refresh-project-docs
Refresh README files and project documentation so they match the current repository state. Use when Codex needs to update stale docs after feature work, sync documentation to current commands, options, configuration, and workflows, rewrite changelog-style wording into evergreen current-state documentation, or turn a rough docs-update prompt into an execution-ready instruction set.
What this skill does
# Refresh Project Docs Update documentation from the live repo state, not from outdated docs or feature-memory summaries. Load [references/prompt-template.md](references/prompt-template.md) when the user wants a polished reusable prompt or when you need a starting template before editing docs directly. ## Modes Choose the lightest mode that fits the request. - `Prompt-only`: refine the user's raw docs-refresh prompt and return the upgraded prompt. - `Docs execution`: inspect the repo and update the relevant docs directly. - `Prompt + execution`: return the upgraded prompt and use the same standards while editing docs. ## Workflow ### 1. Inventory the documentation surface Find the docs that may need to move together: - `README.md` - contributor or setup docs - `docs/` pages - examples, templates, or onboarding guides - CLI or API docs generated from source-adjacent files Do not assume the README is the only source that matters. ### 2. Rebuild the current product and workflow state Treat the repository as the source of truth. Check the most authoritative artifacts available, such as: - command help text, scripts, task runners, and package manifests - config files, environment examples, and migration files - implementation code for user-facing features - tests that document supported behavior - existing docs only after comparing them to the code When commands, flags, options, or workflows can be verified from source, verify them instead of inferring. ### 3. Identify documentation deltas Capture what the docs need to describe in their current form: - current commands, subcommands, flags, and options - current setup, install, deploy, and development flows - current features, integrations, and limitations - renamed, removed, or superseded behavior that should disappear from the docs - duplicated guidance that now needs to be synchronized across files ### 4. Rewrite in evergreen current-state language Write as if the documented behavior has always been part of the project. Use these rules without exception: - describe the present state, not the history of how it changed - remove stale wording instead of narrating the transition - preserve the project's voice and structure unless a clearer structure is needed - update every relevant doc file that carries the affected information Avoid release-note phrasing such as: - `we added` - `now supports` - `recently` - `has been updated` - `X is now Y` ### 5. Verify before finishing Check that: - commands and examples match the real interface - options and configuration names match the current code - duplicated docs agree with each other - stale statements, placeholders, and contradictions are removed - links still resolve if you touched public docs ## Prompt Upgrade Rules When the user gives a rough prompt, keep the intent but add the missing execution structure: - tell the agent to inspect the repo before editing docs - tell the agent to treat code and config as canonical over stale docs - require updating all relevant documentation, not only the README - require evergreen phrasing with no change-log language - require explicit coverage of commands, options, features, and workflows - require a verification pass for consistency and outdated content Prefer the template in [references/prompt-template.md](references/prompt-template.md) over improvising from scratch. ## Red Flags Stop and correct the approach if any of these appear: - trusting existing docs without checking source - updating only `README.md` when the same information lives elsewhere - documenting commands or flags that were not verified - keeping historical phrasing like a mini changelog - leaving contradictory old guidance in secondary docs ## Done Criteria This skill is complete when the upgraded prompt or edited docs: - describe only the current state of the project - include the relevant commands, options, features, and workflows - remove stale or transitional wording - are internally consistent across the touched documentation set
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.