skill CX Codex

reflect · haowjy — Claude Code skill: what it does, how to install

Q: How do I install reflect in Claude Code?

Run `npx skills add haowjy/creative-writing-skills --skill reflect -a claude-code` in your terminal.

Q: What other skills does reflect depend on?

Its instructions load `/intent-modeling` and reference `/knowledge-layers` alongside `/qi-layer`. Those external skills determine placement and write to `AGENTS.md` or `.context/CONTEXT.md`.

Reviews delivered work before the final report and routes session knowledge into project files. Useful for catching overlooked needs while context is fresh.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add haowjy/creative-writing-skills --skill reflect -a claude-code

Open on GitHub

What reflect does

The skill triggers manually before the agent presents its report. It loads /intent-modeling to verify whether the agent addressed the underlying need rather than just literal instructions. It also prompts the model to check adjacent code that could benefit from quick updates. Fresh context makes such fixes easier.

Any insights worth keeping are directed into repository documentation. Placement between AGENTS.md, .context/, knowledge bases, and docs happens via /knowledge-layers. Writing changes directly to AGENTS.md and .context/CONTEXT.md is handled by /qi-layer. The workflow depends on these companion skills, so running it in an environment without them breaks the capture routine.

What it helps with

verify if the output solves the actual problem
spot adjacent codebase improvements while context is fresh
determine the right documentation layer for new insights
write durable project notes to AGENTS.md and .context/CONTEXT.md

Example prompts for the agent

/reflect
/reflect edge cases and error handling
/reflect capture session notes

How to install reflect

1Skills CLI (Vercel)

npx skills add haowjy/creative-writing-skills --skill reflect -a claude-code

2Manually: put the files in place

~/.claude/skills/reflect/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/reflect/

1Skills CLI (Vercel)

npx skills add haowjy/creative-writing-skills --skill reflect -a codex

2Manually: put the files in place

.agents/skills/reflect/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add haowjy/creative-writing-skills --skill reflect -a cursor

2Manually: put the files in place

.cursor/skills/reflect/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install haowjy/creative-writing-skills reflect

2Manually: put the files in place

.github/skills/reflect/SKILL.md

1Skills CLI (Vercel)

npx skills add haowjy/creative-writing-skills --skill reflect -a gemini-cli

2Platform CLI

gemini skills install https://github.com/haowjy/creative-writing-skills --path cw/skills/reflect

Manually: put the files in place

.devin/skills/reflect/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add haowjy/creative-writing-skills --skill reflect -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about reflect

How do I install reflect in Claude Code?

Run npx skills add haowjy/creative-writing-skills --skill reflect -a claude-code in your terminal.

What does the reflect skill do?

It prompts the assistant to inspect recent changes before completing a task. The skill confirms user goals were met and routes important findings into project files.

What other skills does reflect depend on?

Its instructions load /intent-modeling and reference /knowledge-layers alongside /qi-layer. Those external skills determine placement and write to AGENTS.md or .context/CONTEXT.md.

Source text

SKILL.md · Apache-2.0

---
name: reflect
description: 'Use when the user invokes it before you report: checks you delivered what they needed, not only what they literally asked, and routes knowledge capture.'
disable-model-invocation: true
argument-hint: Optional focus for the check
---

# Reflect

Load `/intent-modeling` if it isn't already loaded.

Did you deliver what they actually needed? Given what you changed, is there anything adjacent worth improving now while context is fresh, without opening a new project?

If something should survive this session, put it in the right layer: `/knowledge-layers` for placement (AGENTS.md, `.context/`, KB, docs), `/qi-layer` for writing AGENTS.md and `.context/CONTEXT.md`.

reflect by other authors comes first.

reflect backnotprop Mines the current session transcript using three review subagents and turns discovered lessons into concrete skill edits. CX Codex +1 5,300installs reflect Alireza Rezvani Pauses active task execution to re-evaluate conversation direction, assumptions, and bias across five analytical dimensions. 320installs reflect NeoLabHQ A skill that makes the agent reread its own answer and list the flaws before you accept the work. CX Codex +1 1,400installs memory-reflect basicmachines-co A background skill that reviews recent sessions and daily notes, pulls out what matters and folds it into long-term memory. Runs on a schedule or on demand. CX Codex +1 746installs openspec-context-loading forztf This skill finds specs, active changes and requirements in a project and hands the agent a ready summary. Useful when you need to know what OpenSpec already describes. CX Codex +1 1,100installs bmad-prfaq bmad-code-org This skill tests a product concept with a Working Backwards PRFAQ, moving from a finished-product press release to hard customer and stakeholder questions. CX Codex +1 11,300installs claude-memory-curator stark-ai-de Audits CLAUDE.md, rules, settings and auto memory in Claude, flags stale or conflicting entries and suggests where each one belongs. CX Codex +1 2,600installs context-canary JuliusBrussee Adds a per-turn canary line to every reply: your name, a turn counter, and an honest context self-check. You see the moment the agent stops holding early instructions. CX Codex +1 1,900installs remember jsmastery-pro Saves session state to memory.md at the end of a session and restores it at the start of the next one. Useful when your agent keeps starting from a blank slate. CX Codex +1 944installs

From the same set22

creative-writing-muse A skill for a single agent that switches stances on its own: plans, drafts, critiques and remembers. Useful when no subagents are around. CX Codex +1 494installs creative-research This skill gathers grounded material for a story question: history, culture, daily detail, how a trade actually works. You get back a sourced report. CX Codex +1 487installs information-hierarchy A skill for large human-facing output: reports, docs, multi-section explanations. The answer comes first, depth sits behind it. CX Codex +1 399installs structured-artifact A skill for building structured HTML artifacts: the agent decides how to present the content first, then picks the tools. CX Codex +1 387installs zoom-out Explores an unfamiliar area from several angles at once, then folds the findings into a single orientation map. CX Codex +1 386installs qi-layer A skill that sets the rules for writing and maintaining AGENTS.md and .context/CONTEXT.md so intent docs stay short and load-bearing. CX Codex +1 385installs knowledge-layers A skill that decides which layer holds a piece of knowledge: AGENTS.md, .context/, KB, docs/ or a work directory. Useful when the agent keeps looking in the wrong place. CX Codex +1 384installs md-validation Validates relative links between pages and Mermaid diagrams before you ship. Useful for multi-page artifacts and knowledge bases. CX Codex +1 383installs