m-hosseinpou r · Agent Skills
16 Skills with substantive, source-verified documentation. Open a card to read the original instructions and review package and installation details.
curating-global-instructions
Use when adding to, trimming or reorganizing the instruction file loaded into every session whatever the project — the global CLAUDE.md, AGENTS.md, or whatever plays that role — or when it has grown past what a session can hold.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
designing-persian-rtl-web-ui
Use when building, changing, or checking a Persian (Farsi) web interface — including right-to-left layout, typography, UI copy, numerals, responsive behavior, or dark mode — and before calling Persian UI work done. Not for RTL-only work in non-Persian interfaces.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
dispatching-parallel-agents
Use when delegation is available and allowed and a task has multiple substantial workstreams that may be independent, when parallel agent work is requested, or before running a subagent alongside your own work or other subagents. Not for small multi-step tasks, parallel tool calls, or one delegate you will simply wait for.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
research-with-evidence
Use when researching a question across multiple sources, doing in-depth web research, comparing options using external evidence, investigating conflicting claims, or checking the substantive claims and sources of a research report. Not for a simple factual lookup, explanation from already-sufficient evidence, translation or editing without fact-checking, code-change review, or diagnosing a concrete software failure.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
reviewing-code-changes
Use when starting a review of a PR, merge request, branch, commit range, patch, or uncommitted changes for defects, regressions, requirement conformance, or merge readiness, including direct instructions to review and test changes against a ticket or acceptance criteria; or before completing consequential changes to behavior, public contracts, security, or persisted data. Not for test-only runs, unchanged-code audits, explanation-only walkthroughs, formatting existing findings, receiving review
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
session-handoff
Use when preparing a handoff to another session, agent, or person, preserving ongoing work before a context reset or compaction, or resuming work from a supplied handoff. Not for routine status replies, a completed-work summary, ordinary short delegation briefs, or author-facing code-review reports.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
structured-reasoning
Use when a request requires substantial reasoning, synthesizing evidence, resolving uncertainty, planning, or weighing meaningful alternatives, regardless of domain or whether the result is an answer, recommendation, artifact, or action. Also use for explicit brainstorming, stress-testing an idea or decision, or a guided interview to clarify a plan. Skip simple factual lookups and obvious mechanical tasks.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
systematic-debugging
Use when investigating or fixing a bug, regression, failing or flaky test, build or deployment failure, performance problem, or incorrect output; also when asked why a failure occurred. Not for feature design, failure-free code explanation, or applying an already-verified correction without new uncertainty.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
targeted-proxy-access
Use when a page fetch fails because the site is blocked, geo-restricted, or sanctioned in this network (timeouts, connection resets, 403 from the region); when a domain routed through the tunnel still fails and the gateway, routed domains, or client wiring needs checking; or when the user asks to reach a domain through their VLESS/Trojan configs without tunneling the whole system.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
trimming-project-instructions
Use when a project's instruction file — CLAUDE.md, AGENTS.md or whatever plays that role — has grown past what a session can hold, or when asked to shrink, split or reorganize one.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
understanding-code-changes
Use when you need to understand or explain a pull request, merge request, branch, or diff rather than judge it — especially when taking over unfamiliar code, locating a change in the project's architecture, or getting oriented before reviewing a large change.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
validating-completed-tasks
Use when validating a completed task or a colleague's deliverable for task acceptance, initially or after prior review and revisions: whether the work is correct, complete, and trustworthy, including review plus real acceptance/edge-case testing, re-reviewing fixes against earlier findings and current task requirements, or checking a research/security report and its evidence. Not for defect-only or merge-readiness review without task-completion validation even if a ticket is cited; test-only exe
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
writing-code-review-reports
Use when writing a code-review report from completed review results, whether supplied by others or produced in the current task; includes the reporting stage of a combined review-and-report request, reports with no findings, and editing, translating, or consolidating review reports. Not for code inspection, fixing findings, responding to review feedback, explanation-only walkthroughs, or a brief findings-only review reply when no report is requested.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
writing-implementation-plans
Use when asked to write, review, or update an implementation plan; when substantial cross-component changes, migrations, or high-risk work need coordinated steps and checks; or when preparing multi-session or cross-owner implementation work or resuming from a potentially stale implementation plan. Not for routine local edits without a plan request, executing a current settled plan, design-only exploration, or non-implementation handoffs.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
writing-skills
Use when creating, reviewing, or improving an agent skill; turning a repeatable workflow into a skill; investigating missed or unwanted skill loading; or changing a skill's SKILL.md, references, or helper scripts in ways that affect use. Not for installing or applying an existing skill, explaining the format, or mechanical edits that preserve meaning and behavior.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15
writing-task-briefs-and-guides
Use when a long task or issue description needs a concise team-facing version for estimation while preserving full requirements in a standalone developer guide.
- 1h installs
- 2
- GitHub stars
- 0
- Updated
- Nov 15