writing-issues
Logging and referencing writing issues: craft problems, tics, inconsistencies, and structural concerns found during analysis, critique, or review. Use when an agent identifies something worth tracking beyond a single critique report: repeated tics across chapters, inconsistencies that affect multiple scenes, structural problems that need the author's attention, or patterns that should be fixed in revision.
What this skill does
# Writing Issues Issues are writing problems worth tracking beyond a single critique report. A critic finding a pacing problem in one draft produces a critique finding. A critic noticing the same pacing problem across three chapters produces an issue: it's a pattern that won't be fixed by revising one scene. ## When to Log an Issue Log when the problem is: - **Recurring**: the same tic, habit, or weakness appears across multiple chapters or scenes. A single instance is a critique finding; a pattern is an issue. - **Structural**: affects the project's architecture, not just one passage. Scene-type technique that doesn't scale, emotional register that's inconsistent across the arc, a narrative device approaching its shelf life. - **Worth tracking separately from the content it appears in**: the author might want to address it in a dedicated revision pass rather than fixing it inline during the next draft. Don't log every critique finding as an issue. A scene that runs long is a critique note. A pattern of scenes running long in the middle third of every chapter is an issue. ## Where Issues Live One file per issue in the issues directory. Issues persist across work items because they're project-level concerns, not scoped to a single draft or revision cycle. ## What to Include Each issue file should contain enough for someone encountering it later to understand the problem without re-reading every chapter: - **What the issue is**: specific and concrete, not "pacing could be better" - **Evidence**: quotes, counts, chapter references. The evidence is what makes it an issue rather than an opinion. - **Scope**: what's affected. Specific chapters, a scene type across all chapters, a character's dialogue in certain situations. - **Severity or priority**: how much it damages the reader's experience. A tic that appears 5 times is less urgent than a structural inconsistency that undermines a character arc. ## Checking for Duplicates Before creating a new issue, check what already exists in the issues directory. The same problem discovered independently by different agents (a critic and a style-creator, say) should be one issue with combined evidence, not two separate files saying the same thing. If an existing issue covers the same ground, update it with new evidence rather than creating a duplicate. ## Referencing Issues When a critique report or style analysis identifies something that's already a tracked issue, reference it rather than re-describing it: "this is another instance of the emotional inconsistency issue (see `issues/emotional-inconsistency.md`)." This connects individual findings to the larger pattern. ## Closing Issues When an issue has been addressed: the tics edited out, the inconsistency resolved, the structural problem fixed: the file stays but gets marked as resolved with a note on what changed. Keeping resolved issues provides a record of what was caught and fixed, which helps calibrate future analysis.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.