reflect-skill — Claude Code plugin: mid-conversation reflection
Halts detail work and re-reads the whole conversation from the original goal, so you can see where the direction drifted.
/plugin marketplace add alirezarezvani/claude-skills
/plugin install reflect-skill@claude-code-skillsWhat reflect-skill does
The skill fires mid-conversation, either when you say "reflect" or when the thread has gone ten-plus turns deep on details with no strategic check-in. It stops the current line of work and re-reads the conversation from the original goal forward, not just the last few messages. Then it runs a five-dimension pass: original goal against current direction, unverified assumptions and skipped constraints, whether the problem is framed correctly, bias signals (confirmation, sunk cost, anchoring, complexity, recency), and whether the direction still serves the actual goals.
Output is flowing prose with no headers, ending in one recommendation: Continue, Pivot or Pause. Inside the plugin there is a reflection persona agent, a /cs-reflect slash command, and three stdlib Python scripts — one regex-scans the conversation for the five bias signals, one counts turns and detects implicit triggers, one verifies the output really ends with one of the three verdicts. Reference files cover the cognitive bias canon, honest-output discipline, and Schön's reflective practice.
There are no dependencies, which makes this the most portable piece of the collection: it runs in Claude CLI and on Claude.ai. The rule worth knowing is that the skill refuses to manufacture problems when the path is sound. You get either a specific reason why it holds up or evidence from the conversation for changing course — never a vague "looks good". If you want criticism for its own sake, look elsewhere.
What it helps with
- stop and check the current direction against the original goal
- surface unverified assumptions and skipped constraints
- catch confirmation or sunk-cost bias in a debate
- spot where a simple task got overcomplicated
- get a Continue, Pivot or Pause verdict instead of vague reassurance
Example prompts for the agent
- reflect — we've spent ten turns on details, are we still on track?
- /cs-reflect: step back and tell me if we're missing something
- zoom out and say honestly whether we're solving the right problem
How to install reflect-skill
Plugin marketplace
/plugin marketplace add alirezarezvani/claude-skills/plugin install reflect-skill@claude-code-skillsStep by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own
Questions about reflect-skill
How do I install reflect-skill in Claude?
Add the marketplace with /plugin marketplace add alirezarezvani/claude-skills, then install the plugin: /plugin install reflect-skill@claude-code-skills.
What does reflect-skill do?
It pauses detail work, re-reads the conversation from the original goal, and analyzes it across five dimensions, from direction drift to cognitive bias. It closes with a Continue, Pivot or Pause recommendation.
Does it need any dependencies?
No. It is a pure-reasoning skill, its scripts use the Python standard library, and it works in Claude CLI and on Claude.ai.
Source text
reflect · MIT
# reflect
Mid-conversation reflection skill. Pauses execution and **zooms out from detail-mode** to honestly reassess direction, assumptions, and bias.
## What this skill does
When invoked mid-conversation (explicitly or via implicit signals like 10+ turns deep on details without strategic check-in), the skill:
1. **Halts the current thread** and re-reads the full conversation from the original goal forward — not just recent turns
2. Runs the **5-dimension analysis framework**:
- **Macro Perspective** — original goal vs current direction; drift detection
- **Gap Analysis** — unverified assumptions, missing stakeholders, skipped constraints, dismissed alternatives
- **Reflective Inquiry** — is the problem framed correctly? Right problem vs adjacent easier one? Simpler path overcomplicated? Harder valuable path avoided?
- **Bias Check** — confirmation / sunk cost / anchoring / complexity / recency
- **Contextual Alignment** — does direction serve actual goals + best use of time + external factors honored
3. Delivers **flowing prose** (no headers, conversational tone)
4. Ends with a **clear directional recommendation**: Continue / Pivot / Pause
## Sibling skill relationship
Productivity sibling of `capture` (Slice 1). Both share light-prompt-flow shape, max-1-question intake, fast-to-action discipline. Different mode: `capture` organizes external dumps; `reflect` re-examines internal conversation state.
## Honest-output discipline
The skill explicitly does NOT manufacture problems when things are on track. "This is solid because X" is a valid output. **Vague reassurance ("looks good!") is rejected** — when the path is solid, the skill states specific reasoning for why; when the path needs correction, the skill states specific evidence from the conversation.
## Source spec
`megaprompts/02-reflect-megaprompt.md` (maintainer-local draft spec — gitignored, not in the public repo) (PR #657).
## Plugin layout
```
productivity/reflect/
├── .claude-plugin/plugin.json
├── README.md
├── agents/cs-reflect.md ← reflection persona, honest-output enforcer
├── commands/cs-reflect.md ← /cs-reflect (or auto-triggers on phrases)
└── skills/reflect/
├── SKILL.md
├── references/
│ ├── cognitive_bias_canon.md ← 5 biases + recognition cues (7+ sources)
│ ├── honest_output_discipline.md ← anti-manufactured-problems (7+ sources)
│ └── conversation_reflection_practice.md ← Schön reflective practice canon (7+ sources)
└── scripts/
├── bias_pattern_detector.py ← stdlib: regex scan for 5-bias signals in conversation
├── conversation_depth_analyzer.py ← stdlib: turn count + implicit-trigger signal detection
└── directional_recommendation_validator.py ← stdlib: verify output ends with Continue/Pivot/Pause
```
## Dependencies
**None.** Pure-reasoning skill — most portable in the v2 collection. Works in Claude Code CLI + Claude.ai web natively.
## License
MIT.
© Alireza Rezvani · MIT · alirezarezvani/claude-skills
