Menu
SkillsMP a collecté 42 skills depuis nearai/ironclaw. Ouvrez un skill pour examiner sa source et ses détails.
Affichage de 40 skills collectés sur 42.
Use when adding or changing a Reborn integration — a new extension, a channel surface, model-callable tools, or a shared auth provider — or when deciding whether something is "a channel", "an extension", or "a tool". Maps the unified extension model (NEA-25)…
Langue du texte source : anglais
Use when creating or editing agent guidance in this repo — anything under .claude/ (skills, commands, rules), AGENTS.md or CLAUDE.md files, or the runtime skills/ directory — or when guidance is found citing files, branches, or checks that no longer exist.
Langue du texte source : anglais
Use when adding or reviewing tests for Reborn behavior — choosing a test tier, covering a bug fix, testing model/tool-choice behavior, touching tests/integration or tests/fixtures/llm_traces, or when a test needs Postgres, Docker, or a live LLM.
Langue du texte source : anglais
Use when writing or reviewing a change in crates/ that adds a trait, a crate, a dependency edge, a re-export, or code in ironclaw_composition — or when deciding whether an abstraction, layer, or crate boundary is justified in the IronClaw Reborn stack.
Langue du texte source : anglais
One-time onboarding for the executive/manager commitment workflow — delegation, meeting prep, decision capture, daily digests. Creates a `commitments` project and two dashboard widgets, then excludes itself until its marker file is deleted.
Langue du texte source : anglais
Best practices for code editing, search, and file operations
Langue du texte source : anglais
One-time setup for the commitments tracking system. Creates the workspace structure and schema docs, installs triage and digest missions, then excludes itself once `projects/commitments/README.md` exists.
Langue du texte source : anglais
Track delegated commitments, set follow-up timers, and generate nudge reminders when updates are overdue.
Langue du texte source : anglais
One-time onboarding for the developer workflow — installs github-workflow missions, creates the commitments workspace, registers per-repo projects, writes calibration memories. Excludes itself until its marker file is deleted.
Langue du texte source : anglais
Review a batch or stack of pull requests, or run a recurring PR-review pass on a repo. Best with many PRs, stacked branches, conflicts, or security-sensitive changes. Covers grouping, fan-out to review subagents, verdict synthesis, and posting.
Langue du texte source : anglais
Cross-chain DeFi portfolio discovery, rebalancing suggestions, and NEAR Intent construction. Triggered by a pasted wallet address or questions about yield, positions or rebalancing. Aggregates positions across the user's addresses in one project.
Langue du texte source : anglais
Recognize obligations in conversation, extract signals with immediacy and expiration, create and manage commitments in the workspace.
Langue du texte source : anglais
Helps users delegate tasks, break them into steps, set deadlines, and track progress via routines and memory.
Langue du texte source : anglais
Suggests relevant cron routines based on user context, goals, and observed patterns
Langue du texte source : anglais
Generate or update the IronClaw architecture overview video using Remotion. Use when asked to update, regenerate, or modify the architecture video, add/remove scenes, or reflect codebase changes in the video.
Langue du texte source : anglais
Use when starting work in the IronClaw repo, deciding where a feature/fix/prompt/doc belongs, tracing how a request flows, looking up which crate owns a subsystem, or when repo docs, the knowledge graph, or component names seem stale, missing, or…
Langue du texte source : anglais
Triggered when the user invokes /railway-test or $railway-test, asks to test a pull request on Railway, or requests browser-based exact-head preview QA and pull-request evidence before merging.
Langue du texte source : anglais
Build a user-facing feature in the Reborn stack with the smallest existing contract surface.
Langue du texte source : anglais
Build and maintain documentation sites with Mintlify. Use when creating docs pages, configuring navigation, adding components, or setting up API references.
Langue du texte source : anglais
Paranoid architect review of code changes for bugs, security, missing tests, and undocumented assumptions. Works on local git diffs OR a GitHub pull request (e.g. `owner/repo N`). For PRs, can post findings as line-level review comments.
Langue du texte source : anglais
GitHub API integration via HTTP tool with automatic credential injection
Langue du texte source : anglais
Run an extremely strict maintainability review for abstraction quality, giant files, and spaghetti-condition growth. Use for a thermo-nuclear code quality review, thermonuclear review, deep code quality audit, or especially harsh maintainability review.
Langue du texte source : anglais
Linear issue tracker API integration. Covers first-use identity bootstrap (viewer + teams cached), raw GraphQL for list/search/create/update, and the rules for handling "my issues" / "assigned to me" requests.
Langue du texte source : anglais
Compose and deliver summaries of open commitments, deadlines, pending signals, and resolution suggestions.
Langue du texte source : anglais
One-time onboarding for the content creator workflow — content pipeline stages, trend expiration, cross-platform cascades, heavy idea parking. After successful setup this skill is excluded from selection until the marker file is deleted.
Langue du texte source : anglais
Detect decisions in conversation and record them with rationale, alternatives, and outcome tracking.
Langue du texte source : anglais
Park interesting ideas for later consideration, resurface them periodically, and promote to commitments when ready.
Langue du texte source : anglais
Product strategy and feature prioritization — score features by user demand evidence, effort (human vs AI-assisted), strategic alignment, and market signal. Anti-sycophantic forcing questions to cut through opinion.
Langue du texte source : anglais
Security audit for code changes and PRs — OWASP top 10, auth flows, data handling, secrets exposure, supply chain risks. Writes findings as actionable items.
Langue du texte source : anglais
Detect and track technical debt from conversation and PR review comments. Resurface in weekly retros, promote to commitments when ready to fix.
Langue du texte source : anglais
One-time onboarding for the financial trader workflow — real-time alerts, position-aware relevance, decision journaling with outcome tracking. After successful setup this skill is excluded from selection until the marker file is deleted.
Langue du texte source : anglais
Create and structure a new autonomous project — "/new-project <what project does>"
Langue du texte source : anglais
Query multiple LLM models in parallel from CodeAct and cross-reference their responses
Langue du texte source : anglais
Generate git commit messages from staged changes
Langue du texte source : anglais
Install and operate a full GitHub issue-to-merge workflow for any repository using event-driven and cron missions. Handles issue planning, PR monitoring, CI fixing, staging review, and post-merge learning.
Langue du texte source : anglais
Add a GitHub repository as a tracked project — creates workspace entity, installs workflow automation missions, and includes in dev brief scope.
Langue du texte source : anglais
QA review for code changes — test coverage analysis, edge case identification, test plan generation, regression detection, test health tracking over time.
Langue du texte source : anglais
PR readiness dashboard — tracks which reviews have been completed per branch and gates merge decisions. Shows code review, tests, security, QA, and linting status.
Langue du texte source : anglais
Structured planning mode for autonomous task execution. Creates plans as MemoryDocs, executes via Missions, tracks progress with live checklist.
Langue du texte source : anglais
Pre-merge review checklist based on recurring AI reviewer feedback patterns
Langue du texte source : anglais