cskill-agents

In the author's own words, from each skill's SKILL.md — showing the first 30 of 474 files.

• additive-agent-tool-surface-construction

  Merge agent-specific tool sets (MCP clients + fetched tools) into the parent context without disrupting the parent’s existing pool.

  skills/additive-agent-tool-surface-construction/SKILL.md on GitHub (opens in a new tab)

• agent-specific-mcp-server-initialization

  Connect each agent’s frontmatter MCP servers safely and tear them down without leaking clients, while honoring plugin-only guards.

  skills/agent-specific-mcp-server-initialization/SKILL.md on GitHub (opens in a new tab)

• aggregated-change-signal-return

  Collapse multiple change sources into one caller-facing boolean so headless bootstraps know whether a downstream refresh is necessary.

  skills/aggregated-change-signal-return/SKILL.md on GitHub (opens in a new tab)

• ansi-safe-border-caption-embedding

  Embed captions into terminal borders while preserving alignment, clipping, and color/dim semantics.

  skills/ansi-safe-border-caption-embedding/SKILL.md on GitHub (opens in a new tab)

• api-round-message-grouping

  Split conversation history into API-round buckets so compaction retries cut only the chunks tied to the failed round.

  skills/api-round-message-grouping/SKILL.md on GitHub (opens in a new tab)

• api-round-ptl-retry-truncation

  On prompt-too-long retries, drop the oldest API-round groups first and inject a synthetic user preamble when needed so the summarize request stays valid.

  skills/api-round-ptl-retry-truncation/SKILL.md on GitHub (opens in a new tab)

• append-only-sidechain-transcripts

  Persist every subagent transcript entry by appending with explicit parent UUIDs so transcripts become a linear, resumable sidechain.

  skills/append-only-sidechain-transcripts/SKILL.md on GitHub (opens in a new tab)

• atomic-post-await-state-commit

  After awaiting persistence work, update the shared budget state for each `tool_use_id` exactly once so no concurrent reader ever sees a half-committed decision.

  skills/atomic-post-await-state-commit/SKILL.md on GitHub (opens in a new tab)

• auto-memory-tool-permission-fencing

  Gate every tool call in the auto-memory extract agent so only safe read-only actions and targeted writes execute.

  skills/auto-memory-tool-permission-fencing/SKILL.md on GitHub (opens in a new tab)

• auto-refresh-after-new-plugin-sources

  Trigger a plugin refresh cycle whenever reconciliation installs new marketplaces so plugin state stays in sync.

  skills/auto-refresh-after-new-plugin-sources/SKILL.md on GitHub (opens in a new tab)

• autocompact-circuit-breaker

  Break the autocompact retry loop after several consecutive failures to avoid hammering shared APIs.

  skills/autocompact-circuit-breaker/SKILL.md on GitHub (opens in a new tab)

• autocompact-recursion-guards

  Block autocompact from running in recursive contexts so forks and helpers don’t deadlock.

  skills/autocompact-recursion-guards/SKILL.md on GitHub (opens in a new tab)

• background-marketplace-reconciliation

  Run marketplace diff and reconciliation in the background while surfacing per-source progress to the UI without blocking startup.

  skills/background-marketplace-reconciliation/SKILL.md on GitHub (opens in a new tab)

• bridge-origin-safe-slash-override

  Keep remote slash-command skipping enabled by default, then reopen it only for bridge-safe commands while denying unsafe local commands with a friendly local response.

  skills/bridge-origin-safe-slash-override/SKILL.md on GitHub (opens in a new tab)

• bridge-safe-command-advertising

  Advertise only slash commands that a bridge client can actually invoke by filtering announcements with the same bridge-safety predicate used at execution time.

  skills/bridge-safe-command-advertising/SKILL.md on GitHub (opens in a new tab)

• budget-aware-skill-listing-formatting

  Derive the active model context budget at runtime and format skill listings to fit it instead of emitting raw command sets.

  skills/budget-aware-skill-listing-formatting/SKILL.md on GitHub (opens in a new tab)

• budget-diminishing-continue

  Issue continuation nudges while the turn stays under budget, then halt once diminishing returns or the budget cap justify stopping.

  skills/budget-diminishing-continue/SKILL.md on GitHub (opens in a new tab)

• built-in-agent-feature-gating

  Gate built-in agents based on feature flags and entrypoint types so SDK sessions stay lean.

  skills/built-in-agent-feature-gating/SKILL.md on GitHub (opens in a new tab)

• bundled-and-mcp-turn-zero-skill-filter

  For first-turn skill listings, prefer a small bundled+MCP subset and fall back to bundled-only when the filtered set is still too large.

  skills/bundled-and-mcp-turn-zero-skill-filter/SKILL.md on GitHub (opens in a new tab)

• bundled-skill-file-extraction

  Lazily extract referenced files for bundled skills so large prompts stay offline until needed.

  skills/bundled-skill-file-extraction/SKILL.md on GitHub (opens in a new tab)

• cache-edit-pin-and-replay

  Queue cache edits for the next microcompact request, pin them to user-message positions, replay pinned edits later, and reset state only on explicit lifecycle boundaries.

  skills/cache-edit-pin-and-replay/SKILL.md on GitHub (opens in a new tab)

• cache-identical-fork-prefix-construction

  Build forked conversation prefixes that stay identical across turns so prompt caching keeps working.

  skills/cache-identical-fork-prefix-construction/SKILL.md on GitHub (opens in a new tab)

• cache-prefix-stability-for-subagents

  Preserve cache-critical request fields when a child agent must share the parent's prompt prefix for cache hits.

  skills/cache-prefix-stability-for-subagents/SKILL.md on GitHub (opens in a new tab)

• cache-safe-stop-hook-snapshotting

  Persist a cache-safe stop-hook context snapshot only for main session queries so later helpers can resume from stable state without fork pollution.

  skills/cache-safe-stop-hook-snapshotting/SKILL.md on GitHub (opens in a new tab)

• cache-sweep-activation-fallback

  Sweep stale extension caches before activation, then fall back to a sticky manual-refresh flag if the live refresh fails.

  skills/cache-sweep-activation-fallback/SKILL.md on GitHub (opens in a new tab)

• cache-warm-before-cache-only-fanout

  Warm the authoritative cache path first, then fan out cache-only readers in parallel so derived loaders never race stale state.

  skills/cache-warm-before-cache-only-fanout/SKILL.md on GitHub (opens in a new tab)

• canonical-root-marketplace-path-normalization

  Normalize relative extension source paths against a canonical repo root so shared marketplace records stay stable across worktrees.

  skills/canonical-root-marketplace-path-normalization/SKILL.md on GitHub (opens in a new tab)

• canonical-worktree-path-normalization

  Resolve repo-relative paths against the canonical checkout root so shared state stays stable across Git worktrees.

  skills/canonical-worktree-path-normalization/SKILL.md on GitHub (opens in a new tab)

• capability-aware-offload-skipping

  Skip generic offload wrappers for tools that already bound output locally or would become circular if wrapped again.

  skills/capability-aware-offload-skipping/SKILL.md on GitHub (opens in a new tab)

• capability-based-spinner-glyph-selection

  Select spinner glyphs and colors dynamically based on terminal capability, motion preference, and stall state.

  skills/capability-based-spinner-glyph-selection/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• book-to-skillby virgiliojr94 Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work. 35k stars · 1 skill
• khazix-skillsby KKKKhazix 数字生命卡兹克开源的 AI Skills 合集 | Agent Skills: leader（帮你定义目标）, neat-freak 洁癖, hv-analysis, khazix-writer & more — Claude Code, Codex & 40+ agents 21.4k stars · 6 skills
• skillsby NVIDIA Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA,… 3.6k stars · 30 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 164k stars · 6 skills