Agent Skills

---

name: deliverable-completion

description: Clarifies that file creation tasks are complete when the deliverable is successfully written—no submission step required

---

name: detect-zero-iteration-failure

description: Identify and classify agent failures occurring before execution starts

---

name: detect-zero-iteration-failures

description: Identify and handle pre-execution agent failures occurring before any iterations or tool usage

---

name: diagnostic-stem-delivery

description: Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow

---

name: direct-reportlab-pdf-generation

description: Generate complex multi-page PDFs by running reportlab Python code directly via run_shell when shell_agent fails on document creation

---

name: doc-gen-unicode-diagnostic

description: Systematic document generation with unicode sanitization, engine fallback chain, and explicit error diagnosis

---

name: document-gen-dual-backend

description: Document generation with direct pandoc/ReportLab execution (lightweight default) and optional shell_agent fallback for complex scenarios

---

name: document-gen-fallback

description: Fallback workflow for multi-format document generation when shell_agent encounters errors

---

name: document-gen-resilient

description: Multi-path document generation with tool checks, Unicode handling, and Python fallbacks

---

name: document-gen-resilient-multiformat

description: Resilient multi-format document generation with environment checks, auto-sanitization, and fallback engines

---

name: document-gen-resilient-workflow

description: Robust document generation with engine fallback chain, error diagnostics, and Python alternatives

---

name: document-gen-resilient-workflow

description: Multi-engine document generation with cascading PDF fallbacks and robust Unicode handling

---

name: document-gen-unicode-safe

description: Unicode-safe fallback workflow for multi-format document generation with character sanitization and explicit error capture

---

name: document-gen-unicode-safe

description: Unicode-safe fallback workflow for multi-format document generation with character sanitization

---

name: incremental-audio-workflow

description: Step-by-step audio production with per-stem verification, timing alignment, and incremental quality gates

---

name: remember

description: Review auto-memory entries and propose promotions to OPENSPACE.md, OPENSPACE.local.md, or retained auto-memory topics; detect duplicates, stale facts, conflicts, and ambiguous entries before making changes.

---

name: skill-discovery

description: Search reusable OpenSpace skills locally, and browse cloud packages step by step when a cloud skill may help. Reusing proven skills saves tokens, improves reliability, and extends your capabilities beyond built-in tools.

---

name: branch-pr

description: Create Gentle AI pull requests with issue-first checks. Trigger: creating, opening, or preparing PRs for review.

---

name: chained-pr

description: Trigger: PRs over 400 lines, stacked PRs, review slices. Split oversized changes into chained PRs that protect review focus.

---

name: cognitive-doc-design

description: Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.

---

name: cognitive-doc-design

description: Design docs that reduce cognitive load. Trigger: writing guides, READMEs, RFCs, onboarding, architecture, or review-facing docs.

---

name: comment-writer

description: Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.

---

name: comment-writer

description: Write warm, direct collaboration comments. Trigger: PR feedback, issue replies, reviews, Slack messages, or GitHub comments.

---

name: gentle-ai-bench

description: Trigger: bench, journey, journeys, driven mode, gentle-ai-bench, journey corpus, j-numbers, bench axis. Author and verify gentle-ai bench journeys; go test ./bench never proves driven execution.