pipeline-reflection-ux
Standardizes router-facing narration to keep pipeline reflections concise and explicit.
Install
mkdir -p .claude/skills/pipeline-reflection-ux && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12268" && unzip -o skill.zip -d .claude/skills/pipeline-reflection-ux && rm skill.zipInstalls to .claude/skills/pipeline-reflection-ux
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Improve router-facing pipeline and reflection narration to reduce noisy status churn and make Step 0/Reflection outcomes explicit. Use when updating Router output contract, reflection reminder wording, or post-pipeline notification batching.Key capabilities
- →Make Step 0 visible in router narration
- →Emit Step 0 completion before TaskList()
- →Emit a one-line reflection outcome with report path
- →Batch late post-pipeline notifications into one summary
- →Preserve existing guardrail semantics
How it works
The skill defines a workflow to structure pipeline and reflection narration, ensuring specific events like Step 0 visibility and reflection outcomes are explicitly reported. It also manages notification batching.
Inputs & outputs
When to use pipeline-reflection-ux
- →Improve pipeline output
- →Format reflection narration
- →Batch pipeline notifications
About this skill
Pipeline Reflection UX
Use this skill to keep pipeline/reflection output concise, explicit, and low-noise.
Workflow
- Make Step 0 visible in router narration.
- Emit Step 0 completion before
TaskList(). - Emit a one-line reflection outcome with report path.
- Batch late post-pipeline notifications into one summary.
- Keep guardrail semantics unchanged (
blockstaysblock).
Required Checks
- Add/adjust tests before behavior changes.
- Confirm no regression in routing/taskupdate/read-safety tests.
- Verify debug-log counts improve for repeated violations/noise.
Iron Laws
- ALWAYS emit Step 0 narration (pending reflections count) before any
TaskList()call — omitting the narration makes reflection spawning invisible to the user and breaks the pipeline audit trail. - NEVER batch reflection spawns with tool calls that depend on their results — reflection agents must complete before the router proceeds to routing; mixing them creates race conditions.
- ALWAYS emit a one-line reflection outcome (report path + summary) after reflection-agent completes — without this, the user cannot distinguish a completed reflection from a skipped one.
- NEVER emit one status message per late-completing background agent — per-agent late notifications create noise storms; batch all late completions into one summary after drain gate passes.
- ALWAYS preserve existing
blocksemantics when modifying pipeline narration — changing guardrail modes while fixing UX copy conflates two concerns and masks the behavioral impact of either change.
Anti-Patterns
| Anti-Pattern | Why It Fails | Correct Approach |
|---|---|---|
| Omitting Step 0 narration | Reflection spawning invisible to user; pipeline audit trail broken | Always emit "Step 0: N pending reflections..." before spawning reflection agents |
| Missing one-line reflection outcome | User cannot distinguish completed reflection from skipped one | Emit report path + one-line summary after every reflection-agent completion |
| One status message per late-completing agent | Creates noise storms; clutters pipeline output | Batch all late completions into one summary message after drain gate passes |
| Changing guardrail modes while fixing UX copy | Conflates two changes; behavioral impact of each masked in review | Separate UX copy changes from guardrail mode changes in distinct commits |
| Emitting Step 0 completion after TaskList() | Violates router output contract; narration out of sequence | Emit "Step 0 complete." before calling TaskList(), not after |
Memory Protocol (MANDATORY)
Before starting:
Read .claude/context/memory/learnings.md
After completing:
- New pattern →
.claude/context/memory/learnings.md - Issue found →
.claude/context/memory/issues.md - Decision made →
.claude/context/memory/decisions.md
ASSUME INTERRUPTION: If it's not in memory, it didn't happen.
References
- Detailed UX review:
references/ui-reflection-review.md - Troubleshooting runbook:
.claude/docs/TROUBLESHOOTING.md - Task tracking protocol:
.claude/docs/@TASK_TRACKING_GUIDE.md
When not to use it
- →When changing guardrail modes, as this should be a separate commit
- →When emitting one status message per late-completing background agent, as this creates noise
- →When batching reflection spawns with tool calls that depend on their results
Limitations
- →The skill does not change guardrail semantics; it only affects narration.
- →It requires adding or adjusting tests before behavior changes.
- →It requires confirming no regression in routing/taskupdate/read-safety tests.
How it compares
This skill provides a structured approach to pipeline narration, preventing noisy status churn and making reflection outcomes explicit, unlike an unstructured or manual reporting process.
Compared to similar skills
pipeline-reflection-ux side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| pipeline-reflection-ux (this skill) | 0 | 3mo | Review | Intermediate |
| coderabbit-observability | 1 | 27d | Review | Advanced |
| healthcheck | 0 | 2mo | No flags | Beginner |
| phoenix-observability | 3 | 7mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by oimiragieo
View all by oimiragieo →You might also like
coderabbit-observability
jeremylongshore
Set up comprehensive observability for CodeRabbit integrations with metrics, traces, and alerts. Use when implementing monitoring for CodeRabbit operations, setting up dashboards, or configuring alerting for CodeRabbit integration health. Trigger with phrases like "coderabbit monitoring", "coderabbit metrics", "coderabbit observability", "monitor coderabbit", "coderabbit alerts", "coderabbit tracing".
healthcheck
gkvoelkl
Check Selma's system health: Ollama reachability, configured model availability, config validity, workspace files, loaded skills, session store, and gateway status. Trigger on: healthcheck, health check, /healthcheck, alles ok, status check, ist selma ok, system status.
phoenix-observability
davila7
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
phoenix-tracing
Arize-ai
OpenInference semantic conventions and instrumentation for Phoenix AI observability. Use when implementing LLM tracing, creating custom spans, or deploying to production.
genkit-production-expert
jeremylongshore
Build production Firebase Genkit applications including RAG systems, multi-step flows, and tool calling for Node.js/Python/Go. Deploy to Firebase Functions or Cloud Run with AI monitoring. Use when asked to "create genkit flow" or "implement RAG". Trigger with relevant phrases based on skill purpose.
klingai-usage-analytics
jeremylongshore
Build usage analytics and reporting for Kling AI. Use when tracking generation patterns, analyzing costs, or creating dashboards. Trigger with phrases like 'klingai analytics', 'kling ai usage report', 'klingai metrics', 'video generation stats'.