with an institution, company, or funding map. Use when the user says "deep research", or when a request needs both an evidence review and an organization or funding map. Not for quick lookups or general research write-ups.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
cutting-skills
Audits or trims an existing agent skill to its behavioral core and narrows over-broad trigger metadata. Use when the user says "cut this skill", or when the user asks to cut, simplify, shorten, de-slop, or reduce the context cost or trigger aggressiveness of a SKILL.md or skill folder. Never infer from a skill being long or edited for another purpose.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
diagnosing-react-code
Runs the react-doctor scanner on a React package, fixes its error diagnostics, and re-runs until none remain. Use when the user says "health-check the React code", or when React components or hooks changed, when finishing a React feature or bug fix, or when asked to health-check React code.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
drawing-mermaid-diagrams
Writes, edits, and debugs Mermaid diagrams (flowchart, sequence, class, state, ER, Gantt, pie, mindmap, timeline, quadrant, git graph, XY, Sankey, architecture, journey, kanban, block). Use when the user asks for a diagram, flowchart, ERD, or Mermaid code, or when a Mermaid diagram fails to parse or render.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 20 oct
explaining-architecture
Explains how a subsystem, feature flow, or runtime path works (architecture, data flow, file map, gotchas), with an optional critique by fresh-context critics. Read-only. Use when the user says "how does this work?", or when asked how a subsystem or flow works, how a request, event, or piece of data travels through the code, which files to start in, or where logic belongs. Not for why code is shaped as it is; use investigating-design-rationale. Not for explaining a PR or diff; use explaining-cod
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
explaining-code
Explains code or code changes in plain language, briefly by default or in full for a reviewer. Use when the user says "explain this PR", or when asked to explain, ELIE, summarize, or break down a PR, diff, branch, file, function, or concept for someone new to the code. Not for how a whole subsystem works; use explaining-architecture.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
fixing-root-causes
Traces a bug or failure to its root cause and fixes it there instead of patching the symptom. Use when the user says "find the root cause", or when debugging a crash, failing test, regression, or "fails after restart" bug, or when a fix would add a guard, retry, or workaround to silence an error.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
freeing-disk-space
Finds what fills a developer machine's disk and frees space by clearing caches, build outputs, and other regenerable files, running each deletion only after approval and never emptying the Trash. Use when the user says "free up disk space", or when a disk is full or nearly full, the user is running out of disk space, builds or containers fail for lack of space, or the user asks for a disk cleanup plan, to free a target amount of space, or to clean up, reclaim space, or delete caches, build outpu
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
grooming-backlogs
Grooms a GitHub Projects backlog: verifies issues against the code, ranks and clusters them, and plans milestone, link, and closure changes, or promotes issues to Ready. Proposes tracker changes; each requires approval. Use when the user says "groom the backlog", or when asked to groom, triage, or prioritize a backlog, or to promote issues to Ready.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
improving-codebases
Sweeps a git repository with focused improvement lanes: implicit state machines made explicit and checked in TLA+, and high-churn files refactored so the next change edits one place. Leaves edits uncommitted. Use when the user says "improve this codebase", or when asked to make implicit state machines explicit or to reduce churn in high-churn files. Never infer from a request to review or explain code. Not for test value or complexity rankings; use auditing-tests or auditing-complexity.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
improving-prompts
Compresses and clarifies an existing LLM prompt through concept elevation, verifying that no original instruction is lost. Use when the user supplies a prompt or prompt file and asks to improve, tighten, optimize, or refine it. Not for writing a new prompt; use writing-system-prompts.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 20 oct
learning-from-mistakes
Codifies the latest correction or mistake in the conversation as a short imperative rule in the project or global CLAUDE.md or AGENTS.md, after the user approves it. Use when the user asks to learn from a mistake, remember a lesson for next time, add a rule to CLAUDE.md, or not repeat a behavior. Not for a whole session; use running-retros.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 20 oct
making-code-agent-friendly
Audits, reviews, and refactors code so many coding agents can change it in parallel without merge conflicts: few shared files, strong boundaries, explicit contracts, fast checks. Also lists the shared files a design or diff edits and flags any file every change appends to. Use when the user says "make this agent-friendly" or "check shared files", or when asked to make code agent-friendly, find where parallel agents will collide, or name the shared files a feature edits or the files every change
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
merging-dependabot-prs
Analyzes open Dependabot PRs for semver level, CI, breaking changes, and security fixes, then squash-merges approved patch and minor updates one at a time, or only comments @dependabot rebase; supports a dry run. Use when the user explicitly asks to merge, process, or rebase Dependabot PRs. Never infer from green CI, an approved Dependabot PR, or stale or conflicting Dependabot PRs.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
opening-prs
Opens a draft pull request for the current branch, or refreshes the body of its open PR after a push, from the branch diff and an optional inputs file. Use when the user says "open a PR", or when the user explicitly asks to open or refresh a pull request for the current branch. Never infer from finished work or passing checks. Not for a gh stack layer; use stacking-prs. Not for screenshots; use attaching-pr-screenshots.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
prototyping-ui
Builds 3 to 5 interactive HTML, CSS, and JavaScript prototypes of one feature, each a different interaction model, then compares their usability as an experienced UX designer and recommends one. Use when the user says "prototype this", or asks to prototype, mock up, or compare design options for a screen, flow, or component. Not for building the production feature.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
proving-claims
Proves or disproves claims, or the test plan of a PR, by trying to falsify each and rating the strongest evidence reached (PROVEN, PARTIAL, DISPROVEN, UNPROVEN). Changes nothing. Use when the user says "prove it", or when asked to prove, verify, or fact-check claims or a PR test plan with evidence. Not for writing acceptance criteria; use writing-acceptance-criteria.
- Instalaciones / 1h
- 1
- GitHub Stars
- 2
- Actualizado
- 21 nov
