memory
ALWAYS ACTIVE — Persistent memory protocol. You MUST save decisions, conventions, bugs, and discoveries to engram proactively. Do NOT wait for the user to ask.
Issue creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a GitHub issue, reporting a bug, or requesting a feature.
$ npx -y skills add Gentleman-Programming/engram --skill issue-creation --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/issue-creationContext preview
The summary Claude sees to decide when to auto-load this skill.
Issue creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a GitHub issue, reporting a bug, or requesting a feature.
name: engram-issue-creation description: > Issue creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a GitHub issue, reporting a bug, or requesting a feature. license: Apache-2.0 metadata: author: gentleman-programming version: "1.0"
Use this skill when:
---
1. **Blank issues are disabled** — MUST use the matching bug, feature, docs, or tracked-question template 2. **Every issue gets `status:needs-review` automatically** on creation 3. **A maintainer MUST replace `status:needs-review` with `status:approved`** before any PR can be opened 4. **General questions go to [Discussions](https://github.com/Gentleman-Programming/engram/discussions)**; questions requiring tracked work use `type:question`
---
1. Consider searching existing issues for duplicates 2. Choose the correct template (Bug Report, Feature Request, Documentation Improvement, or Tracked Question) 3. Fill in ALL required fields 4. Submit → issue gets status:needs-review automatically 5. Wait for a maintainer to replace status:needs-review with status:approved 6. Only then open a PR linking this issue
---
Template: `.github/ISSUE_TEMPLATE/bug_report.yml` Auto-labels: `type:bug`, `status:needs-review`
| Field | Description | |-------|-------------| | **Bug Description** | Clear description of the bug | | **Steps to Reproduce** | Numbered steps to reproduce | | **Expected Behavior** | What should have happened | | **Actual Behavior** | What happened instead (include errors/logs) | | **Operating System** | Dropdown: macOS, Linux variants, Windows, WSL | | **Engram Version** | Output of `engram version` | | **Agent / Client** | Dropdown: Claude Code, OpenCode, Gemini CLI, Cursor, Windsurf, Other |
| Field | Description | |-------|-------------| | **Relevant Logs** | Log output (auto-formatted as code block) | | **Additional Context** | Screenshots, workarounds, extra info |
gh issue create --template "bug_report.yml" \ --title "fix(store): duplicate observations on concurrent saves" \ --body " ### Bug Description When two agents save observations concurrently, duplicates are created. ### Steps to Reproduce 1. Start two engram instances pointing to the same DB 2. Both save an observation with the same title simultaneously 3. Query observations — duplicates appear ### Expected Behavior The second save should upsert, not insert a duplicate. ### Actual Behavior Two identical observations exist with different IDs. ### Operating System macOS ### Engram Version 0.3.1 ### Agent / Client Claude Code ### Relevant Logs \`\`\` UNIQUE constraint failed: observations.title \`\`\` "
---
Template: `.github/ISSUE_TEMPLATE/feature_request.yml` Auto-labels: `type:feature`, `status:needs-review`
| Field | Description | |-------|-------------| | **Problem Description** | The pain point this feature solves | | **Proposed Solution** | How it should work from the user's perspective | | **Affected Area** | Dropdown: CLI, MCP Server, TUI, Store, Sync, Skills, Documentation, Other |
| Field | Description | |-------|-------------| | **Alternatives Considered** | Other approaches or workarounds | | **Additional Context** | Mockups, examples, references |
gh issue create --template "feature_request.yml" \
--title "feat(cli): add --json flag to mem search" \
--body "
### Problem Description
When scripting with engram, parsing the human-readable output of mem search is fragile. There's no machine-readable output format.
### Proposed Solution
Add a \`--json\` flag to \`engram mem search\` that outputs results as JSON.
Example:
\`\`\`bash
engram mem search \"auth middleware\" --json
\`\`\`
Expected output:
\`\`\`json
[{\"id\": 42, \"title\": \"JWT auth middleware\", \"type\": \"decision\", ...}]
\`\`\`
### Affected Area
CLI (commands, flags)
### Alternatives Considered
Using \`jq\` to parse the current output, but it's unreliable since the format isn't structured.
"---
Template: `.github/ISSUE_TEMPLATE/tracked_question.yml` Auto-labels: `type:question`, `status:needs-review`
Use this form only when the answer requires maintainer investigation, a repository change, or a durable decision. Send general questions and support to Discussions.
Required fields: the question, why issue tracking is needed, and the affected area. Additional context is optional.
---
| Template | Labels added | |----------|-------------| | Bug Report | `type:bug`, `status:needs-review` | | Feature Request | `type:feature`, `status:needs-review` | | Documentation Improvement | `type:docs`, `status:needs-review` | | Tracked Question | `type:question`, `status:needs-review` |
| Label | When to apply | |-------|--------------| | `status:approved` | Issue accepted for implementation — PRs can now be opened | | `priority:critical` | Critical bug or urgent feature | | `priority:high` | High priority | | `priority:medium` | Important but not blocking | | `priority:low` | Nice to have | | `status:possible-duplicate` | Duplicate under evaluation | | `status:wontfix` | Closed without implementation, including confirmed duplicates | | `resolution:duplicate` | Confirmed duplicate after closure |
---
1. New issue arrives with status:needs-review 2. Review the issue — is it valid, clear, and in scope? 3. If YES → replace status:needs-review with status:approved 4. If NO → comment with reas
Persistent memory system for AI coding agents. Agent-agnostic Go binary with SQLite + FTS5, MCP server, HTTP API, CLI, and TUI.
Repo: Gentleman-Programming/engram
ALWAYS ACTIVE — Persistent memory protocol. You MUST save decisions, conventions, bugs, and discoveries to engram proactively. Do NOT wait for the user to ask.
Architecture guardrails for Engram across local store, cloud sync, dashboard, and plugins. Trigger: Any change that affects system boundaries, ownership, state…
Backlog triage protocol for Engram: audit open issues and PRs, classify each item, infer maintainer ideology from comments, and produce an actionable…
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for…
Product and business-rule guardrails for Engram. Trigger: Any change that affects sync behavior, project controls, permissions, or memory semantics.
Commit and branch naming standards for Engram contributors, enforced by GitHub rulesets. Trigger: Any commit creation, review, or branch cleanup.