Check progress and suggest next task

VerifiedCaution

Check progress and suggest next task by reading the latest dated planning file, analyzing git history and task completion status, then presenting current phase and progress in a table. It identifies the next priority task and suggests running /clarify to start it.

Sby Skills Guide Bot
DevelopmentBeginner
2/28/2026
Claude Code
#session-start#project-planning#git-workflow#task-tracking#context-management

Recommended for

Automated summary

At session start, this skill reads the latest dated planning file, checks Git log and status, then summarizes the current phase, progress, and the next task to pick up.

Strengths

  • Merges checkbox state from the planning file with `git log --oneline -5` and `git status --short` to ground progress in real repository state
  • Renders per-phase progress as a compact table with βœ… / πŸ”„ markers and a completed/total ratio
  • Deliberately terse output (5-10 lines) ending in one concrete action: run `/clarify`
  • Includes a fallback: with no planning file, it infers status from Git history and code state

Limitations

  • Reads only the single most recent planning file (highest YYYYMMDD- prefix), so unfinished tasks in older files can be missed
  • Assumes specific conventions β€” dated planning files, `[ ]`/`[x]` checkboxes, and a `.claude/ai-context/architecture.md` file
  • Does no actual work itself; it stops at a suggestion and hands off to `/clarify`, tying it to that Claude Code workflow
When to use it

Use it when starting a work session on a project that already keeps a dated planning file with checkbox tasks.

When not to use it

Skip it on repositories without planning files or `.claude/ai-context` context, or when you want code analysis rather than a quick status recap.

Security analysis

Caution
Quality score82/100

The skill does not perform destructive, exfiltrating, or obfuscated actions, and its shell usage is limited to reading planning files and inspecting git state. However, because it uses bash/git without declaring allowed-tools, it falls under caution rather than fully safe.

Findings
  • β€’No allowed-tools declared, yet the skill instructs bash/git usage.
  • β€’Uses shell commands for reading planning files and git log/status; these are read-only but still require filesystem/shell access.
How this analysis is made

Examples

Resume a session
Where did I leave off? Check the latest planning file and my git status, then tell me the next task to work on.
Phase progress table
Run /next and show me which phases are done and how many tasks are left.
Kick off the next task
Check my progress and suggest what to start next, then get me going on it.

name: next description: Session start - check progress, suggest next task required_context:

  • .claude/ai-context/architecture.md

Next

Flow

Read Planning β†’ Git Log β†’ Analyze β†’ Present β†’ Suggest /clarify

Execution

  1. Read Planning

    # Read ONLY the latest planning file (by date prefix YYYYMMDD-)
    # e.g., 20260205-improvements.md > 20260128-cli-parsers.md
    # Check checkbox status: [ ] incomplete, [x] complete
    
  2. Git Log

    git log --oneline -5
    git status --short
    
  3. Analyze

    • Identify current phase
    • Count completed/total tasks
    • Identify next priority task
  4. Present (table format) | Phase | Status | Progress | |-------|--------|----------| | Phase 0 | βœ… | 5/5 | | Phase 1 | πŸ”„ | 3/4 |

  5. Suggest

    • Summarize next task
    • Suggest running /clarify

Output Format

## Current Status
- Phase: {current_phase}
- Progress: {completed}/{total} tasks

## Next Task
**{task_id}: {task_name}**
{brief_description}

## Action
Run `/clarify` to start: {task_summary}

Rules

  • Read only the latest dated planning file (highest YYYYMMDD- prefix)
  • If no planning files β†’ infer from git log + code state
  • Keep output concise (5-10 lines)
  • Always suggest /clarify connection

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/check-progress-and-suggest-next-task-mm5t89do/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/check-progress-and-suggest-next-task-mm5t89do' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/check-progress-and-suggest-next-task-mm5t89do/download' --output '.skill-downloads/check-progress-and-suggest-next-task-mm5t89do/SKILL.md.part' && mv '.skill-downloads/check-progress-and-suggest-next-task-mm5t89do/SKILL.md.part' '.skill-downloads/check-progress-and-suggest-next-task-mm5t89do/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/check-progress-and-suggest-next-task-mm5t89do/SKILL.md' && test -s '.skill-downloads/check-progress-and-suggest-next-task-mm5t89do/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/next' && cp -R '.skill-downloads/check-progress-and-suggest-next-task-mm5t89do' '.claude/skills/next'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js β‰₯ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/check-progress-and-suggest-next-task-mm5t89do'

openskills read 'check-progress-and-suggest-next-task-mm5t89do'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/check-progress-and-suggest-next-task-mm5t89do/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills