Automated summary
Finalizes the current pipeline by verifying mandatory gates, updating the spec, moving files, capturing knowledge, and reporting metrics.
Strengths
- Enforces mandatory review and build checks before finalizing
- Maintains spec integrity and traceability
- Captures patterns and metrics for future reference
- Supports cancellation flow for incomplete pipelines
Limitations
- Assumes a specific project structure (.claude/)
- Relies on external scripts (rtk, sync-registry)
- No rollback mechanism after completion
After successful implementation and review to formally close a pipeline.
When the user is still iterating or hasn't run a review.
Security analysis
SafeThe skill manages internal pipeline state files (move, delete, update) and runs pre-existing project scripts; it does not exfiltrate data, execute downloaded payloads, or perform destructive system-wide actions. All file operations are scoped to the project's .claude directory.
No concerns found
How this analysis is madeExamples
/completeI want to cancel the current pipeline./complete - Finalize Pipeline
Trigger
/complete
Description
Finalizes the current pipeline, either completing or canceling.
Verification Gate (MANDATORY)
- Review completed: Check pipeline state — review agent MUST have run and returned APPROVED. If not → dispatch review first (see resume.md step 19)
- Build passes: run build command for each affected subproject (from pipeline-config.md)
- Changes match spec: each
[x]corresponds to a real file - Zero CRITICAL issues: review report shows zero CRITICAL violations (SOLID, design system, patterns, i18n, integration)
- No regressions: existing features still work
If ANY gate fails: do NOT mark complete → report what failed + suggest fix. If review wasn't run → run it now before completing.
Action
- Locate active spec in
.claude/spec/active/ - If none exists → inform user and stop
- Spec Checkpoint — update spec header:
### Status: completed### Phase: CLOSE### Checkpoint: {ISO timestamp now}- Mark all remaining
[ ]as[x]
- Entity Registry — update if needed:
node .claude/scripts/sync-registry.js
- Move spec from
.claude/spec/active/to.claude/spec/completed/ - Pipeline State — cleanup:
- Extract
spec-namefrom the spec directory (e.g.2026-02-26-linked-services-card) - Delete
.claude/.pipeline-states/{spec-name}.json(removes from statusline) 6b. Knowledge Capture: - Review patterns discovered during this pipeline
- For each significant pattern/convention/entity discovered:
echo '{"type":"pattern","name":"...","description":"...","source":"{spec-name}"}' | node .claude/scripts/knowledge-update.js - Focus on: naming conventions used, architectural decisions, integration patterns
- Skip trivial or already-known patterns
- Extract
6c. Token Economy — RTK report (if available):
- Run
rtk gain --all --format jsonvia Bash - If RTK available: extract
saved_tokensandsavings_pct - Include in output block below 6d. Metrics Archive:
- Read metrics from
.claude/.pipeline-states/{spec-name}.json - If metrics exist, ensure
.claude/metrics/directory exists - Save to
.claude/metrics/{spec-name}.json:{ "name": "{spec-name}", "completedAt": "{ISO timestamp}", "durationMs": "{calculated from startedAt to now}", "apiCalls": "{from metrics}", "retries": "{from metrics}", "toolBreakdown": "{from metrics}", "rtkSavings": { "saved": N, "pct": N } } - If no metrics in state file, skip silently
-
Output — visual feedback:
================================================================ PIPELINE COMPLETE — {spec-name} Agents: {n} ok | Files: {created} created, {modified} modified [v] Registry updated | [v] Spec moved to completed/ Token Economy: {saved}k saved ({pct}% reduction) — RTK ================================================================If RTK is not installed or the gain command fails, omit the Token Economy line.
Cancellation Flow
If the user wants to cancel (not complete):
- Update spec:
### Status: cancelled - Move to
completed/anyway (for history) - Delete
.claude/.pipeline-states/{spec-name}.json - Output: "Pipeline cancelled. Spec archived in completed/."
Results Documentation
On completion, the output must include:
- Summary of changes (what and why)
- Files created/modified
When to Use
- After successful implementation and review
- To cancel an ongoing pipeline
- To force close if something went wrong
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/complete-pipeline-mrwakej8/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/complete-pipeline-mrwakej8' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/complete-pipeline-mrwakej8/download' --output '.skill-downloads/complete-pipeline-mrwakej8/SKILL.md.part' && mv '.skill-downloads/complete-pipeline-mrwakej8/SKILL.md.part' '.skill-downloads/complete-pipeline-mrwakej8/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
This file does not provide a usable name/description header for this native procedure. It remains available to download and inspect; use the manual method below.
Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/complete-pipeline-mrwakej8/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Ansible PR Review
DevOps
Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.