Results for “pas”

Forces a second, harder escalation pass using the original glazer prompt words verbatim, pushing for a sharper replacement thesis rather than more polish.

Ingests EPUBs and ebooks into a local vector index, then answers questions and searches passages via a command-line interface.

Run an agent loop until an exit condition is met. Use when the user says "loop", "babysit", "keep trying until", "check every X", "watch", or wants iterative autonomous execution.

Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles.

Compact the current session into a single detailed handoff message that can be pasted into a fresh agent run. Use when switching context, ending a session, or avoiding context-window loss.

Runs a multi-agent adversarial verification loop where two independent reviewers must both pass before output ships, with a fix cycle for convergence.

Code review skill — auto-scopes from git changes, reads DOJO.md for project conventions, and produces structured findings with priority levels. Supports quick single-pass review and deep 3-agent parallel audit.

Builds reliable browser automation skills through iterative experimentation, running an inner agent to browse sites and improving navigation instructions until tasks pass consistently.

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Create, synthesize, and iteratively improve agent skills following the Agent Skills specification. Handles source capture, precision passes, authoring, registration, and validation.

Generates a Playwright test from a user-provided scenario by recording browser interactions via Playwright MCP, then saves and runs the test until it passes.

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Scan and audit AI agent skills for security risks before installation, producing a PASS/WARN/FAIL verdict with findings and remediation guidance.

Run tests and systematically fix all failing tests using smart error grouping. Use when user asks to fix failing tests, mentions test failures, runs test suite and failures occur, or requests to make tests pass.

Use when passing work, tasks, or deliverables between agents. This skill provides a standardized protocol for agent-to-agent handoffs, ensuring context, requirements, and expectations are clearly communicated during task delegation or escalation.

Builds reliable browser automation skills by iteratively running a browsing task, reading the trace, and improving the navigation strategy until it passes consistently.

Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.

Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.

Analyzes draft prompts, identifies intent and gaps, matches ECC components, and outputs an optimized prompt for the user to paste and run. Advisory only, never executes the task.

Builds an evidence-backed ECC install plan for a repository by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes.

Reads a plan document, decomposes it into steps, designs a per-step agent chain from the ECC catalogue, and emits ready-to-paste /orchestrate custom prompts without executing them.

Analyzes past agent sessions to identify recurring failures and skill gaps, then automatically creates or patches skills and runs self-evolution to fix them, tracking improvement over time.

Builds an evidence-backed ECC install plan for a repository by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes.

Store and retrieve API keys, passwords, and credentials in an HSM-backed encrypted vault via MCP or REST API, with policy-based access control, secret rotation, multi-chain signing, and prompt injection scanning.

Autonomous multi-round research review loop. Repeatedly reviews via Codex MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.

Runs a complete quality engineering audit on any codebase, deriving behavioral requirements, generating spec-traced tests, performing multi-pass code review, and producing a consolidated bug report with verified patches.

Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian vault or git-tracked notes repo. Use when raw sources such as web articles, papers, meeting notes, transcripts, screenshots, or past analyses need to be turned into an interlinked knowledge base with immutable source files, LLM-written wiki pages, `index.md`, `log.md`, schema rules in `AGENTS.md` or `CLAUDE.md`, source summaries, query notes, and recurring lint passes. Triggers on: llm-wiki, personal wiki, obsidian wiki, research vault, knowledge base, source ingest, persistent notes, wiki maintenance, source summaries, query filing.

Evaluates image captions by converting them into scene graphs and computing an F-score over semantic propositions, measuring how well a generated caption captures the meaning of an image compared to human references.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Evaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.

Use to convert references to PNAS's numbered citation style — cited in order of appearance, a numbered reference list, full author lists, abbreviated journal titles. Provides formats for article/book/chapter/dataset/preprint and an author-date → PNAS conversion table. Late-stage style pass.

Diagnose Sentry issues without copy-pasting stack traces. Uses the Composio CLI to pull issue details, events, breadcrumbs, and suspect commits, then maps the frames to local source so the agent can propose a fix directly.

Reuse a running Chrome session for browser automation via Playwriter CLI + MCP. Use when the task depends on the browser the user already has open — existing logins, cookies, extensions, passkey-friendly flows, or live-tab continuity. Route repeatable fresh-browser or CI-style checks to `browser-harness` instead.

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.

Build an evidence-backed ECC install plan for a specific repo by sorting skills, commands, rules, hooks, and extras into DAILY vs LIBRARY buckets using parallel repo-aware review passes. Use when ECC should be trimmed to what a project actually needs instead of loading the full bundle.