# Spike Wrap Up

> A Claude skill from mattjaikaran/meridian.

- **Type:** Skill
- **Install:** `agentstack add skill-mattjaikaran-meridian-spike-wrap-up`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mattjaikaran](https://agentstack.voostack.com/s/mattjaikaran)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** Apache-2.0
- **Upstream author:** [mattjaikaran](https://github.com/mattjaikaran)
- **Source:** https://github.com/mattjaikaran/meridian/tree/main/skills/spike-wrap-up

## Install

```sh
agentstack add skill-mattjaikaran-meridian-spike-wrap-up
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# /meridian:spike-wrap-up — Close a Spike and Extract Learnings

Concludes a spike: records the outcome, extracts learnings into the DB, and closes
the gate so dependent plan phases can proceed.

## Arguments
- ` ""` — Close spike and record outcome (no learnings)
- ` "" --learnings "" "" ...` — Also extract learnings

## Keywords
spike, wrap-up, close, conclude, outcome, learnings, findings, gate

## Procedure

### Wrap up without explicit learnings
```bash
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from pathlib import Path
from scripts.db import open_project
from scripts.spikes import wrap_up_spike
with open_project('.') as conn:
    result = wrap_up_spike(
        conn,
        '',
        '',
        [],  # no explicit learnings
        Path('.'),
    )
    print(json.dumps(result, indent=2))
"
```

### Wrap up with learnings
```bash
PYTHONPATH=$MERIDIAN_HOME uv run --project $MERIDIAN_HOME -- python -c "
import json
from pathlib import Path
from scripts.db import open_project
from scripts.spikes import wrap_up_spike
with open_project('.') as conn:
    result = wrap_up_spike(
        conn,
        '',
        '',
        ['', ''],
        Path('.'),
    )
    print(json.dumps(result, indent=2))
"
```

## What Happens on Wrap-Up

1. Spike status → `closed`, `closed_at` set to now
2. Outcome written to DB and to `.planning/spikes//MANIFEST.md`
3. Each learning rule inserted into the `learning` table (scope: project, source: execution)
4. Gate is now clear — `/meridian:plan` on the linked phase can proceed

## Display Format

```
Spike wrapped up: 
Status: closed
Outcome: 

Learnings recorded: 
  1. 
  2. 

Gate cleared for phase: 
Next: run /meridian:plan on phase 
```

## When to Use
- You've finished the exploration and have an answer
- Use before starting `/meridian:plan` on the phase that triggered the spike
- After adding finding files to `.planning/spikes//findings/`

## Notes
- Learnings are stored with `source = 'execution'` and linked to the triggering phase
- The MANIFEST.md is updated in-place with the outcome section
- Once closed, a spike cannot be re-opened (create a new spike instead)

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mattjaikaran](https://github.com/mattjaikaran)
- **Source:** [mattjaikaran/meridian](https://github.com/mattjaikaran/meridian)
- **License:** Apache-2.0

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** yes
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-mattjaikaran-meridian-spike-wrap-up
- Seller: https://agentstack.voostack.com/s/mattjaikaran
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.