Run any Skill in Manus with one click

pull-contributions

Stars2

Forks0

UpdatedJune 12, 2026 at 22:19

Pull generalized contributions from a project into Memnyx. Runs `sanitizer --check` as a mandatory gate before integration.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

MDGrey33

MDGrey33/memnyx

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	pull-contributions
description	Pull generalized contributions from a project into Memnyx. Runs `sanitizer --check` as a mandatory gate before integration.
user_invocable	true
args	Path to a workspace's contributions/ folder (e.g., <workspace>/contributions/)

Model Selection

See .claude/skills/_shared/MODEL_SELECTION.md (in your workspace) for full policy.

Default model: Haiku 4.5 — mechanical file copy + path rewrite from project to Memnyx
Promote to Sonnet when: a contribution needs de-identification or rewording before merging
Promote to Opus when: never

Pull Contributions — Integrate Project Learnings into Memnyx

You are integrating generalized contributions from a project into Memnyx. This skill is meant to be run from the Memnyx repo, not from a project.

Steps

Locate contributions: The user provides the path to <workspace>/contributions/ (e.g., ~/workspace/contributions/). Read all .md files in that folder that do not start with integrated- or skipped-. Files with the integrated- prefix have already been applied; files with the skipped- prefix were reviewed and rejected — skip both silently. sanitizer-report-*.md files are scan reports, not contributions — skip those too.

If no path is provided, ask the user for it.
Sanitize gate (MANDATORY): Run sanitizer in check mode on the contributions folder:
```
/sanitizer <contributions-folder-path> --check --mode=boilerplate
```
- Exit code 0 → proceed.
- Exit code 1 → halt. Surface the sanitizer report. Do NOT pull any contribution with findings. Ask the user to run /sanitizer <path> --apply in the source project to fix, then re-run this skill.
- Do not duplicate sanitization logic here — the sanitizer is the single source of truth for what leaks.
Review each contribution (content check only, not PII/secret — that's sanitizer's job):
- Actionable: The recommendation is concrete enough to apply.
- Categorized correctly: The type and target file make sense.

Present a summary of all contributions found:

Contributions found: [count]
─────────────────────────────
1. [title] (type: skill-update, target: .claude/skills/hello/SKILL.md)
2. [title] (type: convention, target: CLAUDE.md)
...

Ask: "Which contributions should I integrate? (all / specific numbers / none)"

For each approved contribution, apply the changes:
- skill-update: Read the target skill file, apply the recommended changes, show the diff to the user for approval before writing.
- new-skill: Create the new skill directory and SKILL.md. Show the content for approval.
- convention: Add to the relevant section of CLAUDE.md or .claude/docs/conventions.md. Budget gate for always-loaded targets: if the target is a file CLAUDE.md @-imports (e.g. .claude/docs/agent-guardrails.md), measure it first (tokens ≈ bytes/4) against the always-loaded thresholds in .claude/skills/finance-controller/references/thresholds.md. At yellow (>2,000 tokens) or above, the addition is zero-sum: draft a displacement or condensation of at least the addition's size in the same change, and let the user decide which rule loses its slot. Safety rules (production read-only, secrets handling, and similar) are exempt from displacement and may land at yellow — flag the overage instead, so compression rebalances among style and process rules.
- memory-template: Update the memory file templates (MEMORY.md, lessons-learned.md, etc.).
- docs: Update the target doc file.
- config: Update the target config file. Be extra careful with .mcp.json and settings.json.
Always ask for approval before writing any changes. Show exact diffs or new content.
After integration, ask: "Should I mark the processed contributions as integrated?"
- If yes, rename applied contribution files to add an integrated- prefix (e.g., integrated-2025-06-15-improve-hello-mcp-retry.md), and contributions the user reviewed and rejected to add a skipped- prefix. Both prevent re-processing on future runs.
Update CLAUDE.md if new skills were added (add to the skills table).

Report:

Pull Complete
=============
Reviewed: [count] contributions
Integrated: [count]
Skipped: [count] (with reasons)
Files modified: [list]

Remember to commit the changes to the Memnyx repo.

Important Rules

Never auto-apply: Always show changes and get user approval before modifying any file
Flag leaks: If a contribution contains project-specific details, flag it and suggest how to generalize
Preserve structure: When editing existing files, maintain their format and style
One at a time: Apply contributions individually so the user can approve/reject each one

More from this repository

same repository

claude-expert

MDGrey33/memnyx

Definitive reference for how Claude Code works — disambiguates skills vs hooks vs subagents vs MCPs vs slash commands vs memory vs settings. Use when asked "how does Claude Code X work", "what's the difference between X and Y", "where should this live", "build me a [skill|hook|agent|mcp|slash command]", "configure Claude Code", or when picking the right surface for a new capability.

2026-06-272

scribe

MDGrey33/memnyx

Scribe — the project-documentation skill. Generate or maintain a project's Claude-facing documentation (CLAUDE.md, .claude/docs/*, project-context.md, README) from verified facts. Use when the user says "document this project", "write the docs for X", "the docs are stale", "fill in the .claude docs", or "/scribe". Detects existing doc state and routes between from-scratch and update. Verify-before-assert is the core discipline — confirmed facts go to committed docs, inferred/uncertain ones go to a separate hazards artifact, never silently into the repo.

2026-06-252

say-it

MDGrey33/memnyx

Speak content aloud via Kokoro neural TTS (local, offline). Use when the user says "read it for me", "read it to me", "play it in audio", "say it", "speak it", "read that aloud", "/say-it", or asks to hear something spoken instead of reading it.

2026-06-252

setup-voice

MDGrey33/memnyx

Install a local neural voice interface for Claude Code on macOS Apple Silicon. Wires mlx-whisper (STT) + Kokoro TTS (offline neural voices) into voice-claude and vtranscribe CLI scripts. Two voice contexts — personal (af_heart) and tech (af_bella). Multi-session safe — concurrent sessions speak in turn (global lock) and announce their name. No cloud APIs, no API keys.

2026-06-252

collect-my-activity

MDGrey33/memnyx

Collect the user's daily work activity from Slack, Jira, Confluence, GitHub, and Google Drive with source links

2026-06-252

collect-team-activity

MDGrey33/memnyx

Collect a team member's daily work activity from Slack, Jira, Confluence, and GitHub

2026-06-252

Pull Contributions — Integrate Project Learnings into Memnyx

You are integrating generalized contributions from a project into Memnyx. This skill is meant to be run from the Memnyx repo, not from a project.

Steps

Locate contributions: The user provides the path to <workspace>/contributions/ (e.g., ~/workspace/contributions/). Read all .md files in that folder that do not start with integrated- or skipped-. Files with the integrated- prefix have already been applied; files with the skipped- prefix were reviewed and rejected — skip both silently. sanitizer-report-*.md files are scan reports, not contributions — skip those too.

If no path is provided, ask the user for it.

Sanitize gate (MANDATORY): Run sanitizer in check mode on the contributions folder:

/sanitizer <contributions-folder-path> --check --mode=boilerplate

Exit code 0 → proceed.
Exit code 1 → halt. Surface the sanitizer report. Do NOT pull any contribution with findings. Ask the user to run /sanitizer <path> --apply in the source project to fix, then re-run this skill.
Do not duplicate sanitization logic here — the sanitizer is the single source of truth for what leaks.

Review each contribution (content check only, not PII/secret — that's sanitizer's job):

Actionable: The recommendation is concrete enough to apply.
Categorized correctly: The type and target file make sense.

Present a summary of all contributions found:

Contributions found: [count]
─────────────────────────────
1. [title] (type: skill-update, target: .claude/skills/hello/SKILL.md)
2. [title] (type: convention, target: CLAUDE.md)
...

Ask: "Which contributions should I integrate? (all / specific numbers / none)"

For each approved contribution, apply the changes:

skill-update: Read the target skill file, apply the recommended changes, show the diff to the user for approval before writing.
new-skill: Create the new skill directory and SKILL.md. Show the content for approval.
convention: Add to the relevant section of CLAUDE.md or .claude/docs/conventions.md. Budget gate for always-loaded targets: if the target is a file CLAUDE.md @-imports (e.g. .claude/docs/agent-guardrails.md), measure it first (tokens ≈ bytes/4) against the always-loaded thresholds in .claude/skills/finance-controller/references/thresholds.md. At yellow (>2,000 tokens) or above, the addition is zero-sum: draft a displacement or condensation of at least the addition's size in the same change, and let the user decide which rule loses its slot. Safety rules (production read-only, secrets handling, and similar) are exempt from displacement and may land at yellow — flag the overage instead, so compression rebalances among style and process rules.
memory-template: Update the memory file templates (MEMORY.md, lessons-learned.md, etc.).
docs: Update the target doc file.
config: Update the target config file. Be extra careful with .mcp.json and settings.json.

Always ask for approval before writing any changes. Show exact diffs or new content.

After integration, ask: "Should I mark the processed contributions as integrated?"

If yes, rename applied contribution files to add an integrated- prefix (e.g., integrated-2025-06-15-improve-hello-mcp-retry.md), and contributions the user reviewed and rejected to add a skipped- prefix. Both prevent re-processing on future runs.

Update CLAUDE.md if new skills were added (add to the skills table).

Report:

Pull Complete
=============
Reviewed: [count] contributions
Integrated: [count]
Skipped: [count] (with reasons)
Files modified: [list]

Remember to commit the changes to the Memnyx repo.

Important Rules

Never auto-apply: Always show changes and get user approval before modifying any file

Flag leaks: If a contribution contains project-specific details, flag it and suggest how to generalize

Preserve structure: When editing existing files, maintain their format and style

One at a time: Apply contributions individually so the user can approve/reject each one