Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

Back to skills

Project

ASecurity

GitHub Issues as the plan of record; agents read and update them. Auto-invoke on issue-linked branches. Triggers "what's the plan", "project status", "sync with github", "close the issue".

44 stars
0 votes
0 copies
0 views
Added 9/3/2026
ai-agentsrustgobashgitapi

Works with

api

Security Analysis

A100/100

Scanned 9/20/2026

Install to Claude Code

$npx -y skills add darkroomengineering/cc-settings --skill project --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Project?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Project
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/darkroomengineering-project/badge)](https://www.skillsdirectory.com/skills/darkroomengineering-project)

More formats (shields.io, HTML) on the badges page.

Download Zip
Files
SKILL.md
---
name: project
description: GitHub Issues as the plan of record; agents read and update them. Auto-invoke on issue-linked branches. Triggers "what's the plan", "project status", "sync with github", "close the issue".
---

# GitHub Project Sync

Bridge between coding-agent sessions and GitHub Issues/Projects. Issues are the plan — agents read them for context and update them with progress.

## Core Concept

GitHub Issues replace local PLAN.md files. Each issue contains:
- Scope and constraints
- Task breakdown (checkboxes)
- Design decisions and rationale
- Implementation notes (via comments)
- Linked commits and PRs

This means project context is **shared, versioned, and visible** to every team member and their agents — not locked in local handoff files.

## Actions

### Check current issue (auto on session start)

Detect the current branch and find its linked issue:

```bash
# Get current branch
BRANCH=$(git branch --show-current)

# Extract issue number from branch name (e.g., feat/123-description, fix/42-title)
ISSUE_NUM=$(echo "$BRANCH" | grep -oE '[0-9]+' | head -1)

# Read the issue for context
if [[ -n "$ISSUE_NUM" ]]; then
  gh issue view "$ISSUE_NUM" --comments
fi
```

If an issue is found, present a brief summary:
- Issue title and status
- Task checklist progress (X/Y completed)
- Most recent comment (latest context)
- Assigned labels and milestone

### Update issue with progress

After completing work or at session end:

```bash
# Add a progress comment
gh issue comment ISSUE_NUM --body "## Progress Update

### Completed
- [x] Task description
- [x] Another task

### Files Modified
- \`path/to/file.ts\` — description of change

### Notes
Any decisions made or context for next session.

### Next Steps
- [ ] Remaining work"
```

### Check off tasks in issue body

When tasks from the issue body are completed:

```bash
# View current issue body, update checkboxes, edit
gh issue edit ISSUE_NUM --body "$(updated body with checked items)"
```

### View project board status

```bash
# List issues assigned to you
gh issue list --assignee @me --state open

# List issues in a milestone
gh issue list --milestone "v2.0"

# List project items
gh project item-list PROJECT_NUM --owner ORG --format json
```

### Create an issue from a plan

When the user describes a feature or task:

```bash
gh issue create --title "feat: description" --body "$(cat <<EOF
## Goal
What we're building and why.

## Tasks
- [ ] Task 1 — verify: \`command\` → expected output
- [ ] Task 2
- [ ] Task 3

## Decisions
- Decision 1: rationale
- Decision 2: rationale

## Constraints
- Any known constraints or requirements

## Plan stamp
Written against $(git rev-parse --short HEAD) on $(git branch --show-current).
EOF
)"
```

The **plan stamp** anchors the issue to the commit it was written against —
file paths, line refs, and task assumptions are only guaranteed valid at that
SHA. Give tasks machine-checkable done criteria (command → expected output)
where possible, not prose.

Body shaping follows `rules/git.md` "Issue descriptions": observed effect
first, numbered one-action repro steps, one issue per problem — tangents
become their own linked issues.

### Reconcile a stale issue

Before resuming an issue whose plan stamp is behind the current HEAD, reconcile
instead of trusting it:

```bash
# What changed since the plan was written?
git log --oneline PLAN_SHA..HEAD
git diff --stat PLAN_SHA..HEAD
```

- **Verify checked tasks** — re-run their done-criteria commands; a task that
  no longer passes gets unchecked with a comment, not silently trusted.
- **Refresh drifted tasks** — file paths and line refs may have moved;
  re-check them against HEAD and edit the body.
- **Retire dead tasks** — work made obsolete by intervening merges gets
  struck through with a one-line reason, so future audits don't re-litigate it.
- Re-stamp the body with the new SHA once reconciled.

### Link commits to issues

When committing, reference the issue:

```bash
git commit -m "feat: description

Refs #ISSUE_NUM"
```

## Session Workflow

### Starting a session
1. Detect branch → find linked issue
2. Read issue body + recent comments for context
3. Present summary: "You're working on #123: Title. 3/7 tasks done. Last update: ..."

### During work
- Reference the issue task list for what to work on next
- Make progress on tasks, verify with build/tests

### Ending a session
1. Comment on the issue with progress update
2. Check off completed tasks in the issue body
3. Create handoff (existing system) for local session state

## Branch Naming Convention

For auto-detection, use branches that include the issue number:
```
feat/123-add-coupon-validation
fix/42-login-redirect-loop
chore/88-upgrade-dependencies
```

The skill extracts the first number from the branch name and looks up that issue.

## When There's No Linked Issue

If the branch doesn't match an issue:
- Show open issues assigned to the user: `gh issue list --assignee @me`
- Offer to create a new issue from the current work
- Fall back to the regular handoff system

## Integration with Handoffs

This skill **complements** the existing handoff system:
- **GitHub Issue** = shared project state (team-visible, persistent)
- **Local handoff** = session state (personal, ephemeral)

Both get updated. The issue is the source of truth for project progress. The handoff captures session-specific context (open files, debug state, personal notes).

Attribution

darkroomengineeringdarkroomengineering
View sourceMore from darkroomengineering →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1066601 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

686011 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

651 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →