mecris-plan
Standardizes the planning process by requiring a formal spec before any work starts.
Install
mkdir -p .claude/skills/mecris-plan && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/10495" && unzip -o skill.zip -d .claude/skills/mecris-plan && rm skill.zipInstalls to .claude/skills/mecris-plan
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Write a minimal spec as a GitHub issue before acting. Takes the recommended action from mecris-orient and records intent, rationale, and validation criteria. This is the red in red-green-archive. Trigger with /mecris-planKey capabilities
- →Draft GitHub issues
- →Record intent
- →Define validation criteria
- →Open planning issues
How it works
Creates a structured GitHub issue containing intent, rationale, and validation criteria based on orienting reports.
Inputs & outputs
When to use mecris-plan
- →Write a spec for a task
- →Create a planning issue
- →Validate task intent
About this skill
mecris-plan
Spec-writing skill for the Mecris accountability system. Before any code is touched or action is taken, write a three-line GitHub issue on yebyen/mecris recording what will be done, why, and how to know it worked. Consumes the orient report. Produces an auditable spec.
When to Activate
- After
/mecris-orienthas produced a situation report with a recommended action - Before writing any code, making any commit, or triggering any workflow
- When the user says "plan", "write the spec", "what's the plan", "/mecris-plan"
Slash Command
/mecris-plan
Runs the full planning workflow:
- Take the recommended action from the current orient report (must have run
/mecris-orientfirst) - Draft a three-part spec:
- Intent: one sentence — what will be done
- Because: one sentence — what in the orient report motivates this
- Validation: one sentence — how to confirm it worked
- Open a GitHub issue on yebyen/mecris with title
[plan] {intent}and body containing all three parts - RECORD the issue number in your internal scratchpad/history immediately — you will need it for
/mecris-archive. - VERIFY that the issue creation was successful before proceeding to work.
Usage: Type /mecris-plan after orienting. The spec issue will be opened before any action proceeds.
Spec Format
Issue title: [plan] {one-line description of action}
Issue body:
**Intent**: {what will be done — specific and concrete}
**Because**: {what orient showed that motivates this — cite the source: issue number, commit, or NEXT_SESSION.md item}
**Validation**: {observable outcome that confirms success — test pass, issue closed, datapoint in Beeminder, etc.}
Examples
Sync from upstream
[plan] Sync yebyen/mecris from kingdonb/mecris main (18 commits behind)
**Intent**: Fetch and merge kingdonb/mecris main into yebyen/mecris.
**Because**: Orient showed yebyen/mecris is 18 commits behind upstream with no merge conflicts anticipated.
**Validation**: `git rev-list --count HEAD..upstream/main` returns 0.
Fix a bug
[plan] Fix multiplier lever SQL query to respect user_id column
**Intent**: Update the SQL in the Rust service to use the composite primary key (user_id, language_name).
**Because**: NEXT_SESSION.md lists multiplier sync as unverified; issue #122 reports persistence race condition.
**Validation**: `SELECT pump_multiplier FROM language_stats WHERE user_id = ?` returns the value set in the Android app.
Trigger pr-test
[plan] Run pr-test for kingdonb/mecris#142
**Intent**: Dispatch the pr-test workflow against PR #142 and post results as a comment.
**Because**: Orient found issue tagged needs-test referencing PR #142.
**Validation**: Comment posted on kingdonb/mecris#142 with ✅ or ❌ for both Python and Android tests.
Notes
- This skill opens exactly one issue per invocation — no more
- The issue stays open until
/mecris-archivecloses it - If orient did not run first, run
/mecris-orientbefore proceeding - In bot context: the plan issue is the only thing an outside observer can see before the work starts — make it legible to a human
- Keep specs small: if the intent requires more than one sentence, the action is too large — split it
When not to use it
- →Without running mecris-orient first
- →For large tasks requiring multiple issues
Prerequisites
Limitations
- →Opens exactly one issue per invocation
- →Requires orient report to be present
How it compares
Forces a planning phase before any code is touched, ensuring accountability and clear specs.
Compared to similar skills
mecris-plan side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| mecris-plan (this skill) | 0 | 4mo | No flags | Beginner |
| task-master | 22 | 6mo | Review | Intermediate |
| github-project-management | 4 | 6mo | Review | Advanced |
| issue-manage | 2 | 5mo | Review | Beginner |
Try saying
Example prompts that trigger this skill in your AI assistant.
You might also like
task-master
sfc-gh-dflippo
AI-powered task management for structured, specification-driven development. Use this skill when you need to manage complex projects with PRDs, break down tasks into subtasks, track dependencies, and maintain organized development workflows across features and branches.
github-project-management
ruvnet
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
issue-manage
catlog22
Interactive issue management with menu-driven CRUD operations. Use when managing issues, viewing issue status, editing issue fields, performing bulk operations, or viewing issue history. Triggers on "manage issue", "list issues", "edit issue", "delete issue", "bulk update", "issue dashboard", "issue history", "completed issues".
issue-maker
pollinations
Create GitHub issues following Pollinations team conventions. Use when asked to create issues, track work, or plan features.
create-issue
dotCMS
Create GitHub issues using repository templates. Use when the user asks to create an issue, bug report, feature request, task, spike, epic, or UX requirement. Also use when the user describes a problem, bug, enhancement, or work item that should be tracked. Supports both English and Spanish input.
issue-discover
catlog22
Unified issue discovery and creation. Create issues from GitHub/text, discover issues via multi-perspective analysis, or prompt-driven iterative exploration. Triggers on "issue:new", "issue:discover", "issue:discover-by-prompt", "create issue", "discover issues", "find issues".