Skill Claude Code
Deep interview process to transform vague ideas into detailed specs. Works for technical and non-technical users.
not rated 3.9k
+3 8mo ago A Socket: passSnyk: warnSkillSpector: warn 25 tokens
original MIT
grill-me
02Skill Claude Code
A relentless interview to sharpen a plan or design.
not rated 230
+2 18d ago A 14 tokens
copy · 100% MIT
Bande-a-Bonnot/Boucle-framework
Skill Claude Code
Analyze a CLAUDE.md file and install enforce-hooks so tagged rules become verified PreToolUse checks for covered tool calls. Use when users want CLAUDE.md directives enforced as code rather than relying on prompt compliance. Prefer the dynamic plugin mode (--install-plugin), which re-reads CLAUDE.md on every tool…
not rated 125 20d ago A ✓ AI review SkillSpector: warn 86 tokens
original MIT
Skill Claude Code
Use to develop a feature or bug fix end-to-end through a TDD git-worktree workflow — interactively (developer-led) or unattended (autonomous-mode, driven by the dispatcher). Triggers on phrases like "implement issue #N", "fix this bug", "add a feature", "create a worktree", "write test cases", "push and open a PR"…
not rated 38
changed 6d ago A 162 tokens
ralph-config
05Skill Claude Code
Generate ralph.yml and PROMPT.md configuration files for Ralph Orchestrator workflows from plans, tickets, or ideas. Use when setting up Ralph Orchestrator, creating hat-based workflows, or adapting Linear/Jira/markdown plans into ralph.yml + PROMPT.md files.
not rated 8 8mo ago A 0 tokens
skill-valet
06Skill Claude Code
Use when the session feels bloated or slow, the user mentions "too many skills", "context bloat", "skill list is huge", asks why a skill disappeared or isn't available, or wants to manually park/unpark skill groups mid-session. skill-valet automatically moves unused user-skill directories out of /.claude/skills so the…
not rated 6 3mo ago A 91 tokens
original MIT
alex-feel/claude-code-artifacts-public
Skill Claude CodeCodex
Pattern taxonomy, agent role combinations, model routing, unit-of-work sizing, review-findings settling, and resilience discipline for Claude Code dynamic workflows. ALWAYS load this skill before authoring or running any Workflow tool script, and ALWAYS load it when the user mentions "workflow" or "ultracode" in any…
not rated 6
changed yesterday A SkillSpector: pass 160 tokens
original MIT
orchestrator
08aleksandr-chaika/flutter-clean-arch-skills
Skill Claude Code
FULLY AUTONOMOUS Flutter development pipeline orchestrator. Smart routing: PM analyzes -> creates targeted tasks -> Orchestrator executes only needed agents. Supports Asana task URLs. Includes QE verification via Maestro E2E tests. 7-phase flow: PM -> TodoWrite -> Execute -> Review -> Tests -> QE E2E -> Close.
not rated 5 7mo ago A 72 tokens
original MIT
throughline
09Skill Codex
Use when the user asks to use Throughline from Codex, continue or restore Throughline memory, export read-only handoff context for a local launcher, prepare a new Codex thread handoff, summarize a captured Codex session, or check whether the Throughline Codex Stop hook captured the current session. Hide long…
not rated 5 2d ago A 75 tokens
original MIT
Skill Claude Code
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
not rated 5
changed 6d ago A 64 tokens
Skill Claude CodeCodex
View and sync Claude Code, Codex, Grok, and Antigravity memories, plans, tasks, and graph memory mirrored in Eagle Mem. Use when: 'eagle memories', 'show memories', 'sync memories', 'what does the agent remember', 'show plans', 'show tasks', 'mirror memories', 'onboard project', 'what did past sessions learn'. Uses…
not rated 4 4mo ago A 92 tokens
Skill Claude Code
Use when you want structured feedback on a plan or document before implementation.
not rated 4 3mo ago A 17 tokens
original MIT
hooks-daemon
13Edmonds-Commerce-Limited/claude-code-hooks-daemon
Skill Claude Code
Manage Claude Code Hooks Daemon - install, provision a fresh checkout, upgrade, optimise the configuration, check health, restart, run the housekeeping pass, status-line-explained to explain every status-line icon, issue-report to file a defect upstream, file a local bug-report, and report issues.
not rated 4
changed 4d ago A 63 tokens
original MIT
supervisor
14ma-nucho-pro/supervisorLLM-plugin
Skill Claude CodeCodex
Universal multi-agent quality supervisor and release gate for Claude Code, Cursor, Codex, Gemini CLI, ChatGPT/Codex Agent Skills, and other Agent Skills-compatible harnesses. Use for rigorous research, coding, frontend design, testing, anti-hallucination review, independent judges, adversarial review, evidence-based…
not rated 4 25d ago A 82 tokens
prod-debug
15Skill Claude Code
Production debugging skill. Pre-loads DB schema, container registry, and prod environment facts from .claude/prod-debug/ in the current project root. Use when the user invokes /prod-debug or /prod-debug bootstrap.
not rated 3
changed 26d ago A 48 tokens
original MIT
Skill Claude Code needs its repo
Reduce Claude AI token consumption by 5x-27x using prompt-native workflows and structural code manifests. Forces Claude to reason from CONTEXTMANIFEST.md first, fetch max 3 files per turn, and output in a strict compressed format. Use when user says optimize context, reduce tokens, context optimizer, manifest, blast…
not rated 3 4d ago A 75 tokens
copy · 88% MIT
Skill Claude Code needs its repo
Commands for validating, testing, iterating on, and releasing plugins in this marketplace (claude-toolbelt) — plugin validate, watcher-parity check, eval, --plugin-dir dev loop, plugin tag. Use when validating a plugin before pushing, running skill evals, developing a plugin without touching the installed cache, or…
not rated 2
changed 8d ago A 73 tokens
original MIT
Skill Claude CodeCodex
Skill "founder-voice" from assafkip/founder-voice-kit, covering founder voice skill, before writing, writing rules (enforced), 1. sentence structure and 2. no hedging.
not rated 2 1mo ago A 0 tokens
original MIT
data-explore
19giacomogaglione/claude-awesome-stack
Skill Claude CodeCodex
Profile and explore datasets -- schema inference, distributions, missing values, outliers, correlations. Use when starting work with a new dataset or investigating data quality issues.
not rated 2 7mo ago A 36 tokens
original MIT
no-npm
20Skill Claude Code
Block npm/npx/yarn and suggest the pnpm equivalent. Triggers when a command uses npm/npx/yarn as a standalone word.
not rated 2 3mo ago B 33 tokens
original MIT
Skill Claude CodeCodex
Audit CLAUDE.md against .claude/settings.json. Reports which rules are enforced by hooks/permissions and which are prose, plus context cost, import resolution, contradictions, and structure. Use when the user asks to audit, check, lint, or grade their CLAUDE.md, or asks whether their Claude Code rules are enforced.
not rated 2
changed 1mo ago A 75 tokens
original MIT
nil
22Skill Claude CodeCodex
The inverse of /sfl. Where sfl saved each window for later, /nil says later is now: it reopens them. You choose which to bring back.
not rated 1 1mo ago A 153 tokens
original MIT
checkpoint
23Skill Claude CodeCodex
Creates a git checkpoint commit of all current changes. Use when you want to save progress mid-session before risky changes. Invoke with /checkpoint or "save checkpoint" or "git checkpoint".
not rated 1 5mo ago A 39 tokens
sessme
24Skill Claude CodeCodex
A command that lists recent multi-turn coding sessions and lets you choose one to restore in full.
not rated 1 3mo ago A 134 tokens
original MIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: