agentleFS
Sign inStart free
theyoungastronautstheyoungastronauts/polaris/skills/execute/SKILL.md

execute

Skill4 starsChanged 3 months agoMITView on GitHub

Execute one phase of an implementation plan — plan mode, implement, test, summarize; leaves changes uncommitted for the reviewer.

57 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use context-optimize, ralplan and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • ibahgatSkill

    context-optimize

    Improve context efficiency and cache stability for long or complex sessions.

    Also in 3 projects that use this

  • ibahgatSkill

    ralplan

    Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

    Also in 5 projects that use this

  • Yeachan-HeoSkill

    ultragoal

    Create and execute durable repo-native multi-goal plans over Codex goal mode artifacts.

    Also in 4 projects that use this

  • buddyhSkill

    deep-dive

    Deep dive on any topic. Decomposes into subtopics, researches each in parallel with thorough source gathering, then synthesizes into a comprehensive report (4,000-10,000+ words, 40-100+ sources). Scales depth dynamically based on topic complexity. Use when asked for a deep dive, deep research, comprehensive analysis, or thorough investigation of a topic.

    Also in 4 projects that use this

  • mukcoSkill

    principles

    General software engineering principles — DRY, SOLID, YAGNI, KISS, naming, code smells, and refactoring. Language-agnostic. Use alongside language-specific skills.

    Also in 3 projects that use this

  • team-attentionSkill

    compound

    This skill should be used when the user says "/compound", "compound this", "document learnings", "save what we learned", or after completing a PR. Extracts knowledge from PR context and saves to docs/learnings/.

    Also in 3 projects that use this

  • +1 more from ibahgat

The file

We split this skill into the rules it gives an agent

8 rules. 0 are common, 6 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 55 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Look for plan.md in the current directory, then ../plan.md.

    line 13
  2. Distinctive:

    If the user specified a phase number, use that.

    line 17
  3. Distinctive:

    Read existing code before modifying anything

    line 36
  4. Distinctive:

    Write tests alongside implementation, not after

    line 37
  5. Distinctive:

    Do not commit: Leave all changes staged/unstaged.

    line 38
  6. Distinctive:

    If something in the plan doesn't make sense after seeing the actual code, stop and flag it rather than blindly following.

    line 41
  7. Very specific:

    If this phase produces or changes API endpoints, generate an integration summary at docs/integration/[feature].md covering endpoints, …

    line 45
  8. Distinctive:

    When the phase is complete, provide a summary:

    line 49

“Common” is measured: kept by at least 6 in 10 of the 55 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Execute a Phase

You are executing a phase of an implementation plan. Follow these steps exactly.

1. Find the Plan

Look for plan.md in the current directory, then ../plan.md. If not found, ask the user where it is.

2. Identify the Phase

If the user specified a phase number, use that. Otherwise, review the plan and ask which phase to execute. Show a brief summary of each phase so the user can pick.

3. Plan the Implementation

If a /autopilot or /orchestrator lead spawned you against a pre-approved plan.md, skip plan mode — the approved plan is your approval. Explore the codebase as needed and go straight to implementation.

In an interactive session, enter plan mode before writing any code. Read through the phase tasks, explore the existing codebase, and present a concrete implementation plan:

  • Which files you'll create or modify
  • What approach you'll take for each task
  • What order you'll work in
  • Any decisions or trade-offs the user should weigh in on

The user can adjust the approach, reorder tasks, or flag concerns before any code is written. Only exit plan mode and start implementing after the user approves.

4. Implement

Work through each task in the phase sequentially:

  • Read existing code before modifying anything
  • Write tests alongside implementation, not after
  • Do not commit. Leave all changes staged/unstaged. The verifier will commit after the phase passes verification.
  • Stay within the phase scope — if you find work that belongs in another phase, note it but don't do it

If something in the plan doesn't make sense after seeing the actual code, stop and flag it rather than blindly following.

5. Integration Summary (if applicable)

If this phase produces or changes API endpoints, generate an integration summary at docs/integration/[feature].md covering endpoints, request/response shapes, auth, and error codes.

6. Wrap Up

When the phase is complete, provide a summary:

  • What was implemented
  • Files changed (list them)
  • Any deviations from the plan and why
  • Any concerns or notes for the next phase

Suggest running /verify in a new session as the next step.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free