evolve-lite:recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
Best use case
evolve-lite:recall is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
Teams using evolve-lite:recall should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/evolve-lite-recall/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How evolve-lite:recall Compares
| Feature / Agent | evolve-lite:recall | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Entity Retrieval
## Overview
This skill loads relevant stored Evolve entities into the current turn before substantive work begins.
Use this skill first whenever the task involves:
- code changes
- debugging
- code review
- repo exploration
- file inspection
- environment/tooling investigation
Skip only for trivial conversational requests with no local context.
## Required Action
Before any non-trivial local work, you must complete the recall workflow below. Reading this `SKILL.md` alone does not satisfy the skill.
### Completion Rule
Do not proceed to other analysis or tool use until all steps below are complete.
1. If a manifest has already been injected for this turn, use it to pick which entity files to open. Otherwise inspect `${EVOLVE_DIR:-.evolve}/entities/` and `${EVOLVE_DIR:-.evolve}/public/` for guidance relevant to the current task.
2. Read each matching entity file that appears relevant.
3. Summarize the applicable guidance in your own words before proceeding.
4. If no relevant entities exist, state that explicitly before proceeding.
### Required Visible Completion Note
Before moving on, produce an explicit completion note in your reasoning or user update using one of these forms:
- `Recall complete: searched ${EVOLVE_DIR:-.evolve}/entities/, read <files>, applicable guidance: <summary>`
- `Recall complete: searched ${EVOLVE_DIR:-.evolve}/entities/, no relevant entities found`
### Minimum Acceptable Procedure
1. List or search files under `${EVOLVE_DIR:-.evolve}/entities/` and `${EVOLVE_DIR:-.evolve}/public/` (or read the injected manifest if one is present).
2. Identify candidate entities relevant to the task.
3. Open and read those entity files.
4. Summarize what applies, or state that nothing applies.
### Failure Conditions
The skill is not complete if any of the following are true:
- You only read this `SKILL.md`
- You did not inspect `${EVOLVE_DIR:-.evolve}/entities/`
- You did not read the relevant entity files
- You proceeded without stating whether guidance was found
## How It Works
Bob has no auto-injection hook for entity retrieval. Complete the **Required Action** workflow above on every applicable task.
Entities can come from multiple sources:
- **Private entities**: Your own local entities (not shared)
- **Subscribed entities**: Entities cloned from any configured repo —
read-scope subscriptions and write-scope publish targets both live
under `${EVOLVE_DIR:-.evolve}/entities/subscribed/{name}/`
## Entities Storage
```text
.evolve/entities/
guideline/
use-context-managers-for-file-operations.md <- private
subscribed/
memory/ <- write-scope clone (publishes land here)
guideline/
my-published-guideline.md
alice/ <- read-scope clone
guideline/
alice-guideline.md <- annotated [from: alice]
```
The manifest output is human-readable:
```text
- `.evolve/entities/guideline/use-context-managers-for-file-operations.md` [guideline] — When processing files or managing resources
- `.evolve/entities/subscribed/alice/guideline/error-handling.md` [guideline] — When writing error handlers
```
Each file still uses markdown with YAML frontmatter:
```markdown
---
type: guideline
trigger: When processing files or managing resources
---
Use context managers for file operations
## Rationale
Ensures proper resource cleanup
```
## On-Demand Expansion
When a manifest entry's trigger matches the current task, use `read_file` to load the full entity. The file body contains the guideline content and an optional `## Rationale` section.Related Skills
recall
Must be used at the start of any non-trivial task involving code changes, debugging, repo exploration, file inspection, or environment/tooling investigation to surface stored guidance before analysis or tool use.
evolve-lite:unsubscribe
Remove a repo from the unified repos list and delete its local clone.
evolve-lite:sync
Pull the latest guidelines from every configured repo (read- and write-scope).
evolve-lite:subscribe
Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.
evolve-lite:save
Captures the current session's successful workflow and saves it as a reusable skill with SKILL.md and helper scripts
evolve-lite:save-trajectory
Save the current conversation as a trajectory JSON file in OpenAI chat completion format for analysis and fine-tuning
evolve-lite:publish
Publish a private guideline to a configured write-scope repo.
evolve-lite:provenance
Analyze saved trajectories and recall audit events offline to record whether recalled guidelines influenced completed sessions.
evolve-lite:learn
Must be used near the end of any non-trivial turn that produced potentially reusable tools, guidance, errors, workarounds, or workflows, so those lessons are saved for future turns.
unsubscribe
Remove a repo from the unified repos list and delete its local clone.
sync
Pull the latest guidelines from every configured repo (read- and write-scope).
subscribe
Add a shared guidelines repo (read-scope subscription or write-scope publish target) to the unified repos list.