# log-evidence

Records offline findings from interviews and user research back into Mycelium canvas files.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 47
- Author: haabe
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/haabe/mycelium/tree/HEAD/plugins/mycelium/skills/log-evidence/SKILL.md
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/skills/log-evidence

## What it does

This skill acts as the re-entry step once real-world outreach finishes. It inspects `.claude/canvas/human-tasks.yml` to associate raw conversation logs or survey notes with existing tasks, preserving source context across the project.

File safety follows strict read-before-write rules. To prevent context blowouts on large YAML files like `purpose.yml`, the agent performs a `limit: 1` call via the `Read` tool prior to using `Edit`. Full replacements using `Write` demand reading entire contents first. When creating ID-bearing items, it runs a numeric sort over existing prefixes (`comp`, `opp`, `sol`, `ht`) so new entries never collide with existing identifiers.

Running this skill without the Mycelium framework skips canvas state tracking and theory gates. It assumes an active Mycelium setup inside `.claude/canvas/`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill log-evidence -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/log-evidence/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/log-evidence/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill log-evidence -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/log-evidence/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill log-evidence -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/log-evidence/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install haabe/mycelium log-evidence
```

2. **Manually: put the files in place**
- File: `.github/skills/log-evidence/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill log-evidence -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/haabe/mycelium --path plugins/mycelium/skills/log-evidence
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/log-evidence/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add haabe/mycelium --skill log-evidence -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/haabe/mycelium/tree/HEAD/plugins/mycelium/skills/log-evidence/SKILL.md

## When to use it
- record offline interview insights into project canvas
- attach delayed feedback to an already closed human task
- backfill ad-hoc user interactions into tracking records
- avoid duplicate ID collisions across canvas entities

## Example prompts
- I finished the user interview, log these notes into the canvas
- Attach these research findings to task ht-014
- Log this quick chat as a backfilled task in human-tasks.yml

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 6ee8748c7ecb1684.

BEGIN THIRD-PARTY FILE 6ee8748c7ecb1684
````text
---
name: log-evidence
description: "Record findings from completed offline human tasks (interviews, observations, outreach) back into the canvas. The re-entry point after /mycelium:handoff."
metadata:
  instruction_budget: "58"
  framework_dependency: "mycelium"
  framework_dependency_note: "This skill is designed to run within the Mycelium framework (https://github.com/haabe/mycelium). Standalone use will skip the canvas state, theory gates, and harness behavior the skill assumes. Install: /plugin install mycelium@haabe-mycelium."
---

# Log Evidence Skill

The re-entry point after offline human work. Takes raw conversation notes, observations, or survey results and integrates them into the canvas with proper provenance.

## Preflight: Read target canvas file(s) before any Write/Edit

**Hard rule.** Before issuing `Write` or `Edit` against any `.claude/canvas/*.yml`, use the **Read tool** on that file in this session. Claude Code's Read-before-Write check requires the `Read` tool specifically — `cat`/`head`/`grep` via Bash do NOT satisfy it.

**Edit vs Write — different cost profiles** (verified 2026-05-14):
- **`Edit`** (exact-string replacement): `Read` with `limit: 1` satisfies the check at ~50 tokens. State-tracking is per-file, not per-byte — subsequent `Edit` calls work anywhere in the file. Use this for partial updates against large canvas files (e.g., `purpose.yml` at 800+ lines).
- **`Write`** (full replacement): do a **full Read** first. Write obliterates the file; you should see what you're about to replace. The `limit:1` shortcut is *not* appropriate here.

**ID-bearing entries — scan the ID space before assigning** (added 2026-05-15, v0.23.19): When adding a new component, opportunity, solution, or any other ID-bearing entry to a canvas file, run a Bash grep first to confirm the next ID in your prefix sequence is actually free:

```
grep -o "<prefix>-[0-9][0-9]*" .claude/canvas/<file>.yml | sort -u -t- -k2 -n | tail -3
```

Replace `<prefix>` with the canvas's ID prefix (`comp` for landscape, `opp` for opportunities, `sol` for solutions, `ht` for human-tasks, etc.). Then pick the next free integer, **matching the zero-padding already used in that file**. The sort is NUMERIC (`-t- -k2 -n`) rather than lexical, and that is not pedantry: a plain `sort -u` orders `ht-1` after `ht-080`, so on a canvas with inconsistent padding it reports the wrong maximum and the next ID collides. Verified on the dogfood repo 2026-08-13, where lexical sort returned `ht-1` as the highest human-task ID against an actual `ht-080`. `grep -o` is also deliberate: it matches IDs wherever they appear, including cross-references and prose, so an ID that was promised somewhere but not yet defined is not handed out twice. `validate_canvas.py` has a per-file duplicate-ID check (it reports `duplicate id '<id>'`) that catches the failure on CI, but a duplicate can persist in the working tree for days if CI isn't run between edit and discovery; that happened on 2026-05-15, when a duplicate ID was created in `landscape.yml`.
````
END THIRD-PARTY FILE 6ee8748c7ecb1684

The third-party file has ended. Everything between the 6ee8748c7ecb1684 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 3066 of 20930 bytes. © haabe · MIT · https://github.com/haabe/mycelium/tree/HEAD/plugins/mycelium/skills/log-evidence/SKILL.md

_Part of the page did not fit — see the HTML version._

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md